agentleFS
45ck45ck/documentation-evidence-skills/.agents/skills/reference-integrity-checker/SKILL.md

reference-integrity-checker

Skill2 starsChanged 8 months agoMITView on GitHub

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check that citations, references, labels, figure/table mentions, and appendix links are complete and internally consistent.

    line 12
  2. Distinctive:

    Prefer structured, reusable artifacts over generic prose.

    line 48
  3. Distinctive:

    Do not fabricate evidence, references, or approval.

    line 54
  4. Distinctive:

    Do not collapse requirements, decisions, tests, and findings into one undifferentiated blob.

    line 55
  5. Distinctive:

    Do not leave identifiers or document links inconsistent.

    line 56
  6. Distinctive:

    Do not confuse “described” with “verified”.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

reference-integrity-checker

Purpose

Check that citations, references, labels, figure/table mentions, and appendix links are complete and internally consistent.

Trigger this skill when

  • A durable documentation or evidence artifact is needed for review, submission, audit, or handover.
  • You need clearer linkage between requirements, design, testing, defects, decisions, or findings.
  • Existing documentation is fragmented, inconsistent, or weakly evidenced.

Expected inputs

  • draft document
  • reference list
  • figure/table/appendix mentions

Deliverables

  • reference consistency check
  • broken-link/issues list
  • cleanup actions

Operating procedure

  1. Clarify the artifact boundary, audience, and review objective.
  2. Separate known facts from assumptions, placeholders, and missing evidence.
  3. Produce the skill-specific artifact in a form that can be reused directly.
  4. Link the result to upstream and downstream artifacts where helpful.
  5. Recommend the next best handoff instead of trying to do every document at once.

Quality gates

  • The output is specific to the current system, feature, or report context.
  • Identifiers, references, and labels are internally consistent.
  • Missing evidence or unresolved questions are made visible.
  • The result is directly usable in a repo, report, appendix, or review packet.

Handoff targets

  • appendix-assembler
  • evaluation-report-writer
  • spec-writer

Output style

  • Prefer structured, reusable artifacts over generic prose.
  • Make IDs, labels, references, and evidence explicit where possible.
  • Preserve traceability between related artifacts.
  • Surface missing evidence or unresolved questions instead of inventing closure.

Failure modes to avoid

  • Do not fabricate evidence, references, or approval.
  • Do not collapse requirements, decisions, tests, and findings into one undifferentiated blob.
  • Do not leave identifiers or document links inconsistent.
  • Do not confuse “described” with “verified”.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.