Lean vacuity audit

Inspect Lean declarations chapter by chapter for proofs that type-check, are sorry-free and axiom-clean, and still carry no mathematical content — assuming what they claim, concluding something trivially true, or resting on a false premise.

Skills it satisfies

A skill states the capability; this Tool is one way to exercise it. Each skill’s declared input and output contract follows, where it has one.

lean-proof-vacuity-audit

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, conclude something trivially true, or rest on a false premise). These slip past proof-statement-integrity (which only checks signature-stability + an axiom sweep), so detection is semantic and agent-checked. Use when auditing Lean for circular / vacuous / trivially-true proofs, after a batch proof-statement-integrity normalization (the batch “wrap the conclusion in a structure field and project it” fix produces these), or when a “theorem” looks too easy. Emits per-block QA sidecar params under the proof-no-* criteria.

Source: folio-assistant-sci/skills/content/folio-paper-adapter/lean-proof-vacuity-audit.md.

The skill declares no I/O contract (schemas/skills/lean-proof-vacuity-audit/{input,output}.schema.json).

Inputs and outputs

Each port names a shared type by IRI, so two Tools for one skill can be checked for interchangeability.

porttyperequireddescriptionconstraint
inchapterSlugOne chapter instead of the whole corpus.string · pattern ^[a-z0-9][a-z0-9-]*$ · A folio slug, e.g. quantum-observable-universe
instrictFlagboolean · A boolean switch — projects to a bare flag, with no value word
incheckAxiomsFlagAxiom-cleanliness is a separate question from vacuity: a proof can be axiom-clean and still assume its conclusion.boolean · A boolean switch — projects to a bare flag, with no value word
injsonFlagboolean · A boolean switch — projects to a bare flag, with no value word
outfindingsTextSorry inventory and trivial-truth detections. Sibling of lean-coverage, not an alternative to it: that one COUNTS what is proved, this one asks whether a proof says anything.string · A short single-line human string. Not admissible as a command-line argument.

Processes and tasks

No process step names a skill this Tool satisfies.

How it is deployed and reached

  • Command line. From the repository root: bun run folio-assistant-sci/scripts/lean-audit.ts.
  • GitHub Actions. No workflow in this checkout runs its command.

As an API: its operation in the OpenAPI document and the MCP tool list of its layer.

installnone
runtimebun
networkno

What it is made of

Linked data

The Tool is published as its own JSON-LD document at its IRI, https://litlfred.github.io/folio-assistant/folio-assistant-sci/tools/lean-audit.jsonld, partOf its layer’s document. The node below is the definition this page was drawn from, and is embedded in the page as application/ld+json.

{
  "@context": "https://litlfred.github.io/folio-assistant/folio-assistant-sci/folio-assistant-sci.context.jsonld",
  "@id": "https://litlfred.github.io/folio-assistant/folio-assistant-sci/tools/lean-audit.jsonld",
  "@type": "https://litlfred.github.io/cat-harness/v0/ns/Tool",
  "partOf": "https://litlfred.github.io/folio-assistant/folio-assistant-sci/folio-assistant-sci.jsonld",
  "name": "lean-audit",
  "title": "Lean vacuity audit",
  "description": "Inspect Lean declarations chapter by chapter for proofs that type-check, are sorry-free and axiom-clean, and still carry no mathematical content — assuming what they claim, concluding something trivially true, or resting on a false premise.",
  "install": {
    "none": true
  },
  "invoke": {
    "shell": "bun run folio-assistant-sci/scripts/lean-audit.ts"
  },
  "io": {
    "inputs": [
      {
        "name": "chapter",
        "schema": "https://litlfred.github.io/folio-assistant/cat-harness/tool-types.schema.json#/$defs/Slug",
        "description": "One chapter instead of the whole corpus.",
        "required": false,
        "arg": {
          "flag": "--chapter"
        }
      },
      {
        "name": "strict",
        "schema": "https://litlfred.github.io/folio-assistant/cat-harness/tool-types.schema.json#/$defs/Flag",
        "required": false,
        "arg": {
          "flag": "--strict"
        }
      },
      {
        "name": "checkAxioms",
        "schema": "https://litlfred.github.io/folio-assistant/cat-harness/tool-types.schema.json#/$defs/Flag",
        "description": "Axiom-cleanliness is a separate question from vacuity: a proof can be axiom-clean and still assume its conclusion.",
        "required": false,
        "arg": {
          "flag": "--check-axioms"
        }
      },
      {
        "name": "json",
        "schema": "https://litlfred.github.io/folio-assistant/cat-harness/tool-types.schema.json#/$defs/Flag",
        "required": false,
        "arg": {
          "flag": "--json"
        }
      }
    ],
    "outputs": [
      {
        "name": "findings",
        "schema": "https://litlfred.github.io/folio-assistant/cat-harness/tool-types.schema.json#/$defs/Text",
        "description": "Sorry inventory and trivial-truth detections. Sibling of `lean-coverage`, not an alternative to it: that one COUNTS what is proved, this one asks whether a proof says anything."
      }
    ]
  },
  "satisfies": [
    "lean-proof-vacuity-audit"
  ],
  "requirements": {
    "runtime": [
      "bun"
    ],
    "network": false
  }
}

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 dev