Skills

Derived: every skill markdown file, with the description it declares in its own front matter.

This is an index, not the documentation. It says what exists and what each artefact declares about itself. What a process is for, when you would be in it, and what it is not, is authored beside it and reuses these entries rather than restating them — see the auto-docs skill.
ArtefactWhat it declares about itself
block-density
cat-harness/skills/authoring/authoring-core/block-density.md		Audits individual content blocks for single-topic coherence, length, and embedded tables.
canonical-watcher
cat-harness/skills/authoring/authoring-core/canonical-watcher.md		Derivation-discipline integration watcher — watches the default branch + open active PRs + newly-opened PRs for non-canonical empirical / fitting / calibration inputs beyond the project's declared set, numerology, or ju…
chapter-complexity-review
cat-harness/skills/authoring/authoring-core/chapter-complexity-review.md		Analyse a chapter's internal dependency graph to find backward edges (blocks that reference something defined later), compute graph energy, and suggest section/block reorderings that minimise complexity.
compute-integration-watcher
cat-harness/skills/authoring/authoring-core/compute-integration-watcher.md		Cross-layer wiring auditor — watches for newly-landed formal/analytic improvements (proofs, propositions, lemmas, axiom→theorem upgrades, witness data) on the default branch AND on open PRs, and checks whether each one…
content-graph
cat-harness/skills/authoring/authoring-core/content-graph.md		Editorial graph analysis skill — builds a content graph from uses[], interprets, proofs, and examples relationships; builds a chapter/section topology graph; and applies heuristics to identify forward references, cross-…
content-profiles
cat-harness/skills/authoring/authoring-core/content-profiles.md		Adapters and profiles are different axes and conflating them is costly.
detangler-integration-watcher
cat-harness/skills/authoring/authoring-core/detangler-integration-watcher.md		Structural-QA integration watcher — watches the default branch + open active PRs + newly-opened PRs for organisational changes (paper / chapter manifest edits, new blocks, edited uses[] / kind / label / `interpret…
devils-advocate-watcher
cat-harness/skills/authoring/authoring-core/devils-advocate-watcher.md		Logical devil's-advocate integration watcher — for every content block (.ts/.md) and formal sibling, constructs the strongest adversarial case that it is WRONG: the objection a hostile-but- competent referee would raise…
editor
cat-harness/skills/authoring/authoring-core/editor.md		no description in the artefact
evidence-review
cat-harness/skills/authoring/authoring-core/evidence-review.md		Evidence review as an instance of untainted verification — the separation of the appraising party from the drafting party, what recurring surveillance in a living guideline shares with a stale QA verdict, and which of g…
exposition-swarm-drain
cat-harness/skills/authoring/authoring-core/exposition-swarm-drain.md		Drain the paper's narrative blocks through an exposition-quality swarm: a small fleet of grouped-batch agents each audit their batch against the Milnor exposition gate (expo-milnor-clarity, H1–H8) plus the deterministic…
integration-audit
cat-harness/skills/authoring/authoring-core/integration-audit.md		Sidecar-invalidation utility for the integration-watcher pipeline.
md-authoring
cat-harness/skills/authoring/authoring-core/md-authoring.md		no description in the artefact
milnor-exposition-standard
cat-harness/skills/authoring/authoring-core/milnor-exposition-standard.md		The eight hallmarks of mathematical exposition, scored 0-2 with sixteen the only passing total, derived from John Milnor's "Link Groups" (1954).
one-voice-audit
cat-harness/skills/authoring/authoring-core/one-voice-audit.md		no description in the artefact
one-voice-integration-watcher
cat-harness/skills/authoring/authoring-core/one-voice-integration-watcher.md		One-voice integration watcher — watches origin/main + open active PRs + newly-opened PRs for content-block changes (.md, .ts, proof files), runs the per-block QA suite covering scholarly voice, AI-slop detection, se…
one-voice-style-guide
cat-harness/skills/authoring/authoring-core/one-voice-style-guide.md		Author voice profile and narrative style guide.
production-vs-exploratory-discipline
cat-harness/skills/authoring/authoring-core/production-vs-exploratory-discipline.md		Distinguish PRODUCTION (derived-only, no fits) from EXPLORATORY (empirical-fit probes OK as shape-hints) from NUMEROLOGY (post-hoc fits to known constants).
readability-editing
cat-harness/skills/authoring/authoring-core/readability-editing.md		no description in the artefact
review-heatmap
cat-harness/skills/authoring/authoring-core/review-heatmap.md		The review page's heat map: a section-by-metric table that tells a reviewer of a large document where to look first.
scientific-accuracy
cat-harness/skills/authoring/authoring-core/scientific-accuracy.md		no description in the artefact
technical-documentation
cat-harness/skills/authoring/authoring-core/technical-documentation.md		Write and review technical documentation of standards, software and knowledge assets as an SDO writes.
todo-review
cat-harness/skills/authoring/authoring-core/todo-review.md		Monitor and triage open feedback across all content blocks.
uses-editorial-review
cat-harness/skills/authoring/authoring-core/uses-editorial-review.md		Adjudicate uses-editorial-completeness — read a block as a reader would and judge whether its uses[] is complete and genuinely expository.
voice-authoring-guidance
cat-harness/skills/authoring/authoring-core/voice-authoring-guidance.md		Load the active voices' rules BEFORE writing, so a block is drafted in the register it will be reviewed against.
voice-editorial-review
cat-harness/skills/authoring/authoring-core/voice-editorial-review.md		Adjudicate a voice-* finding — read the flagged passage as a reader of THAT genre would and decide whether the register is wrong, the criterion is out of scope, or the block is a stated exception.
voice-overlay-review
cat-harness/skills/authoring/authoring-core/voice-overlay-review.md		Review a block against the active voices' rules and record the verdict on its QA sidecar.
content-author
cat-harness/skills/authoring/content-lifecycle/content-author.md		no description in the artefact
content-feedback
cat-harness/skills/authoring/content-lifecycle/content-feedback.md		no description in the artefact
content-plan
cat-harness/skills/authoring/content-lifecycle/content-plan.md		no description in the artefact
content-publish
cat-harness/skills/authoring/content-lifecycle/content-publish.md		no description in the artefact
content-retire
cat-harness/skills/authoring/content-lifecycle/content-retire.md		no description in the artefact
content-review
cat-harness/skills/authoring/content-lifecycle/content-review.md		no description in the artefact
content-test
cat-harness/skills/authoring/content-lifecycle/content-test.md		no description in the artefact
content-validate
cat-harness/skills/authoring/content-lifecycle/content-validate.md		no description in the artefact
evidence-appraisal
cat-harness/skills/authoring/content-lifecycle/evidence-appraisal.md		no description in the artefact
ig-publisher-service-contract
cat-harness/skills/authoring/content-lifecycle/ig-publisher-service-contract.md		The contract the ig-publisher-service role is held to: what the JVM services an IG build shells out to must produce, and how a caller tells a pass from a run that never happened.
lean-toolchain-contract
cat-harness/skills/authoring/content-lifecycle/lean-toolchain-contract.md		The contract the lean-toolchain role is held to: what a Lean toolchain must answer when a paper folio's formal half is built, and what it must not be asked.
agent-memory
cat-harness/skills/conduct/conduct-core/agent-memory.md		Durable memory for a subagent — the three entry labels and what each promises, why entries are authored as graph nodes rather than in the generated file, the injection budget that silently truncates, and archiving as th…
agent-permissions
cat-harness/skills/conduct/conduct-core/agent-permissions.md		Securing what a coding agent may do without asking, from the person who can grant it: the secure-agent-permissions sub-process, run at session start and on demand when an action is denied.
communication-language
cat-harness/skills/conduct/conduct-core/communication-language.md		Determine the language an agent SPEAKS IN — the language of a turn, as against the language of content.
confirmation-waiver
cat-harness/skills/conduct/conduct-core/confirmation-waiver.md		A human may waive a confirmation they are owed — for a session, for a process run, or until a stated time.
decision-comparison
cat-harness/skills/conduct/conduct-core/decision-comparison.md		Lay a decision out as a comparison before you ask it — what each option does, its pro, its con, what it changes downstream, and how reversible it is — in the prose that precedes the question, never inside the option lab…
deletion-requires-confirmation
cat-harness/skills/conduct/conduct-core/deletion-requires-confirmation.md		An agent never removes a durable artefact on its own initiative.
getting-started
cat-harness/skills/conduct/conduct-core/getting-started.md		Triage what a person means when they ask to create a folio, and route them.
harness-projections
cat-harness/skills/conduct/conduct-core/harness-projections.md		Who may write under .claude/, and when.
interaction-modality
cat-harness/skills/conduct/conduct-core/interaction-modality.md		Establish how to talk to the person in front of you before deciding what to say — audio, ordinary chat, selectable options for limited hand function, large-type for low vision, plain language — and hold that choice dura…
repo-conversion
cat-harness/skills/conduct/conduct-core/repo-conversion.md		Lay folio-assistant over a repository that already exists, without losing or silently moving what is in it.
retry-backoff
cat-harness/skills/conduct/conduct-core/retry-backoff.md		Every error gets a falling-off retry rate — each wait doubles, with jitter.
symbiotic-interaction
cat-harness/skills/conduct/conduct-core/symbiotic-interaction.md		Recognize and respond to the three epistemic registers of author input — Socratic steer (known-answer correction), honest gap (flagged unknown), and intuition seed (tenuous cross-domain identification) — with the coacti…
untrusted-input
cat-harness/skills/conduct/conduct-core/untrusted-input.md		Keep attacker-controlled values out of program text — in GitHub Actions, in command lines, in anything that is parsed before it runs.
unverified-constraints
cat-harness/skills/conduct/conduct-core/unverified-constraints.md		Never encode a constraint you have not verified — a rule that refuses a working setup is worse than no rule.
where-does-this-go
cat-harness/skills/conduct/conduct-core/where-does-this-go.md		The router for filing decisions.
injection-boundaries
cat-harness/skills/conduct/security/injection-boundaries.md		Where a value becomes program rather than data — workflow expressions, shell strings, and archive members.
path-containment
cat-harness/skills/conduct/security/path-containment.md		Turning a value from outside into a path.
security
cat-harness/skills/conduct/security/security.md		The security sub-KG's entry point.
zero-trust-handover
cat-harness/skills/conduct/security/zero-trust-handover.md		How this platform applies zero trust (the zero-trust-architecture methodology, NIST SP 800-207) to every hand-over between agents, skills, tools and graphs: rules H1-H9, the hand-over screen and where it is wired, the r…
covered-is-not-reachable
cat-harness/skills/folio-core/covered-is-not-reachable.md		A skill can be satisfied by the neighbours of its mechanism while the mechanism is reachable from no Tool node.
mcp-assembly
cat-harness/skills/folio-core/mcp-assembly.md		Compose several Tool nodes into one MCP service — naming, collisions, grouping and versioning.
mcp-contract
cat-harness/skills/folio-core/mcp-contract.md		Verify an MCP service's tools against the Tool nodes and skill declarations they came from — I/O equivalence in both directions.
mcp-projection
cat-harness/skills/folio-core/mcp-projection.md		Generate an MCP server from Tool nodes — the mapping from this harness's skill/Tool vocabulary onto the current MCP standard.
skills-and-tools
cat-harness/skills/folio-core/skills-and-tools.md		A skill states a capability generically; a Tool node carries the concrete mechanism.
tool-authoring
cat-harness/skills/folio-core/tool-authoring.md		How concrete Tools are authored, structured, packaged, and registered across the separated multi-repository platform: defining Knowledge Graph Tool nodes, implementing TypeScript handlers in the tools repository, regist…
domain-fencing
cat-harness/skills/kg/graph-management/domain-fencing.md		How a domain-specific rule is kept out of the platform without being lost — the opt-in axis mechanism, the one criterion that should use it and does not, and the test for whether a rule generalizes at all.
edge-kinds-and-blast-radius
cat-harness/skills/kg/graph-management/edge-kinds-and-blast-radius.md		A graph has more than one kind of edge, and conflating them corrupts both the ordering and the impact answer.
graph-detanglement
cat-harness/skills/kg/graph-management/graph-detanglement.md		Drive a tangled graph toward a clean partition, so a sub-graph can be split off when it grows too large or when a business reason separates it.
graph-rendering
cat-harness/skills/kg/graph-management/graph-rendering.md		Draw any graph in a harness (schemas, processes, a paper's block graph, a Lean proof's dependencies, a detangle partition) so the picture is derived, checkable and readable.
kg-separation
cat-harness/skills/kg/graph-management/kg-separation.md		Separate a Knowledge Graph into its own repository — as a CONTENT repository (files to read, no code) and a TOOLS repository (the code that writes and checks it) — once it is too large, or its consumers or cadence diffe…
kg-subgraph-layout
cat-harness/skills/kg/graph-management/kg-subgraph-layout.md		Lay out one declared sub-graph of a knowledge graph (a harness's schema overview, one named sub-graph, a declaration's kinds) as a single Graphviz diagram in the i2ce Form Documentor's convention, and show it on the sit…
lsi-indexing
cat-harness/skills/kg/graph-management/lsi-indexing.md		Build, read and audit a Latent Semantic Indexing index over a declared prose graph — a library, the skills, the beans, docs — to find units that discuss the same thing in different words, near-duplicates, outlier cluste…
named-query-execution
cat-harness/skills/kg/graph-management/named-query-execution.md		How to execute audited SPARQL 1.1 named queries over partitioned W3C N-Quads dataset distributions across CLI, MCP tools, and WebAssembly browser clients.
nquads-distribution
cat-harness/skills/kg/graph-management/nquads-distribution.md		How to compile, partition by named subgraphs, and distribute W3C N-Quads datasets beside pre-compiled SPARQL 1.1 named queries for static edge and client-side querying.
sub-kg-lifecycle
cat-harness/skills/kg/graph-management/sub-kg-lifecycle.md		A sub-KG is a knowledge graph staged as a directory inside a harnessed repository, declared as its own instance, that may later leave for a repository of its own.
artefact-reachability
cat-harness/skills/kg/kg-core/artefact-reachability.md		Which declared executable artefacts can be reached — decision tables, BPMN diagrams, self-declared entry points.
associate-harness
cat-harness/skills/kg/kg-core/associate-harness.md		Declare a harness this one knows about and does not hold (associatedHarnesses): a folio in another repository, published at its own site.
audit-coverage
cat-harness/skills/kg/kg-core/audit-coverage.md		Which audits reach which KIND of node, measured rather than inferred.
code-node-review
cat-harness/skills/kg/kg-core/code-node-review.md		Review the knowledge graph's CODE nodes — Tool definitions in the tools graph and schema definition nodes under schemas/ — for the joins a reader cannot see: that a node declares what it is, that what it names resol…
content-context-and-state-graphs
cat-harness/skills/kg/kg-core/content-context-and-state-graphs.md		Every declared graph is the subject a process produces, static context it reads, or live state it writes.
corpus-grep
cat-harness/skills/kg/kg-core/corpus-grep.md		Pre-declaration corpus check.
data-modelling
cat-harness/skills/kg/kg-core/data-modelling.md		Build a data model: identify the entities a body of work is actually about, the relations between them, and the cardinalities — then declare it where the tools can read it.
directory-conventions
cat-harness/skills/kg/kg-core/directory-conventions.md		no description in the artefact
external-registry-contract
cat-harness/skills/kg/kg-core/external-registry-contract.md		The contract the external-registry role is held to: what a trusted registry outside this instance must provide for a portal to verify what it received, and what the verifier does when it cannot.
flushable-containers
cat-harness/skills/kg/kg-core/flushable-containers.md		A flushable container is a named store that accumulates by design — a trash you can recover from, a review preview, a console log.
fsh-guts
cat-harness/skills/kg/kg-core/fsh-guts.md		The trashcan that is kept — where work that is not wanted goes instead of being deleted, what declares itself there, and what does NOT belong.
harness-requirements
cat-harness/skills/kg/kg-core/harness-requirements.md		What an instance OWES for every directory it declares — a visualiser, a documentation entry, a governing skill, json/jsonld/schema.json serialisations at the directory's URL and at every node beneath it, and a starting…
index-config
cat-harness/skills/kg/kg-core/index-config.md		index.config.json at an instantiation root says which harnesses the checkout instantiates, where each one comes from (local, or a remote mount pinned to a SHA), each instance's config INLINE in its entry (a legacy `<n…
instance-kinds
cat-harness/skills/kg/kg-core/instance-kinds.md		How to make a new KIND of harness instance — choosing the prefix family, the keep-the-kind's-name default and the owner's right to decline it, which inherited files the new owner may repoint, and what a new GRAPH typolo…
instance-publication
cat-harness/skills/kg/kg-core/instance-publication.md		Every asset carries an id and a version and sits in DRAFT.
kg-contribution-offer
cat-harness/skills/kg/kg-core/kg-contribution-offer.md		Ask whether agreed requirements should become knowledge-graph content, and as what — in a form the person can answer by selecting.
kg-export
cat-harness/skills/kg/kg-core/kg-export.md		Serialize an instance's knowledge graph to one JSON document, for publication and inspection.
kg-to-portal
cat-harness/skills/kg/kg-core/kg-to-portal.md		Getting a knowledge graph out to a public portal — the six stages between "the graph is in the repository" and "a reader's browser has the bytes", why a CDN is a layer rather than a publication host, and which decisions…
npm-kg-distribution
cat-harness/skills/kg/kg-core/npm-kg-distribution.md		Package, release, distribute, and retrieve Knowledge Graphs using npm tooling and tarballs: declare package.json as an authored pre-packaging asset in the Knowledge Graph, build .tgz packages via bun pm pack, reco…
placement
cat-harness/skills/kg/kg-core/placement.md		Establish where a new node belongs BEFORE you create it — which instance, which declared graph, which kind of node, and which of the two "stub" conventions applies.
remote-mount
cat-harness/skills/kg/kg-core/remote-mount.md		Bring a harness, and every instance it depends on, into a checkout that does not hold it, from another repository at a pinned commit, as declared directories with a lock: a source.remote entry in the downstream's root…
schema-management
cat-harness/skills/kg/kg-core/schema-management.md		Manage a schema over its life — add one, change one, read the schema graph and its viewer, and act on what the reader could not determine.
skill-registration
cat-harness/skills/kg/kg-core/skill-registration.md		Adding a skill is never a one-file change.
skill-voice-review
cat-harness/skills/kg/kg-core/skill-voice-review.md		Reviews a skill against a voice that judges skills — the base agent-skill-authoring voice or a vendor override such as Claude's, Gemini CLI's or OpenAI's — rule by rule, with each rule's citation open, and records the…
surprise-to-corpus
cat-harness/skills/kg/kg-core/surprise-to-corpus.md		What was unexpected in that task, and does it belong in the corpus? Logical surprise is the detectable kind, recurrence is the filter that stops this generating noise every turn, and the agent PROMPTS — it never writes…
uml-overview
cat-harness/skills/kg/kg-core/uml-overview.md		Read, regenerate or extend the UML class diagrams of a harness: one per harness and one per named sub-graph it declares, plus the harness object model.
vocabulary-authority
cat-harness/skills/kg/kg-core/vocabulary-authority.md		One vocabulary is authoritative for one kind of fact, and every other is a derived rendering reached by a declared mapping.
kg-navigation
cat-harness/skills/kg/kg-navigation/kg-navigation.md		How a cold agent finds and loads the skill that governs its task.
copy-out-materialized
cat-harness/skills/library/large-datasets/copy-out-materialized.md		Materialized content is read-only.
kg-subscription
cat-harness/skills/library/large-datasets/kg-subscription.md		Subscribing a folio or harness to an external knowledge graph — a substrate — and walking its parts from referenced to materialised, one at a time and only through the shared materialisation gates.
materialize-on-demand
cat-harness/skills/library/large-datasets/materialize-on-demand.md		After bootstrap, a person asks for part of a remote subgraph to be held locally.
materialize-remote
cat-harness/skills/library/large-datasets/materialize-remote.md		Landing remote content locally — the five gates, the three states, and the two purposes.
sample-import
cat-harness/skills/library/large-datasets/sample-import.md		Testing an import of a SAMPLE of a remote source into a knowledge graph or other structured store: scope it, let materialize-remote gate it, land it in the library (permanent) or the kept, unpublished trashcan (trial),…
adopt-methodology-from-source
cat-harness/skills/library/library-core/adopt-methodology-from-source.md		The general process for turning a shared paper, book or standard into an adopted methodology: establish origin and licence, ingest the source, find and summarize related beans and issues and ask whether to coordinate, r…
asset-extraction
cat-harness/skills/library/library-core/asset-extraction.md		Reading a container — a zip, a PDF, a saved web page — into the knowledge graph.
code-lists
cat-harness/skills/library/library-core/code-lists.md		Author, extend or consume a code list: a closed set of codes, each with a label, a definition and a source, kept as a node and published as SKOS.
content-acquisition
cat-harness/skills/library/library-core/content-acquisition.md		Getting a resource INTO the graph in the first place — accepting one offered unprompted, or asking for one and then asking for it to be uploaded.
library-ingestion
cat-harness/skills/library/library-core/library-ingestion.md		The BASIC ingestion flow every asset takes: an upload is accepted, its metadata goes into the knowledge graph, and the asset lands in library/<slug>/ if it is materialized.
literature-search
cat-harness/skills/library/library-core/literature-search.md		Finding the source a node cites but does not hold — memory first, then this repository, then open-access services.
term-disagreement
cat-harness/skills/library/library-core/term-disagreement.md		When a glossary term the extractor minted and an authorised terminology disagree — the corpus spells a concept differently from the authority, or uses a word the authority does not carry — decide among three outcomes: c…
translation-manager
cat-harness/skills/library/library-core/translation-manager.md		Translation lifecycle management for folio content.
upload-naming
cat-harness/skills/library/library-core/upload-naming.md		What an ingested file may be CALLED.
upload-routes
cat-harness/skills/library/library-core/upload-routes.md		How a file actually REACHES uploads/ — the two mechanisms that write bytes into a declared queue, the persona that performs one of them on somebody's behalf, and what each writer owes that the route does not do for th…
uploads-watch
cat-harness/skills/library/library-core/uploads-watch.md		Notice what has landed in the acquisition queue, and tell an arrival from a backlog.
compiled-artefact-cache
cat-harness/skills/process/process-core/compiled-artefact-cache.md		The general pattern for caching expensive compiled artefacts (Lean .oleans, FHIR ASTs) across builds.
decision-methodology-selector
cat-harness/skills/process/process-core/decision-methodology-selector.md		Given a decision context, select the applicable methodology from the methodology graph.
methodology-adoption
cat-harness/skills/process/process-core/methodology-adoption.md		How a named external methodology enters the knowledge graph, and how an agent picks which one applies.
role-model
cat-harness/skills/process/process-core/role-model.md		Actors, roles and skills — who performs a BPMN task, under which swimlane, with which skills.
swimlane-glossary
cat-harness/skills/process/process-core/swimlane-glossary.md		no description in the artefact
swot-analysis
cat-harness/skills/process/process-core/swot-analysis.md		Running a SWOT situation analysis — the four activities of swot-analysis.bpmn, what each step must produce, and the one thing the technique must never be used for.
task-authorization
cat-harness/skills/process/process-core/task-authorization.md		The check every BPMN task execution runs before anything is recorded: is the actor authenticated, assigned to the role the lane binds, authorized by an ODRL policy to perform the task, and allowed access to the content…
raci
cat-harness/skills/process/raci/raci.md		RACI over this repository's processes — who is Responsible, Accountable, Consulted and Informed for each activity.
bpmn-authoring
cat-harness/skills/process/workflow/bpmn-authoring.md		no description in the artefact
bpmn-processes
cat-harness/skills/process/workflow/bpmn-processes.md		Every process here is BPMN, the diagrams are executable, and the base processes are strict.
branch-freshness
cat-harness/skills/process/workflow/branch-freshness.md		Periodically rebase or merge main into the feature branch, detect what changed upstream, and re-analyse the session workplan.
code-review-process
cat-harness/skills/process/workflow/code-review-process.md		Where code review sits in the release lifecycle.
deterministic-and-agentic
cat-harness/skills/process/workflow/deterministic-and-agentic.md		Workflow processing is a SPECTRUM, not a switch.
dmn-authoring
cat-harness/skills/process/workflow/dmn-authoring.md		no description in the artefact
process-state
cat-harness/skills/process/workflow/process-state.md		Track where you are inside a running process — which task, in which swimlane, under which role — and recover deliberately when you find yourself outside it.
release-epic-planning
cat-harness/skills/process/workflow/release-epic-planning.md		Plan and track releases using bean epics.
release-lifecycle
cat-harness/skills/process/workflow/release-lifecycle.md		Governs the release lifecycle: semver policy, draft/named releases, changelogs, release gating, and the relationship between feature branches, PRs, beans, and releases.
render-kg-to-cdn
cat-harness/skills/process/workflow/render-kg-to-cdn.md		Render a Knowledge Graph, or a list of its Subgraphs, for publication to a CDN at a publication root URL, and report a status and one message.
session-context
cat-harness/skills/process/workflow/session-context.md		What a state machine tracks across a session, as against one process instance.
session-state-machine
cat-harness/skills/process/workflow/session-state-machine.md		An agent PLAYING a state machine rather than an engine executing one.
specification-compiled-agents
cat-harness/skills/process/workflow/specification-compiled-agents.md		When a diagram already says what the process is, the model should not be planning it.
workflow-state
cat-harness/skills/process/workflow/workflow-state.md		Where a running process keeps what it knows, and which store answers which question.
crdm-data-model
cat-harness/skills/sdlc/crdm/crdm-data-model.md		The CRDM data-modelling phase — when in the requirements process a model is built, what it is built from, who confirms it, and what it hands to the phases either side.
crdm-detect
cat-harness/skills/sdlc/crdm/crdm-detect.md		Detect when a request needs requirements agreed before anything is built, and which of the two parallel requirements methodologies governs it.
crdm-impact-analysis
cat-harness/skills/sdlc/crdm/crdm-impact-analysis.md		Guide for CRDM Phase 4 — Impact Analysis and Migration Planning.
crdm-needs-assessment
cat-harness/skills/sdlc/crdm/crdm-needs-assessment.md		Facilitate Phase 1 (Needs Assessment) of the CRDM requirements workflow.
crdm-recorded-walkthrough
cat-harness/skills/sdlc/crdm/crdm-recorded-walkthrough.md		Turn a recorded requirements walkthrough (a video call where a business analyst demonstrates a feature and a stakeholder asks for changes) into CRDM Phase 3 requirements with evidence: transcripts compared, an independe…
crdm-requirements-template
cat-harness/skills/sdlc/crdm/crdm-requirements-template.md		Guide and template for CRDM Phase 3 — Requirements Definition.
crdm-requirements-workflow
cat-harness/skills/sdlc/crdm/crdm-requirements-workflow.md		no description in the artefact
activity-log
cat-harness/skills/sdlc/sdlc-core/activity-log.md		no description in the artefact
adjudication
cat-harness/skills/sdlc/sdlc-core/adjudication.md		Settle a review that reached no mechanical or consensus agreement.
adversarial-code-review
cat-harness/skills/sdlc/sdlc-core/adversarial-code-review.md		Review a pull request an agent touched by building the strongest case that it is wrong, unsafe, or not what it claims, and record the verdict where the merge gate reads it: one merge-review/v1 file per head, on the `m…
agent-handoff
cat-harness/skills/sdlc/sdlc-core/agent-handoff.md		Governs handing ONE task to an agent in another environment — a local agent with network the cloud session lacks, a sibling on a different machine, anything that cannot read the coordinator's context and that a person m…
bean-blocking
cat-harness/skills/sdlc/sdlc-core/bean-blocking.md		Default to non-blocking when updating a bean's status.
bean-coordination
cat-harness/skills/sdlc/sdlc-core/bean-coordination.md		Pointer to the bean-based session work-plan system (the beans CLI flat-file issue tracker, data under beans/).
before-after-preview
cat-harness/skills/sdlc/sdlc-core/before-after-preview.md		Make a reviewer-facing BEFORE/AFTER preview of a change to anything that is rendered — a docs site, a paper's PDF, a FHIR IG, a slide deck, a website — and put it where the review and feedback processes expect it.
benchmarking-mode
cat-harness/skills/sdlc/sdlc-core/benchmarking-mode.md		Benchmarking output is a synthesized report across models and configurations, deliberately excluded from declared knowledge-graph typologies.
blocked-build-dependencies
cat-harness/skills/sdlc/sdlc-core/blocked-build-dependencies.md		A build or a model download fails from an agent container.
branch-archaeology
cat-harness/skills/sdlc/sdlc-core/branch-archaeology.md		Classify every remote branch against the default branch (merged, landed by squash or cherry-pick, partially landed, unlanded, undetermined) by commit ancestry, patch-id and merge-tree, not by subject line.
bun-use
cat-harness/skills/sdlc/sdlc-core/bun-use.md		How Bun is used as the JavaScript/TypeScript execution runtime, test runner, package manager, and tarball packager across separated repositories: standalone subgraph configuration (bunfig.toml, package.json, tsconfig.js…
ci-health
cat-harness/skills/sdlc/sdlc-core/ci-health.md		A red workflow looks exactly like a green one from inside a checkout.
continual-progress
cat-harness/skills/sdlc/sdlc-core/continual-progress.md		Make in-flight work trackable by others in real time — open a PR from the first commit, push small coherent increments continuously (never hoard uncommitted work), keep a live status checklist in the PR body, and post b…
coordinate
cat-harness/skills/sdlc/sdlc-core/coordinate.md		Coordinate work across multiple in-flight Claude PRs working toward a shared goal.
decision-audit
cat-harness/skills/sdlc/sdlc-core/decision-audit.md		Record why a decision was made, or why a finding in it was left.
delivery-summary
cat-harness/skills/sdlc/sdlc-core/delivery-summary.md		Post-delivery summary with server restart command and viewer links
deployment-auth
cat-harness/skills/sdlc/sdlc-core/deployment-auth.md		no description in the artefact
diff
cat-harness/skills/sdlc/sdlc-core/diff.md		Show per-block content changes with viewer links, changelog, and undo impact analysis
dispatch-agent
cat-harness/skills/sdlc/sdlc-core/dispatch-agent.md		Dispatch one or more background sub-agents against parallel research/build fronts with a STANDARDIZED live progress contract, and monitor them on a 2-minute heartbeat.
feature-staging
cat-harness/skills/sdlc/sdlc-core/feature-staging.md		Manages feature-branch staging deployments under gh-pages/STAGING/<branch-slug>/ for before/after publication review comparison.
finding-software
cat-harness/skills/sdlc/sdlc-core/finding-software.md		A script needs a program or module the container does not have (tesseract, pdftoppm, PyMuPDF, a CLI from a GitHub release).
gate-tree-mutation
cat-harness/skills/sdlc/sdlc-core/gate-tree-mutation.md		Reading bun run cat gates' "NOT clean" verdict.
generalise-the-fix
cat-harness/skills/sdlc/sdlc-core/generalise-the-fix.md		You have a fix.
github-state-inspection
cat-harness/skills/sdlc/sdlc-core/github-state-inspection.md		Answer questions about GitHub-hosted state — is a page published, where does it live, did CI pass, does a branch exist — by reading the ref or the API, never by composing a URL or fetching one.
goal-review
cat-harness/skills/sdlc/sdlc-core/goal-review.md		Cold start, then review a time window of activity — sibling sessions, the work plan, issues, change proposals, branches, CI — and prioritise what it finds against goals stated in the owner's words.
handover-report
cat-harness/skills/sdlc/sdlc-core/handover-report.md		Write a handover report: a templated snapshot of an agent's current state, committed as a bean note, so that a session or subagent that stalls, runs out of context, or loses its container can be picked up by another age…
idle-backlog
cat-harness/skills/sdlc/sdlc-core/idle-backlog.md		While idle or waiting on a long-running async task (a build, a long compute script, a CI run, a background agent), pull the applicable backlog in priority order and work non-conflicting items instead of stalling.
integration-backlog
cat-harness/skills/sdlc/sdlc-core/integration-backlog.md		Dispatcher for the /integration-backlog <axes> slash command.
integration-watch
cat-harness/skills/sdlc/sdlc-core/integration-watch.md		Dispatcher for the /integration-watch slash command.
integration-watcher
cat-harness/skills/sdlc/sdlc-core/integration-watcher.md		Abstract parent skill for domain-specific **integration watchers**.
issue-working
cat-harness/skills/sdlc/sdlc-core/issue-working.md		Working a tracked issue — announce the branch when you create it rather than when you finish, and re-check the issue for new AND edited comments while you work.
merge-conflict-patterns
cat-harness/skills/sdlc/sdlc-core/merge-conflict-patterns.md		Merge the base branch in and resolve, without a person, only the conflicts a DECLARED pattern covers — generated files, generated README regions, QA sidecars — then prove the result with the gate set.
merge-queue
cat-harness/skills/sdlc/sdlc-core/merge-queue.md		Order the ready PRs and land them as a train: read each PR's live facts, let the reprioritisation table place it, merge the members together, run the gate set on the combination, and on red attribute and eject the culpr…
merge-to-main
cat-harness/skills/sdlc/sdlc-core/merge-to-main.md		Merging to main is its own step with its own gate: the merge-to-main sub-process, which every process that lands work CALLS rather than inlines.
minimal-change
cat-harness/skills/sdlc/sdlc-core/minimal-change.md		Three rules for any edit to a repository: make the smallest change that does the job and keep the diff minimal; read the repository's code-style files before writing code; and write Markdown without HTML tags.
narrative-asserts-code
cat-harness/skills/sdlc/sdlc-core/narrative-asserts-code.md		Judge whether the prose side of a declared prose ↔ code pair still says what the code does, when the machine could not settle it.
opening-brief
cat-harness/skills/sdlc/sdlc-core/opening-brief.md		Brief a bean or a topic BEFORE touching anything: what you are doing and why it is worth doing, what you already know and with what provenance, how you plan to do it and what would falsify the approach.
package-release
cat-harness/skills/sdlc/sdlc-core/package-release.md		Cut a release of a repository's packages: decide the next version, write the release notes, tag, and create the release — for any repository, the platform or a folio.
pending-show
cat-harness/skills/sdlc/sdlc-core/pending-show.md		Show the current session's pending work — beans list + ledger intent.
pickup
cat-harness/skills/sdlc/sdlc-core/pickup.md		Pick up / continue work on one or more existing open PRs efficiently.
platform-gates
cat-harness/skills/sdlc/sdlc-core/platform-gates.md		bun test passing is not the gates passing.
pr-description
cat-harness/skills/sdlc/sdlc-core/pr-description.md		Write or update a pull request's description so that someone who has never seen the work can follow it: the problem, why it matters, how it was approached, what constrained it, the solution, how to use it, and what is n…
prepare-for-handover
cat-harness/skills/sdlc/sdlc-core/prepare-for-handover.md		Prepare for a handover: commit and push everything you hold, then write a handover report that cites the commits.
prepare-merge-auto
cat-harness/skills/sdlc/sdlc-core/prepare-merge-auto.md		Full prepare-merge → resolve → merge pipeline.
prepare-merge
cat-harness/skills/sdlc/sdlc-core/prepare-merge.md		Take a feature branch to a clean, conflict-free, green, pushed state so it can be merged with no surprises: base merged in, generated files regenerated, the folio's content-type gates run, then pushed.
publish-verification
cat-harness/skills/sdlc/sdlc-core/publish-verification.md		Verify what a publish produced BEFORE it is deployed, and alert the publication manager whenever any step after the publish button fails — the verifier set, how to add a verifier, what is in scope, and how the publicati…
qa-report-signing
cat-harness/skills/sdlc/sdlc-core/qa-report-signing.md		no description in the artefact
qa-reports
cat-harness/skills/sdlc/sdlc-core/qa-reports.md		Where a QA result lives now.
qa-witness
cat-harness/skills/sdlc/sdlc-core/qa-witness.md		The QA projections written to test/results/witnesses/ and stored on the qa-reports branch — what a qa-witness/v1 document says, which three families produce one, how to read a verdict and the witness behind it, an…
ref-stewardship
cat-harness/skills/sdlc/sdlc-core/ref-stewardship.md		Steward a WATCHED REF — a long-lived branch many processes write and one consumer serialises.
related-work-coordination
cat-harness/skills/sdlc/sdlc-core/related-work-coordination.md		Before new work takes shape, find the work it touches.
rendered-impact
cat-harness/skills/sdlc/sdlc-core/rendered-impact.md		The list of rendered files a Change Set alters, and how a reviewer approves against it.
rendered-verification
cat-harness/skills/sdlc/sdlc-core/rendered-verification.md		Confirm a UI change by LOOKING at it in a browser and sending the screenshots to the author, rather than describing it.
secrets
cat-harness/skills/sdlc/sdlc-core/secrets.md		Adding, rotating and revoking the credentials the harness's automation needs, one mechanism at a time, with the exact GitHub UI path for each step.
session-intent
cat-harness/skills/sdlc/sdlc-core/session-intent.md		Session-start intent declaration + session-end results recording, against the goal-scoped master ledger and queue file.
specification-management
cat-harness/skills/sdlc/sdlc-core/specification-management.md		Governs the lifecycle, syntax, and traceability of specifications and requirements across the harness.
staging-review
cat-harness/skills/sdlc/sdlc-core/staging-review.md		Staging preview and before/after comparison for content review.
stalled-agent-triage
cat-harness/skills/sdlc/sdlc-core/stalled-agent-triage.md		Triage incoming work from stalled agents.
swarm-management
cat-harness/skills/sdlc/sdlc-core/swarm-management.md		Decide whether to run parallel agents at all, and if so how many, at which model level, against which decomposition.
test-engineer
cat-harness/skills/sdlc/sdlc-core/test-engineer.md		no description in the artefact
test-plan-execution
cat-harness/skills/sdlc/sdlc-core/test-plan-execution.md		Run a test-plan/v1 against a system under test and take it to a certification decision — the five lanes of test-plan-execution.bpmn (requester, tester, untainted checker, certifier, attestation service), how the tes…
todo-manager
cat-harness/skills/sdlc/sdlc-core/todo-manager.md		Maintain and display work-in-progress task lists using the beans CLI issue tracker.
turn-reporting
cat-harness/skills/sdlc/sdlc-core/turn-reporting.md		Say which bean you are on, every turn — the opening and closing report formats, the rules that make a report worth reading (two sentences and a link per bean, every mention), and the STRICT rule that the "next" line is…
untainted-verification
cat-harness/skills/sdlc/sdlc-core/untainted-verification.md		The party that produced an artefact does not write the verdict on it.
upstream-version-adoption
cat-harness/skills/sdlc/sdlc-core/upstream-version-adoption.md		Watch a pinned upstream dependency for a new release, and take a candidate version through impact analysis, an MVP build, review and a person's adopt/hold/decline decision.
visual-diff
cat-harness/skills/sdlc/sdlc-core/visual-diff.md		Pictures of a changed figure, diagram or table, before and after, and how much of it changed.
watch
cat-harness/skills/sdlc/sdlc-core/watch.md		Background-watch a branch (default origin/main) or a GitHub PR for new activity while you work, and on every event report whether to integrate / whether it conflicts with the current branch / whether it lets you simplif…
where-a-proposal-goes
cat-harness/skills/sdlc/sdlc-core/where-a-proposal-goes.md		no description in the artefact
work-plan-restructure
cat-harness/skills/sdlc/sdlc-core/work-plan-restructure.md		Reorganise a work plan that has outgrown one-bean-at-a-time repair — session logs typed as epics, duplicate families, generated template beans, stale claims, unparented work — through a reviewed PLAN rather than in bulk.
change-size
cat-harness/skills/sdlc/spec-kit/change-size.md		The change-size rule: keeps review increments adjudicable by establishing a line-count threshold (~400 effective lines), recording its empirical basis, weighting prose/KG lower than code, and distinguishing size from co…
spec-kit
cat-harness/skills/sdlc/spec-kit/spec-kit.md		Spec-driven development, adopted whole: define what and why before deciding how, and do not develop before a spec exists.
spec-template
cat-harness/skills/sdlc/spec-kit/spec-template.md		The single declared template artefact for platform feature specifications, adopted from github/spec-kit.
create-sticky-note
cat-harness/skills/ui/theming/create-sticky-note.md		Draft a sticky note from the conversation, choose its theme and its place, preview it, and only then attach it to a node.
site-presentation-assets
cat-harness/skills/ui/theming/site-presentation-assets.md		A visual fact — a colour, a glyph, a theme — lives in a graph node, and the stylesheet the site serves is a rendering of it.
theme-art-intake
cat-harness/skills/ui/theming/theme-art-intake.md		Accept or refuse a set of three theme/avatar layouts arriving through document ingestion, with a named reason for every refusal.
theme-artefacts
cat-harness/skills/ui/theming/theme-artefacts.md		The per-surface SPECIALISATION layer — sticky, landing board, docs background, navbar avatar.
theme-contrast
cat-harness/skills/ui/theming/theme-contrast.md		Why every scrim is measured over PURE BLACK rather than over the art actually in use, what the AAA floor is, and why the high-contrast pair declares no backdrop at all.
theme-declaration
cat-harness/skills/ui/theming/theme-declaration.md		What a theme IS as data — the palette, the three required layouts, and the per-image regions (textRegion, avatarRegion).
theme-generation
cat-harness/skills/ui/theming/theme-generation.md		Turning a declared theme into CSS — bun run cat themes:css — and the single consumer-side failure this stage exists to stop: a theme with no CSS rule falls back to an opaque surface and paints over its own art.
theming
cat-harness/skills/ui/theming/theming.md		The map of this subgraph: theming is split on PIPELINE STAGE first — intake, declaration, generation, contrast — with producer/consumer as the direction each stage faces, and per-artefact specialisation last.
archimate-models
cat-harness/skills/ui/ui-core/archimate-models.md		ArchiMate models as knowledge-graph content: how an instance declares the Archi models it holds, what the archimate subgraph gives every model, view, element and relationship (an IRI, a thin page, and every view drawn…
auto-docs
cat-harness/skills/ui/ui-core/auto-docs.md		Derived documentation for a sub-graph — what the handler emits, what it deliberately does not, and the obligation on whoever authors a harness's docs: summarise what the index lists, by reusing it rather than restating…
board-diagram-interchange
cat-harness/skills/ui/ui-core/board-diagram-interchange.md		A board is a DIAGRAM OF a folio, not a container of one.
board-windows
cat-harness/skills/ui/ui-core/board-windows.md		Everything starts as its avatar; opening projects a window onto the board.
deployment-awareness
cat-harness/skills/ui/ui-core/deployment-awareness.md		The agent must know its UI surface — gh-pages, local server, with/without MCP, or chat discussion only — because deployment surfaces are declared architectural facts that decide which tools apply, forbid request-time as…
docs-generation
cat-harness/skills/ui/ui-core/docs-generation.md		Generate and deploy documentation artifacts: schema docs (TypeDoc), formal-layer API docs, dependency graphs, schema manifests, and per-paper HTML/PDF/Markdown outputs.
harness-tiles
cat-harness/skills/ui/ui-core/harness-tiles.md		A tile is a function of the harness watching a directory, not of nodes.
html-rendering-qc
cat-harness/skills/ui/ui-core/html-rendering-qc.md		no description in the artefact
incremental-render
cat-harness/skills/ui/ui-core/incremental-render.md		Rendering only what changed — seeding a build from a previous render, the two edges that decide what must re-run, why a step declares GRAPH TYPOLOGIES rather than paths, and the rule that could-not-determine always re-r…
kg-viewer
cat-harness/skills/ui/ui-core/kg-viewer.md		Render a published knowledge-graph document so a person can read it — faceted index, node detail, followable edges, and an honest account of what the document is missing.
liquid-templates
cat-harness/skills/ui/ui-core/liquid-templates.md		Authoring a Liquid template in this repository — a README template the subgraph-readmes Tool renders with liquidjs, or a Jekyll include on the just-the-docs site.
markdown-render-check
cat-harness/skills/ui/ui-core/markdown-render-check.md		no description in the artefact
pdf-inline-viewer
cat-harness/skills/ui/ui-core/pdf-inline-viewer.md		Show a published PDF inside a generated page — search, scroll, jump to page, print and download — with the pinned pdf.js viewer the site build installs.
readme-sections
cat-harness/skills/ui/ui-core/readme-sections.md		A folio's README is the author's file; the platform owns only the marked regions it generates.
render-logging
cat-harness/skills/ui/ui-core/render-logging.md		Log every render to the publish branch — what was published, removed, restored or deliberately retained — to an append-only log that lives beside what it describes.
render-order
cat-harness/skills/ui/ui-core/render-order.md		no description in the artefact
serving-renderings
cat-harness/skills/ui/ui-core/serving-renderings.md		no description in the artefact
theme-ui-review
cat-harness/skills/ui/ui-core/theme-ui-review.md		Review graphical assets AS THEY ARE INGESTED, in the context of the website or app design they are for — accessibility, branding, languages — to determine what the assets and the UI will be.
ui-accessibility
cat-harness/skills/ui/ui-core/ui-accessibility.md		Every user interface this project produces must be operable by keyboard, legible at measured contrast, and comfortable to hit.
visualizer-loading
cat-harness/skills/ui/ui-core/visualizer-loading.md		The general strategy for a complex visualizer: the generated page carries identity, layout and a pointer, and its bulky or repeated content is fetched from the Knowledge Graph in the browser rather than baked into every…
wireframe-design-review
cat-harness/skills/ui/ui-core/wireframe-design-review.md		Design a user interface (a page, a visualiser, a navbar) by the WireGen methodology: a written design intent, at least two mid-fidelity HTML candidates, each with a web AND a mobile layout, mechanical checks at both vie…
wireframe-viewport-check
cat-harness/skills/ui/ui-core/wireframe-viewport-check.md		Render wireframe candidates at a web viewport (1280x800) and a mobile viewport (390x844), and record, per candidate and viewport, a pass or fail entry with a note for each mechanical criterion: renders, no-overflow, no-…
fhir-questionnaire-wireframe
fhir-harness/skills/content/fhir-ig-authoring/fhir-questionnaire-wireframe.md		no description in the artefact
fhir-validation
fhir-harness/skills/content/fhir-ig-authoring/fhir-validation.md		no description in the artefact
ig-publication
fhir-harness/skills/content/fhir-ig-authoring/ig-publication.md		no description in the artefact
l3-fhir-authoring
fhir-harness/skills/content/fhir-ig-authoring/l3-fhir-authoring.md		no description in the artefact
terminology-management
fhir-harness/skills/content/fhir-ig-authoring/terminology-management.md		no description in the artefact
fhir-client-operations
fhir-harness/skills/fhir-client/fhir-client-operations.md		Reading, searching and writing FHIR R4 resources through the SMARTerFHIR client (BaseClient and its vendor subclasses): the launch-context reads, requestResource, create with its automatic subject/encounter/contex…
smart-launch
fhir-harness/skills/fhir-client/smart-launch.md		How a browser app performs a SMART on FHIR launch — EHR launch and standalone launch — with the SMARTerFHIR library: SmartLaunchHandler, the LAUNCH and EMR enums, the scopes it requests per EHR vendor, how the red…
fhir-ig-create
fhir-harness/skills/fhir-ig-base/fhir-ig-create.md		Somebody asked for a new FHIR Implementation Guide.
ig-ast-delta
fhir-harness/skills/fhir-ig-base/ig-ast-delta.md		List and view what changed between two IG ASTs, check whether an AST is still valid for the IG's current inputs, and render the delta as just-the-docs pages that carry the provisional mark.
ig-binary-artefacts
fhir-harness/skills/fhir-ig-base/ig-binary-artefacts.md		Where the IG Publisher's binary outputs go — full-ig.zip, package.tgz and its R4/R4B variants, package.db, validator packs, and the definitions, examples and expansions zips — and why a pages branch is the wrong place f…
ig-build-pipeline
fhir-harness/skills/fhir-ig-base/ig-build-pipeline.md		The bare FHIR IG pipeline — FSH to SUSHI to the IG Publisher to a pages branch, with no pre-processing and no post-processing.
ig-publisher-fork
fhir-harness/skills/fhir-ig-base/ig-publisher-fork.md		Requirements for an agent working a local experimental fork of the IG Publisher — which repositories, what the AST must carry, what must not change, and the acceptance criteria.
ig-publisher-reduction
fhir-harness/skills/fhir-ig-base/ig-publisher-reduction.md		The phased transition that reduces the IG Publisher to AST + QA — five phases, each with an exit criterion that is measured rather than asserted, and the staleness contract that makes an AST-backed staging build honest.
ig-render-jekyll
fhir-harness/skills/fhir-ig-base/ig-render-jekyll.md		Rendering a FHIR IG's content through the just-the-docs pipeline instead of mounting the IG Publisher's finished HTML — the JSON-only representation contract, navigation derived from sushi-config.yaml, and the LHS rail.
ig-site-links
fhir-harness/skills/fhir-ig-base/ig-site-links.md		What happens to an IG's links when its pages are rendered on our site rather than by the IG Publisher: which are rewritten (artefact pages, a case-only mismatch, the Publisher's downloads and pages, files of the IG's re…
ig-site-theme
fhir-harness/skills/fhir-ig-base/ig-site-theme.md		How an IG rendered through just-the-docs wears the theme its instance ALREADY declares: the one webpage theme becomes the IG site's colour scheme.
corpus-commit-contract
folio-assistant-core/skills/content/content-lifecycle-ext/corpus-commit-contract.md		The contract the corpus role is held to when an accepted edit is committed into it: take the write only on the editor's acceptance, as one change with its QA sidecars, under the commit-hygiene requirement and with no…
quality-control
folio-assistant-core/skills/content/content-lifecycle-ext/quality-control.md		no description in the artefact
registry-authority-contract
folio-assistant-core/skills/content/content-lifecycle-ext/registry-authority-contract.md		The contract the external-registry role is held to when a candidate source is checked against the body that publishes it: resolve the identifier through its own API and return the record, so authority is a resolved fa…
review-comments
folio-assistant-core/skills/content/content-lifecycle-ext/review-comments.md		Reviewer comments on a folio's edit-set, from a tagged pull-request comment to a structured todo on the review page.
block-actions
folio-assistant-core/skills/content/folio-document-adapter/block-actions.md		Every block of a rendered document links back to where it can be changed: [edit] opens the block's Markdown source in GitHub's editor, and [feedback] opens a GitHub issue about that block, from the folio's own issue for…
document-authoring
folio-assistant-core/skills/content/folio-document-adapter/document-authoring.md		no description in the artefact
document-publishing
folio-assistant-core/skills/content/folio-document-adapter/document-publishing.md		no description in the artefact
document-structure
folio-assistant-core/skills/content/folio-document-adapter/document-structure.md		no description in the artefact
normative-statements
folio-assistant-core/skills/content/folio-document-adapter/normative-statements.md		no description in the artefact
public-comment
folio-assistant-core/skills/content/folio-document-adapter/public-comment.md		no description in the artefact
plan-request-gate
folio-assistant-core/skills/content/requirements-planning/plan-request-gate.md		When somebody asks for a PLAN — "plan", "approach", "proposal", "how would you", "come up with" — produce a requirements document and a work plan, post or commit them where the governing methodology says, hand over both…
requirement-definition
folio-assistant-core/skills/content/requirements-planning/requirement-definition.md		What a requirement IS, said once for both requirements methodologies: a statement, a conformance level, a source, at least one success criterion with its verification method, and a sign-off owner.
deep-document-research
folio-assistant-core/skills/deep-document-research.md		Answer a question from a corpus this folio already holds, iteratively, and stop on a stated condition.
dublin-core-renderings
folio-assistant-core/skills/library/catalogue/dublin-core-renderings.md		Render a catalogue's Dublin Core records in the two standard forms an outside reader can use: Dublin Core XML, which a harvester reads, and JSON-LD bound to DCMI Metadata Terms.
oxigraph-catalogue-search
folio-assistant-core/skills/library/catalogue/oxigraph-catalogue-search.md		How to compile, partition, distribute via CDN, and query digital library catalogue and Qualified Dublin Core metadata using Oxigraph in-memory WebAssembly on the static edge.
archiving-arxiv
folio-assistant-core/skills/library/cataloguing/archiving-arxiv.md		Materializing a paper from arXiv — why the version suffix is part of the identity rather than a detail, what to keep beside the PDF, and which facts must be read from the published API rather than recalled.
archiving-web-pages
folio-assistant-core/skills/library/cataloguing/archiving-web-pages.md		Capturing a web page so it can be cited later — the two fidelities, what each one is evidence of, and why capturing only one of them loses something that cannot be recovered.
bib-human-review
folio-assistant-core/skills/library/cataloguing/bib-human-review.md		Human-validated bibliography workflow.
bib-photo-ingestion-watcher
folio-assistant-core/skills/library/cataloguing/bib-photo-ingestion-watcher.md		Integration-watcher for bib physical-review issues.
bib-qa
folio-assistant-core/skills/library/cataloguing/bib-qa.md		Bibliography quality-assurance agent — validates every reference in content/schema/references.ts against several QA checks: URL availability, URL resolution, metadata completeness, citation coverage, and screenshot/imag…
filing-dublin-core
folio-assistant-core/skills/library/cataloguing/filing-dublin-core.md		Cataloguing a source as it arrives — which facts are dcterms, which are this project's own, and why the line is drawn by the vocabulary rather than by convenience.
glossary-build
folio-assistant-core/skills/library/cataloguing/glossary-build.md		no description in the artefact
glossary-terms
folio-assistant-core/skills/library/cataloguing/glossary-terms.md		Add terms to an instance's glossary: local SKOS terms (folio-glossary/v1) with a definition, a code and links to external SKOS concepts, and references to whole external schemes.
ontologist
folio-assistant-core/skills/library/cataloguing/ontologist.md		Semantic Ontologist — scans narrative text for ambiguous terms, generates a formal glossary/registry, and produces a mapping linking narrative strings to formal identifiers.
audio-transcription
folio-assistant-core/skills/library/ingestion/audio-transcription.md		Turn recorded speech (a meeting recording, a video with audio, an interview) into a transcript the library can cite, and choose WHICH open-source recogniser to run for the job: whisper.cpp by default, faster-whisper, Wh…
document-intake
folio-assistant-core/skills/library/ingestion/document-intake.md		Process uploaded documents (PDFs, scans, LaTeX, structured/normative guidelines, etc.) from uploads/ into structured content objects.
l1-coverage
folio-assistant-core/skills/library/ingestion/l1-coverage.md		Check that an L1 extraction accounted for every normative sentence in its source publication — captured as a node, or excluded for a fixed-list reason a person signed off.
l1-document-ingestion
folio-assistant-core/skills/library/ingestion/l1-document-ingestion.md		The detailed method for turning a DOCUMENT in uploads/ into a complete L1 entry in library/<bib-slug>/ — which rung reads it and why, what a complete L1 entry holds, why an inferred structure is refused rather than…
tabular-metadata
folio-assistant-core/skills/library/ingestion/tabular-metadata.md		Extract tabular metadata from a CSV or spreadsheet as CSVW — tables, rows, headers, columns, datatypes and location on sheet — recording every field as determined or explicitly undetermined.
review
folio-assistant-core/skills/review/review.md		Where to start when a person or an agent reviews a document folio larger than one chapter, such as a DAK or an L1 digital transformation handbook.
latex-authoring
folio-assistant-sci/skills/content/authoring-math/latex-authoring.md		no description in the artefact
lean-formalization
folio-assistant-sci/skills/content/authoring-math/lean-formalization.md		no description in the artefact
proof-verification
folio-assistant-sci/skills/content/authoring-math/proof-verification.md		no description in the artefact
build-docs
folio-assistant-sci/skills/content/folio-paper-adapter/build-docs.md		Builds the Lean HTML documentation (doc-gen4) locally in the workspace, for any paper folio's Lean package.
build-pdf
folio-assistant-sci/skills/content/folio-paper-adapter/build-pdf.md		Builds a paper folio's PDF locally in the workspace — the monolithic PDF plus split per-chapter PDFs.
category-theory
folio-assistant-sci/skills/content/folio-paper-adapter/category-theory.md		Category Theory formalization skill — handles diagram chasing, universal properties, functorial translation, and whiskering in Lean 4.
chapter-analysis
folio-assistant-sci/skills/content/folio-paper-adapter/chapter-analysis.md		Thorough analysis and Lean 4 formalization of a single manuscript chapter.
compute-audit
folio-assistant-sci/skills/content/folio-paper-adapter/compute-audit.md		Audit compute scripts for a catalogue of correctness and performance antipatterns extracted from a long review of the project's compute history.
compute-author
folio-assistant-sci/skills/content/folio-paper-adapter/compute-author.md		Pre-work briefing + durable patterns for anyone writing or modifying compute scripts (or the native crates they call).
content-block-review
folio-assistant-sci/skills/content/folio-paper-adapter/content-block-review.md		Reviews existing content blocks for adherence to all requirements — structural integrity, Lean proof rules, cross-reference consistency, status accuracy, and naming conventions.
content-validation
folio-assistant-sci/skills/content/folio-paper-adapter/content-validation.md		no description in the artefact
critical-path-analysis
folio-assistant-sci/skills/content/folio-paper-adapter/critical-path-analysis.md		Analyse the critical path of the paper's argument chain, audit statement and proof contexts (e.g.
definition-clarity-audit
folio-assistant-sci/skills/content/folio-paper-adapter/definition-clarity-audit.md		Definition / statement clarity + concision audit.
ffi-roundtrip-audit
folio-assistant-sci/skills/content/folio-paper-adapter/ffi-roundtrip-audit.md		Audit compute scripts for script ↔ native ping-pong patterns — loops that cross the FFI / subprocess boundary per iteration, instead of one boundary crossing for the whole pipeline.
formalizer
folio-assistant-sci/skills/content/folio-paper-adapter/formalizer.md		Lean 4 Formalizer — translates the logical skeleton of narrative mathematical proofs into Lean 4 tactic blocks.
groebner-basis
folio-assistant-sci/skills/content/folio-paper-adapter/groebner-basis.md		Compute Gröbner bases and normal forms for (possibly non-commutative) algebraic structures using a CAS (e.g.
latex-build-cache
folio-assistant-sci/skills/content/folio-paper-adapter/latex-build-cache.md		LaTeX build performance — findings + what's safe.
latex-compilation
folio-assistant-sci/skills/content/folio-paper-adapter/latex-compilation.md		Compile LaTeX source documents into PDF using latexmk and pdflatex, with safe shell-escape isolation across trusted and untrusted environments.
latex-validation
folio-assistant-sci/skills/content/folio-paper-adapter/latex-validation.md		no description in the artefact
lean-build-fix
folio-assistant-sci/skills/content/folio-paper-adapter/lean-build-fix.md		Iteratively fix Lean build errors and linter warnings until the build passes cleanly.
lean-cache-restore
folio-assistant-sci/skills/content/folio-paper-adapter/lean-cache-restore.md		The Lean build loop — restore a warm cache before working, and contribute your build back when done.
lean-completeness-audit
folio-assistant-sci/skills/content/folio-paper-adapter/lean-completeness-audit.md		Audit Lean formalization completeness across all papers: verify Lake project setup, check import coverage, identify missing .lean files for content blocks that require them, report formalization gaps, and detect stale w…
lean-environment-setup
folio-assistant-sci/skills/content/folio-paper-adapter/lean-environment-setup.md		Sets up and troubleshoots the Lean 4 environment for Claude Code sessions.
lean-formal-graph
folio-assistant-sci/skills/content/folio-paper-adapter/lean-formal-graph.md		Build and query the FORMAL dependency graph — what a proof actually invokes, derived from lean.ref.
lean-generation
folio-assistant-sci/skills/content/folio-paper-adapter/lean-generation.md		Extract theorem-like objects from LaTeX source and generate corresponding Lean 4 stub files with sorry placeholders.
lean-mathlibext-curator
folio-assistant-sci/skills/content/folio-paper-adapter/lean-mathlibext-curator.md		Curate <Paper>/MathlibExt.lean — the staging area for upstream- candidate lemmas (List/sort plumbing, Foldl/foldr at Monoid level, Real-function bridges).
lean-proof-review
folio-assistant-sci/skills/content/folio-paper-adapter/lean-proof-review.md		Review Lean 4 proofs for correctness, style, and completeness.
lean-proof-vacuity-audit
folio-assistant-sci/skills/content/folio-paper-adapter/lean-proof-vacuity-audit.md		Detect and fix Lean "vacuous proof" anti-patterns — declarations that type-check, are sorry-free and axiom-clean, and whose statement matches the .md, yet carry NO mathematical content (they assume what they claim, conc…
lean-substantive-pass
folio-assistant-sci/skills/content/folio-paper-adapter/lean-substantive-pass.md		Convert abstract holds : Prop / claim : Prop placeholder Lean stubs into typed sub-claim contexts with manuscript-semantic field names.
lean-witness-audit
folio-assistant-sci/skills/content/folio-paper-adapter/lean-witness-audit.md		Audit computation scripts (typically Python) that produce witness statements for Lean formalization.
paper-importer
folio-assistant-sci/skills/content/folio-paper-adapter/paper-importer.md		Import external papers from PDF, LaTeX, or arXiv into the content object system.
proof-conciseness
folio-assistant-sci/skills/content/folio-paper-adapter/proof-conciseness.md		Tighten narrative (human-readable) proofs without changing mathematical content.
proof-editor
folio-assistant-sci/skills/content/folio-paper-adapter/proof-editor.md		Coordinator skill for proof review and repair.
proof-exposition-review
folio-assistant-sci/skills/content/folio-paper-adapter/proof-exposition-review.md		Paper-wide retrospective review of a single proof block.
proof-gap-audit
folio-assistant-sci/skills/content/folio-paper-adapter/proof-gap-audit.md		Audit individual proofs and the network of proofs for gaps.
proof-integration-watcher
folio-assistant-sci/skills/content/folio-paper-adapter/proof-integration-watcher.md		Proof-QA integration watcher — watches origin/main + open active PRs + newly-opened PRs for narrative-proof (.md) or Lean-proof (.lean) changes, runs the proof QA skill suite on every detected change, queues gaps, a…
proof-narrative-lean-equivalence
folio-assistant-sci/skills/content/folio-paper-adapter/proof-narrative-lean-equivalence.md		For each content block with both a narrative proof (.md) and a Lean sibling (.lean), verify the two prove the same thing.
proof-simplifier
folio-assistant-sci/skills/content/folio-paper-adapter/proof-simplifier.md		Analyse small clusters (2–4) of connected proofs to find simplifications: shared lemmas, redundant constructions, factored abstractions, or shorter proof paths through the dependency graph.
proof-status-tracking
folio-assistant-sci/skills/content/folio-paper-adapter/proof-status-tracking.md		Maintain the proof-objects.json manifest tracking formalization status, review records, and LaTeX-to-Lean linkages.
proof-triage
folio-assistant-sci/skills/content/folio-paper-adapter/proof-triage.md		Systematically triages and resolves sorry stubs across the Lean codebase.
proposition-consolidation-audit
folio-assistant-sci/skills/content/folio-paper-adapter/proposition-consolidation-audit.md		Scan a chapter (or the whole paper) for propositions/theorems/lemmas that overlap structurally — same boxed equation under different parametrisations, near-identical proof skeletons, explicit "specialisation of"/"case o…
q-usage-watcher
folio-assistant-sci/skills/content/folio-paper-adapter/q-usage-watcher.md		q-usage integration watcher — detects how each content block treats the substrate parameter $q$ (symbolic / generic-R / real-positive / q > 1 / |q| > 1 / unit-circle / root-of-unity / fixed q_0 / n/a) and cross-checks t…
remark-audit
folio-assistant-sci/skills/content/folio-paper-adapter/remark-audit.md		Audit remarks for provable content.
rendering-auditor
folio-assistant-sci/skills/content/folio-paper-adapter/rendering-auditor.md		Multi-pass rendering auditor for content blocks.
rendering-fixes
folio-assistant-sci/skills/content/folio-paper-adapter/rendering-fixes.md		Quick-fix reference for common rendering errors found by the rendering-auditor.
semantic-review-scoping
folio-assistant-sci/skills/content/folio-paper-adapter/semantic-review-scoping.md		Decide what to review FIRST.
simulator-math-audit
folio-assistant-sci/skills/content/folio-paper-adapter/simulator-math-audit.md		Audit simulator content objects against the formal mathematics they visualise — formulas and physical constants must be derived from the paper's canonical sources, never hardcoded in the visualisation.
simulator
folio-assistant-sci/skills/content/folio-paper-adapter/simulator.md		no description in the artefact
verify-local-substrate
folio-assistant-sci/skills/content/folio-paper-adapter/verify-local-substrate.md		Verify that every result block of a designated class traces back to a designated anchor definition through the uses[] dependency graph.
witnessed-values
folio-assistant-sci/skills/content/folio-paper-adapter/witnessed-values.md		no description in the artefact
hypothesis-generation
folio-assistant-sci/skills/content/hypothesis-generation/hypothesis-generation.md		Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans.
scientific-critical-thinking
folio-assistant-sci/skills/content/scientific-critical-thinking/scientific-critical-thinking.md		Evaluate scientific claims and evidence quality.
scientific-visualization
folio-assistant-sci/skills/content/scientific-visualization/scientific-visualization.md		Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly.
reference-dataset-ingestion
folio-assistant-sci/skills/data/reference-dataset-ingestion.md		Ingest a published REFERENCE dataset — a constants table such as CODATA, AME or PDG — into a library entry whose values are addressable in prose as {{ <instance>.library.<entry>.<slug> }}, with edition, source, sha256 a…
lean-formal-edges
folio-assistant-sci/skills/lean/lean-formal-edges.md		Extract ELABORATED formal dependencies between a folio's lean.ref declarations — the trustworthy replacement for the lexical --scan cache.
lean-html-docs
folio-assistant-sci/skills/lean/lean-html-docs.md		Build and publish the visualiser of a folio's declared lean directory: the package's doc-gen4 HTML render, staged under the folio's site and wrapped in the harness navbar and rail.
dak-l1-library
smart-base/skills/content/authoring-who-smart-guidelines/dak-l1-library.md		Build a DAK's library from the L1 sources its Component 1 cites, and the L1 knowledge graph that records them.
dak-postprocessing
smart-base/skills/content/authoring-who-smart-guidelines/dak-postprocessing.md		What the DAK post-processing phase accomplishes after the IG Publisher runs — the JSON/JSON-LD surface, the DAK API hub, and the metadata-to-Liquid bridge that is the seam the just-the-docs transition cuts at.
dak-preprocessing
smart-base/skills/content/authoring-who-smart-guidelines/dak-preprocessing.md		What the DAK pre-processing phase actually accomplishes, step by step, before the IG Publisher runs — and which of its steps exist only to satisfy the Publisher's own page index — and how it runs as the overlay on fhir-…
grade
smart-base/skills/content/authoring-who-smart-guidelines/grade.md		GRADE — the grading system a WHO guideline folio declares for certainty of evidence, and the Evidence-to-Decision judgement a recommendation rests on.
guideline-use-case
smart-base/skills/content/authoring-who-smart-guidelines/guideline-use-case.md		Stage 0 of smart-guideline-end-to-end: turn a request for a SMART Guideline into a use case — population, setting, jurisdiction and interventions in scope, new or an adaptation — in the requester's own words.
ig-artifact-ingestion
smart-base/skills/content/authoring-who-smart-guidelines/ig-artifact-ingestion.md		no description in the artefact
l2-component-edit-review
smart-base/skills/content/authoring-who-smart-guidelines/l2-component-edit-review.md		How one L2 DAK component is edited by the agent and reviewed by a person: personas and user scenarios, BPMN business processes, DMN decision and scheduling logic, core data elements and glossary with their terminology b…
l2-dak-authoring
smart-base/skills/content/authoring-who-smart-guidelines/l2-dak-authoring.md		Author the L2 layer of a WHO SMART Guideline — the Digital Adaptation Kit between the narrative L1 guideline and the L3 FHIR artefacts — one DAK component per pass (personas, user scenarios, business processes, data dic…
l2-dependency-choice
smart-base/skills/content/authoring-who-smart-guidelines/l2-dependency-choice.md		Stage 3 of smart-guideline-end-to-end: choose which existing DAKs (WHO's, or a jurisdiction's adaptation) the guideline builds on.
l3-dependency-choice
smart-base/skills/content/authoring-who-smart-guidelines/l3-dependency-choice.md		Stage 5 of smart-guideline-end-to-end: choose which existing FHIR IGs (WHO's, or a jurisdiction's) the guideline's L3 builds on.
l3-readiness
smart-base/skills/content/authoring-who-smart-guidelines/l3-readiness.md		The check between stages 5 and 6 of smart-guideline-end-to-end (Gateway_L3Ready): may the agent write L3 assets yet? Yes only when every source of the use case has its L1 extraction, every L2 asset names the L1 node it…
l4-application-brief
smart-base/skills/content/authoring-who-smart-guidelines/l4-application-brief.md		Stage 7 of smart-guideline-end-to-end: get from the requester a description of the consuming application — who uses it, on what device, which L2 processes and L3 resources it covers, connectivity, the systems it talks t…
l4-application-build
smart-base/skills/content/authoring-who-smart-guidelines/l4-application-build.md		Stage 8b of smart-guideline-end-to-end: build the consuming application against the stage-6 IG build (a clean build, not a publication), from the brief and the chosen stage-8a wireframes, with conformance tests from the…
recommendation-candidates
smart-base/skills/content/authoring-who-smart-guidelines/recommendation-candidates.md		Turn one ingested L1 source into L1 3.0 recommendation nodes: list every normative sentence as a candidate, let the agent decide each in a curation file, then refuse a non-verbatim statement or unknown location and writ…
recommendation-extraction
smart-base/skills/content/authoring-who-smart-guidelines/recommendation-extraction.md		Extract the recommendations of an L1 source as L1 3.0 recommendation and remark nodes, then describe each one's scenario: the persona (role) who acts on it, the business process they act in, and the user story, as smart…
recommendation-scenarios
smart-base/skills/content/authoring-who-smart-guidelines/recommendation-scenarios.md		Join each L1 recommendation to who acts on it and during which business process: one smart-kg L2 user-scenario candidate per recommendation, from the agent's mapping, reusing the target guide's personas and processes fi…
smart-base-tools
smart-base/skills/content/authoring-who-smart-guidelines/smart-base-tools.md		no description in the artefact
smart-guideline-create
smart-base/skills/content/authoring-who-smart-guidelines/smart-guideline-create.md		Somebody asked for a new WHO SMART Guideline (an IG built on smart-base, or a DAK that will feed one).
smart-guideline-end-to-end
smart-base/skills/content/authoring-who-smart-guidelines/smart-guideline-end-to-end.md		The whole road from a use case to a running application on WHO SMART Guidelines, for a new guideline or a jurisdiction's adaptation, as an orchestrator of ten named stage skills, each with its own input and output contr…
smart-stack-layering
smart-base/skills/content/authoring-who-smart-guidelines/smart-stack-layering.md		Which layer a WHO SMART asset, rule, script or page belongs to — fhir-harness, smart-base (with its L1 and DAK document kinds) or smart-ig — and the one question that settles it.
toolchain-ownership
smart-base/skills/content/authoring-who-smart-guidelines/toolchain-ownership.md		Taking ownership of the WHO smart-base scripts in a litlfred fork, rewriting them to the Skill I/O contract, and the one gate that governs when a script may actually move.
transcription-verbatim
smart-base/skills/content/authoring-who-smart-guidelines/transcription-verbatim.md		Check L1 authored from pictures (a schedule poster, a slide deck: a source with no usable text layer) against the image narratives and transcriptions it names: every statement verbatim in one of them, every transcriptio…
iris-dspace
who-iris/skills/iris-dspace.md		How WHO IRIS uses DSpace and qualified Dublin Core — the three identifier systems, MeSH as a controlled vocabulary, bundles, and the containment path.
iris-oxigraph
who-iris/skills/iris-oxigraph.md		How to compile, validate, distribute, and query WHO IRIS catalogue and Qualified Dublin Core metadata using Oxigraph in-memory WebAssembly and CLI pipelines.

folio-assistant — code under the Apache License 2.0, documentation under CC BY 3.0. Generated schema and API references are rebuilt from source on every push to main.

deployed b08c961 · 2026-10-23T23:11:09Z