write-docs
Skill0 starsChanged 2 months agoApache-2.0View on GitHub
Write or update a project's documentation, such as a README, a guide, a how-to, a contributor document, or a reference page, with every claim checked against the code and the project's own writing rules applied, then hand the change to implement-issue. Use it whenever a user asks to write, update, fix, or bring documentation up to date, including when a README or guide no longer matches the code, even if the request does not mention sources or verification. Do not use it to change code, configuration, or behavior.
43 other projects use a version of this.
Adopted by
Most recently taken up by
- alchemy-run/alchemy-effecttheir own version, first seen Nov 9, 2026
- alchemy-run/alchemytheir own version, first seen Nov 8, 2026
- adhamhaithameid/write-skillstheir own version, first seen Nov 8, 2026
- dzhng/jevgreptheir own version, first seen Nov 7, 2026
- oberon-systems/enggraphtheir own version, first seen Nov 6, 2026
- dzhng/skillstheir own version, first seen Nov 4, 2026
Used with
Projects with it also use close-spec, design-with-images and 10 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.
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 5 projects that use this
dzhngSkilldesign-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
Also in 5 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 5 projects that use this
LucasMatuszewskiSkillaudit-agents
Audit and maintain agent configuration files (.claude/agents, AGENTS.md, CLAUDE.md, agent-memory). Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines. Fixes all issues and commits.
Also in 5 projects that use this
wolverin0Skillaudit-decisions
Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.
Also in 4 projects that use this
rhnfzlSkillexplore-unknowns
Walk the user through mapping the unknowns of a task before, during, and after they build it, and hand them a four-quadrant map (settled ground, open decisions, taste, and landmines) they keep. Reach for this eagerly whenever a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, a build-queue or architecture-changing task is about to start, a mid-build deviation needs capturing, or a finished change needs buy-in or verified understanding before merge. Trigger even when the skill is not named: "do a blindspot pass", "find my unknown unknowns", "interview me about this change", "brainstorm the approach for a task I am about to build", "help me scope this", "what am I missing here", "plan this before I build", "I know nothing about X in this codebase". When a territory profile is present it reads memory and the graph first and feeds the map into the build pipeline; without one it degrades to a plain general map. Not for trivial or mechanical tasks with clear acceptance criteria, single-fact lookups, pure debugging of a known symptom, or pure code review, those have their own tools. Do not use it to run the build itself; the map is the deliverable and implementation remains a separate task, whether it has not started or is already underway.
Also in 5 projects that use this
- +6 more from dzhng
Other versions43 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 43
- tldraw/tldraw★ 51ksame name
- tabler/tabler★ 42ksame name
- videojs/video.js★ 40ksame name
- PrefectHQ/prefect★ 24ksame name
- comet-ml/opik★ 23ksame name
- coder/coder★ 17ksame name
- browseros-ai/BrowserOS★ 14ksame name
- Agenta-AI/agenta★ 4.9ksame name
- liveblocks/liveblocks★ 4.8ksame name
- dzhng/jevgrep★ 3.2ksame name
33 more not listed
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 repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyze-codebaseSkill
- analyze-projectSkill
- propose-improvementsSkill
- retrospect-workSkill
- triage-issuesSkill
- debug-codeSkill
- refactor-codeSkill
- resolve-defectSkill
- write-testsSkill
- develop-minecraft-fabricSkill
- develop-minecraft-forgeSkill
- audit-workflow-enforcementSkill
- bootstrap-projectSkill
- develop-dartSkill
- develop-goSkill
- develop-javaSkill
- develop-kotlinSkill
- develop-swiftSkill
- develop-typescriptSkill
- update-dependenciesSkill
- develop-android-composeSkill
- develop-compose-multiplatformSkill
- develop-flutterSkill
- develop-iosSkill
- develop-kotlin-multiplatformSkill
- develop-react-nativeSkill
- create-issueSkill
- create-prSkill
- deliver-changeSkill
- fix-prSkill
- implement-issueSkill
- improve-projectSkill
- merge-prSkill
- plan-issueSkill
- review-prSkill
- develop-reactSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 9 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 42 edited versions we read keep these.
9
Distinctive
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 13
Write or update the document within the agreed scope.
- Very specific: line 14
Verify every claim, command, path, and link, then complete the list only when each claim is verified or listed as unverified.
- Distinctive: line 16
Keep exactly one item in progress.
- Distinctive: line 32
Stop and ask only when you cannot write the documentation without a decision that is not about wording, such as choosing between two …
- Very specific: line 45
Prefer the project's own entry points in examples, such as a mise.toml task or a Makefile target, over raw tool commands, because readers …
- Distinctive: line 53
Use the project's glossary terms.
- Distinctive: line 54
Keep examples short and runnable as written.
- Distinctive: line 55
Keep the existing structure and headings unless the request asks to change them.
- Distinctive: line 60
Run each command the document shows when it is safe to run, or check its definition when it is not, and record the result.
- Distinctive: line 62
Check that every path and file name exists, and that every internal link and anchor resolves.
- Distinctive: line 64
Run the project's documentation checks when it has them, such as a Markdown linter or a link checker.
“Common” is measured: kept by at least 6 in 10 of the 42 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.
Files
Write Docs
Todo List
- in progress: Resolve the document, its readers, its scope, and the project's writing rules.
- Collect the source in the repository for every claim the document will make.
- Write or update the document within the agreed scope.
- Verify every claim, command, path, and link, then complete the list only when each claim is verified or listed as unverified; hand off the change to
implement-issue.
Keep exactly one item in progress. Mark an item complete only when its evidence exists. Use the host's native Todo List, or keep the same list as a Markdown checklist when no native list is available.
Resolve and Guard
- This is a document-layer skill. It writes documentation files in the working
tree and hands the change to
implement-issue, which commits it on the Issue branch. It does not commit, create a branch, an Issue, or a Pull Request. - Resolve the target file to write or change, who reads it, and what it must cover, from the request or its Issue. Do not widen the scope to other files.
- Change documentation only. When the request pairs a documentation change
with a code, configuration, or behavior change, write the documentation for
the code as it is today, leave the other change undone, record it, and hand
it to
implement-issue. Do not describe the requested behavior as if it existed. - Stop and ask only when you cannot write the documentation without a decision that is not about wording, such as choosing between two conflicting behaviors in the code or stating a policy the project has not set.
- Find the project's writing rules before writing: a style guide, a glossary,
CONTRIBUTING.md, or a linter configuration such as.markdownlint.yamlor.vale.ini. They take precedence; see "Writing quality" for the rules that apply when the project has none.
Collect sources
- For each claim the document will make, find its source: the function signature, the command definition, the configuration key, the default value, or the test that shows the behavior. Read the source, not an older document.
- Prefer the project's own entry points in examples, such as a
mise.tomltask or aMakefiletarget, over raw tool commands, because readers run what the project supports.
Write
- State what the reader can do and how, with the command or code they need.
- Name each thing in full on first mention and use that term throughout. Use the project's glossary terms.
- Keep examples short and runnable as written.
- Keep the existing structure and headings unless the request asks to change them.
Verify
- Run each command the document shows when it is safe to run, or check its definition when it is not, and record the result.
- Check that every path and file name exists, and that every internal link and anchor resolves.
- Run the project's documentation checks when it has them, such as a Markdown linter or a link checker.
- List every claim you could not verify, with the reason.
Handoff
Report the changed files, a table of claims with their sources, every claim
left unverified, and every request left undone because it was not
documentation. Hand the working-tree change and this record to
implement-issue.
Writing quality
These rules bind the documentation files this skill writes into the project and the handoff report. Follow the project's own writing rules. Where the project states none, follow persistent prose.
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.

