Generated from
cat-harness/skills/authoring/content-lifecycle/content-review.md— do not edit here. Typed contract: schema reference.
Content Review
Formal review and approval of validated content before publication.
Responsibilities
- Review L2 content before L3 begins (phase gate)
- Review L3 content before publication (phase gate)
- Assess breaking vs. non-breaking changes
- Ensure alignment with source guidelines
- Approve draft publications for stakeholder circulation
- Provide final publication release sign-off
Actors
- Content Reviewer (lead, approval authority)
- Technical Officer (first-pass review)
- Clinical SME (clinical sign-off)
- Programme Manager (governance oversight)
Inputs
- Validated content artifacts
- Validation reports
- Change log / diff from previous version
Outputs
Findings and a decision — two things, not one. See
decision-audit and
schemas/qa-review.ts.
- Findings — one per observation, each carrying the axis this reviewer can
speak on:
blocking | suggestion | praisefor a person,critical | major | minorfor a checker. Neither defaults into the other, andpraisehas no machine equivalent. - A decision —
approve | request-changes | reject, naming every finding it weighed and every one it overruled. An overruled finding stays on the record. - Audit notes — why this outcome, and why each overruled finding was left.
At least one per decision, each citing corpus evidence. Approving over an open
criticalorblockingfinding without overruling it is a reported problem.
Staging links
When a staging preview exists, every request this skill makes for feedback,
review or sign-off carries it: one deep link per changed page, to the anchor
where the change sits, with the same page on main as before. Where the skill
declares an output contract, they go in its stagingLinks field. The rule, and
where the page list comes from:
staging-review §”The deep-link rule”.
Processes that run this skill
| process | step(s) that name it |
|---|---|
| Narrative review | Read the sidecar findings |
| Review task | Classify what changed; Consolidate findings |
| Authoring a document | 8 · Review and feedback |
| Content Change and Review | Review each slice (calls a sub-process); Review impact assessment; Request changes |
| Content lifecycle | Editing and HCI validation (calls a sub-process); Draft, review and publish (calls a sub-process) |
| Draft, review and publish | Circulate the draft; Review the draft publication; Clinical / scientific sign-off |
| Editing and HCI validation | Agent review of the change; Human / SME review |
| Evidence for a recommendation | Review the guidance already in this content |
| Authoring a paper | 8 · Review and feedback |
| L2 component edit and review | Review the staged component (calls a sub-process) |
| L2 DAK authoring | Clinical validation |
| SMART Guideline end to end | Adjudicate the L1 source list (calls a sub-process); Adjudicate the L1 KG (calls a sub-process); Adjudicate L2 dependencies (calls a sub-process); Review each L2 asset (before / after if adapted) (calls a sub-process); Adjudicate L3 dependencies (calls a sub-process); Review each L3 asset (before / after if adapted) (calls a sub-process); Adjudicate the L4 wireframes and application (calls a sub-process) |