documenter
Skill4 starsChanged 11 days agoMITView on GitHub
Evidence-backed review, writing, revision, or restructuring of durable READMEs, specs/ADRs, agent guides, and public API/release docs when claims or structure need judgment. Route AGENTS.md to agents-md-generator; add documenter-coauthoring for staged work. Let matching domain skills lead when code, packaging, or release machinery also changes. Not for mechanical copy edits, chat summaries/handoffs, prompt behavior, binary-file work, regulated document control, or docs-site tooling alone.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- felvieira/claude-skills-fvtheir own version, first seen Sep 2, 2026
- LiminaLabsAI/ToolsConnectortheir own version, first seen Apr 23, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- felvieira/claude-skills-fv★ 27same name
- LiminaLabsAI/ToolsConnector★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agentic-sdlc-improvementSkill
- agentic-sdlcSkill
- agent-skill-generatorSkill
- agents-md-generatorSkill
- backend-guidanceSkill
- backend-systems-guidanceSkill
- bounded-delegationSkill
- chrome-devtools-axiSkill
- coding-guidance-bashSkill
- coding-guidance-cppSkill
- coding-guidance-goSkill
- coding-guidance-go-tuiSkill
- coding-guidance-pythonSkill
- coding-guidance-qtSkill
- context-engineeringSkill
- deepseek-harnessSkill
- design-md-authorSkill
- development-contract-processSkill
- development-contract-repo-overlay-templateSkill
- development-contract-systemSkill
- documenter-coauthoringSkill
- dream-thinkingSkill
- fuse-skillsSkill
- godotSkill
- go-testing-with-testifySkill
- jekyllSkill
- lighthouseSkill
- playwright-testingSkill
- project-config-and-testsSkill
- project-core-devSkill
- project-platform-diagnoseSkill
- project-release-maintainerSkill
- project-vendor-boundarySkill
- prompt-engineeringSkill
- recursive-thinkingSkill
- security-identity-accessSkill
- securitySkill
- setup-playwrightSkill
- story-clarifierSkill
- story-implementation-plannerSkill
- story-repo-scoutSkill
- story-to-plan-orchestratorSkill
- tester-mindsetSkill
- thinkingSkill
- ui-design-guidanceSkill
- ui-guidanceSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. About 0 are common, 16 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Treat review and chat-only draft requests as read-only.
- Distinctive: line 14
Before editing, inspect the target and relevant initial diff when available.
- Very specific: line 17
Use agents-md-generator as primary for root or nested repository AGENTS.md files.
- Very specific: line 19
Add documenter-coauthoring for user-directed context gathering, outline agreement, or staged drafting.
- Distinctive: line 22
When implementation, release machinery, or doc-site infrastructure also changes, use the relevant implementation or project skill for that …
- Distinctive: line 36
Use a specialized workflow for regulated document control.
- Distinctive: line 43
document type and output target
- Distinctive: line 45
Read the target, applicable local guidance, existing changes, and evidence relevant to affected claims:
- Distinctive: line 68
update only affected sections for a narrow edit
- Distinctive: line 70
before restructuring, map meaningful content as retained, moved, or intentionally removed and search for inbound links or anchors that may …
- Distinctive: line 78
keep examples free of credentials, private data, and environment-specific secrets
- Distinctive: line 86
run applicable existing documentation builds, formatters, linters, or link checks
- Distinctive: line 88
check local paths, anchors, identifiers, filenames, and cross-references
- Distinctive: line 89
run examples only when they are safe and local
- Distinctive: line 90
do not publish, deploy, release, install dependencies, migrate data, or cause other consequential mutations without the required authority.
- Distinctive: line 101
Use the repository's established format first.
- Distinctive: line 115
API documentation or comment: follow native language tooling and describe inputs, outputs, errors, invariants, side effects, and examples …
- Distinctive: line 124
When revising this skill family or its activation boundary, use references/trigger-evals.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Documenter
Boundaries And Composition
- Treat review and chat-only draft requests as read-only. Edit repository files only when the user asks to create or update them. If the user later switches to apply mode, refresh the target, evidence, applicable guidance, and initial diff before editing.
- Before editing, inspect the target and relevant initial diff when available. Preserve and attribute existing changes, patch around clear overlaps, and stop rather than overwrite when ownership or intended content is ambiguous.
- Use
agents-md-generatoras primary for root or nested repositoryAGENTS.mdfiles. - Add
documenter-coauthoringfor user-directed context gathering, outline agreement, or staged drafting. Document length neither selects nor excludes it. - When implementation, release machinery, or doc-site infrastructure also changes, use the relevant implementation or project skill for that work and apply this skill to the documentation content.
- For an authorized change involving generated output, find its authoritative source, determine whether source and output must remain synchronized, and inspect the generator's side effects before editing. Regenerate only when safe and authorized; never hand-edit the output. If required synchronization cannot be completed, do not create a partial inconsistent state. When local policy permits temporary divergence, leave it only with explicit user acceptance and never report that state as complete. If a failed regeneration already created a partial state, undo only this task's safely attributable delta when possible; otherwise stop. When synchronization remains blocked, report exact source and output states, the blocking side effect or dependency, and the smallest authority or safe tooling needed to continue.
- Use a specialized workflow for regulated document control.
Core Workflow
- Classify the work before writing:
- intent: review, chat-only draft, or apply
- audience and reader task
- document type and output target
- claim status: current, proposed, normative, or historical
- Read the target, applicable local guidance, existing changes, and evidence
relevant to affected claims:
- current behavior: code, config, schemas, tests, safe command output, shipped artifacts, and applicable versioned primary sources for external contracts
- proposed behavior: supplied requirements, draft decisions, explicit user direction, and visible open questions
- normative behavior: accepted decisions, approved specifications, policies, and standards
- historical claims: versioned records, changelogs, release artifacts, ADRs, and other dated evidence Local guidance controls placement and conventions; claim-specific evidence controls factual content. Reconcile conflicts by scope, version, and authority. Expose unresolved material conflicts and pause when the requested edit requires choosing a source; never choose silently or change implementation to make prose true. A proposal may preserve an unresolved conflict, but factual current-state documentation must label a disputed material claim as unknown or stop when settling it is required. For review-only work, validate as applicable and return prioritized, evidenced findings with limitations; skip drafting and edit-only completion. For a chat-only draft, continue without repository writes and label its validation status.
- Choose the smallest coherent change:
- update only affected sections for a narrow edit
- outline a new or large document before drafting it autonomously
- before restructuring, map meaningful content as retained, moved, or intentionally removed and search for inbound links or anchors that may break; when applying the change, update in-scope callers, preserve a compatible anchor, or defer the breaking removal and report it
- Draft in the repository's native markup and language conventions:
- organize standalone pages around one dominant reader task; gateway documents such as READMEs may deliberately orient and route several tasks
- mark planned behavior and illustrative examples clearly
- keep examples free of credentials, private data, and environment-specific secrets
- for API comments, document contracts and non-obvious behavior rather than narrating syntax
- Validate proportionally:
- inspect validation commands for file writes, generated output, dependency installation, and external effects before running them; in review or chat-only draft mode, use read-only or check-only variants
- run applicable existing documentation builds, formatters, linters, or link checks
- check local paths, anchors, identifiers, filenames, and cross-references
- run examples only when they are safe and local
- do not publish, deploy, release, install dependencies, migrate data, or cause other consequential mutations without the required authority; authoring or validation intent does not supply that authority
- report important examples and commands as observed, statically inspected, illustrative, or unverified when the distinction matters
- Tighten and hand off: remove duplication and accidental placeholders, link new durable docs from the nearest existing index when appropriate, review the resulting diff when files changed, and report checks plus material uncertainty.
Document-Type Decisions
Use the repository's established format first. Use Diataxis as a lens for the reader's dominant need, not as mandatory site architecture.
- Tutorial: teach by doing and make each stage produce an observable result.
- How-to: solve one known task without unrelated theory.
- Reference: present contracts, options, flags, or facts for fast lookup.
- Explanation: clarify concepts, rationale, and trade-offs.
- README or hub: orient its audience and include or link only the install, use, build, test, or release workflows relevant to that audience.
- Spec or proposal: state status, problem, scope, constraints, decisions, and unresolved questions appropriate to its phase.
- ADR: separate context, decision, status, and consequences.
- Changelog or release note: emphasize user-visible effects, breaking changes, and required upgrade action.
- API documentation or comment: follow native language tooling and describe inputs, outputs, errors, invariants, side effects, and examples only where they add useful contract information.
Bundled References
- Load references/doc-templates.md when no stronger local format exists and a compact README, ADR, endpoint, API-comment, or changelog structure would help.
- When revising this skill family or its activation boundary, use references/trigger-evals.md.
Completion Criteria
For review-only work, finish when findings are prioritized, evidenced, scoped, and paired with material limitations. For a draft or applied change, finish when the artifact serves its stated audience and current stage; current, proposed, normative, and historical claims are distinguishable; material claims have appropriate evidence; links and examples have an honest validation status; required generated artifacts are synchronized; incomplete synchronization is reported as unfinished work rather than completion; meaningful content was not lost silently; and placeholders are removed or explicitly labeled and accepted for the current stage.
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
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.

