agentleFS
mabykomabyko/AgentSkills/skills/docs-sync/SKILL.md

docs-sync

Skill0 starsChanged 33 days agoMITView on GitHub

Use when documentation and implementation may be out of sync, docs may define intended behavior, code changes need docs updates, or the user asks for 문서 체크, 문서 갱신, 문서 동기화, or 문서 기준.

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tdd, code-review and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 4 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 5 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 4 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep documentation and implementation aligned after user-facing code changes.

    line 10
  2. Distinctive:

    Do not classify source of truth by edit order alone.

    line 14
  3. Distinctive:

    When declared intent conflicts with tests, build behavior, or security constraints, report the conflict before editing.

    line 21
  4. Distinctive:

    Run doc-first and code-first passes, verifying examples against implementation.

    line 38
  5. Distinctive:

    Verify changes with relevant code tests or the available docs build/formatting check, then report what changed and any unresolved gaps.

    line 40
  6. Very specific:

    Read references/doc-coverage-checklist.md for audit targets, source-of-truth classification, report format, and patch guidance.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 36 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 Sync

Overview

Keep documentation and implementation aligned after user-facing code changes. Changed docs may define intended behavior that code needs to match.

Core Rule

Do not classify source of truth by edit order alone. Honor the current task's declared intent first: user request, issue, PR description, spec, implementation plan, tests, and repository guidance.

  • Code-led sync: implementation declares intended behavior; update docs to match it.
  • Docs-led sync: documentation declares intended behavior; implement code changes when requested, or report gaps for an audit.
  • Mixed change: code and docs changed together; verify consistency both ways.
  • Audit mode: the user asks for a check/report; report discrepancies without editing. If an update request leaves the source of truth ambiguous, ask before making dependent edits.

When declared intent conflicts with tests, build behavior, or security constraints, report the conflict before editing.

Choose the action from the request: checks and reports are read-only; update requests authorize targeted edits and verification. Ask only when missing scope or conflicting intent prevents a reliable choice. Honor decisions already supplied in the conversation.

Shortcuts

  • $docs-sync current branch: audit changed code/docs against the base branch.
  • $docs-sync 문서 체크: audit docs intent against implementation.
  • $docs-sync 코드 갱신: treat docs as intended behavior, update code to match, and run relevant checks.
  • $docs-sync 문서 갱신 or $docs-sync 문서 동기화: update docs to match the declared intended behavior and verify the changes.
  • $docs-sync 문서 기준: treat docs as intended behavior; audit unless the request also asks for changes.
  • $docs-sync 리포트만 or $docs-sync 리포트: audit only; do not edit docs or code.

Workflow

  1. Infer scope from the request and repository: branch or selected files, docs roots, generated docs, and exclusions. Ask only about material ambiguity.
  2. Classify source of truth from declared intent, not edit order.
  3. Run doc-first and code-first passes, verifying examples against implementation.
  4. For an audit, report discrepancies and proposed edits with evidence. For an update, apply targeted changes within the authorized scope.
  5. Verify changes with relevant code tests or the available docs build/formatting check, then report what changed and any unresolved gaps.

For an update, correct in-scope mismatches or failed examples found during verification, then rerun the affected check. If the failure reveals conflicting intent, an unrelated defect, or an unavailable dependency, report that blocker and any pending verification without broadening the task. An audit reports findings without entering an edit-and-retry loop.

Reference Routing

Read references/doc-coverage-checklist.md for audit targets, source-of-truth classification, report format, and patch guidance.

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.