agentleFS
nelantonenelantone/cognivia/.agents/skills/docs-update/SKILL.md

docs-update

Skill1 starsChanged 2 months agoMITView on GitHub

Update Cognivia documentation from verified implementation and current-session evidence. Use for README, architecture, validation, status, reviewer, or future-work documentation after implementation changes. Do not use for product prompt edits, speculative roadmap writing, code changes, generated handoffs, or claims that cannot be verified.

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 11

    Distinctive

    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:

    Use when a maintained repository document must be synchronized with verified code, tests, runtime evidence, or an approved migration state.

    line 15
  2. Distinctive:

    Do not use for product prompts, code comments, automatic handoff reports, historical rewrites, marketing copy, or unverified future …

    line 20
  3. Distinctive:

    Read the target document and the evidence that owns each affected claim.

    line 33
  4. Distinctive:

    Never invent implementation, test results, readiness, provider behavior, or security guarantees.

    line 50
  5. Distinctive:

    Never treat agent documentation as product-domain evidence.

    line 52
  6. Distinctive:

    Do not expose secrets, environment values, private URLs, or raw logs.

    line 53
  7. Distinctive:

    Do not modify product code, tests, or unrelated documents through this skill.

    line 54
  8. Distinctive:

    Do not silently rewrite an authoritative audit or historical source.

    line 55
  9. Distinctive:

    Verify every changed factual claim against its owning source.

    line 59
  10. Distinctive:

    Check local links and literal repository paths.

    line 60
  11. Distinctive:

    Run git diff --check and review the documentation diff.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “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

Docs Update

Purpose

Make documentation accurately describe current implementation, evidence, limitations, and pending work without inventing features or validation.

Trigger

Use when a maintained repository document must be synchronized with verified code, tests, runtime evidence, or an approved migration state.

Do not trigger

Do not use for product prompts, code comments, automatic handoff reports, historical rewrites, marketing copy, or unverified future architecture.

Inputs

  • Target document, audience, and requested scope.
  • Current code or configuration evidence.
  • Tests and commands actually run in the current session.
  • Manual or browser checks actually performed.
  • Known limitations and explicitly planned work.

Workflow

  1. Read the target document and the evidence that owns each affected claim.
  2. Classify claims as implemented, tested, manually verified, pending, or unverified using evidence language.
  3. Identify stale, ambiguous, historical, or marketing-heavy wording.
  4. Edit only the requested sections and preserve historical evidence unless the task explicitly changes its status or ownership.
  5. Separate current functionality, current limitations, and future work.
  6. Review links, paths, commands, dates, and validation claims.

Outputs

Return the documents and sections changed, the evidence used, claims still pending verification, validation performed, and any intentionally preserved historical wording.

Safety

  • Never invent implementation, test results, readiness, provider behavior, or security guarantees.
  • Never treat agent documentation as product-domain evidence.
  • Do not expose secrets, environment values, private URLs, or raw logs.
  • Do not modify product code, tests, or unrelated documents through this skill.
  • Do not silently rewrite an authoritative audit or historical source.

Validation

  • Verify every changed factual claim against its owning source.
  • Check local links and literal repository paths.
  • Run git diff --check and review the documentation diff.
  • State clearly which product tests, if any, were not required for a docs-only change.

References

  • AGENTS.md — evidence and documentation rules.
  • docs/agents/README.md — agent-tooling facts.
  • Evidence language — canonical claim status definitions for this skill.

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.