docs-update
Skill1 starsChanged 3 months agoMITView on GitHub
Audit all Hangar docs (README, ai-workflow, ARCHITECTURE, THREAT_MODEL) for missing features, stale content, and prose quality issues. Reports findings and, on approval, applies fixes. Use before a release, after a significant feature, or whenever docs feel out of date.
19 other projects use a version of this.
Adopted by
Most recently taken up by
- TsukiNi22/skillstheir own version, first seen Nov 16, 2026
- TsukiNi22/ai-utilstheir own version, first seen Nov 16, 2026
- jellydn/my-ai-toolstheir own version, first seen Nov 15, 2026
- microsoft/veronatheir own version, first seen Nov 8, 2026
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- aka-kika/akakika-skillstheir own version, first seen Nov 1, 2026
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- microsoft/verona★ 3.7ksame name
- warpdotdev/oz-skills★ 825same name
- bagofwords1/bagofwords★ 463same name
- jellydn/my-ai-tools★ 129same name
- hiromaily/go-crypto-wallet★ 128same name
- TangleML/tangle-ui★ 104same name
- buildomator/buildomator★ 102same name
- harukikuri/spotnote★ 25same name
- aka-kika/akakika-skills★ 11same name
- Escoto/RustifyMyClaw★ 8same name
9 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 repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- aiwf-syncSkill
- config-fieldSkill
- hangar-validateSkill
- releaseSkill
- smokeSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
8
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
- Distinctive: line 41
Look for descriptions that no longer match the current product — renamed UI elements, removed options, changed defaults, moved files.
- Distinctive: line 71
Check that no doc contradicts a rule in CLAUDE.md:
- Distinctive: line 74
Never mention the old name "FleetView"
- Distinctive: line 82
Check the Security Controls — Required list: have any been implemented since the last model update?
- Distinctive: line 93
If no issues are found in a category, say so in one line.
- Distinctive: line 96
After the report, ask: "Apply these fixes?"
- Distinctive: line 103
When editing, preserve the existing style: sentence case, terse, no trailing summaries.
- Distinctive: line 104
Prefer removing noise over adding words.
“Common” is measured: kept by at least 6 in 10 of the 18 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
Audit all Hangar documentation for gaps, staleness, and prose quality issues. Propose updates; apply them only on approval.
Inputs to read (in parallel)
README.md— fulldocs/ai-workflow.md— fulldocs/ARCHITECTURE.md— fulldocs/THREAT_MODEL.md— fullCLAUDE.md— conventions that docs must reflectCHANGELOG.md— recently shipped features/fixeshangar.config.example.json— source of truth for config fields- Recent git log:
git log --oneline -40— catch anything shipped after the last CHANGELOG entry
What to look for
A. Missing or undocumented features
Compare CHANGELOG entries and recent commits against what each doc describes. Flag any user-visible feature or behaviour that shipped but isn't mentioned.
For each gap, note:
- Which doc it belongs in
- A proposed one-line addition or the section it should go under
Docs most likely to fall behind:
README.md— config table, feature highlights, screenshots calloutsdocs/ai-workflow.md— new AIWF phases, skills, or routesdocs/ARCHITECTURE.md— new components, changed data flows, updated tech stack versions, new known-debt items, resolved debt that should be removed
B. Stale or inaccurate content
Look for descriptions that no longer match the current product — renamed UI elements, removed options, changed defaults, moved files.
Key cross-checks:
README.mdconfig table vshangar.config.example.jsonfield names and defaultsdocs/ARCHITECTURE.mdcomponent list vsserver/src/file listingdocs/ARCHITECTURE.mdtech stack table vs root/server/webpackage.jsondependency versionsdocs/THREAT_MODEL.mdattack surface table vs the routes defined inserver/src/index.tsdocs/THREAT_MODEL.mdsecurity controls vs current implementation (checkserver/src/index.tsCORS config, rate limiter, andserver/src/aiwf.tsexec calls)
C. Prose quality: leaked implementation details
Scan prose sections (not API tables, "Where it lives", or developer-reference sections — those are intentional) for internal names that would confuse a user who hasn't read the source:
- TypeScript field names in backticks used as explanation (e.g.
(`skipWorktree`)) - Internal constant or function names mid-sentence
- Source file paths in plain-English paragraphs
- Internal type shape mappings
The test: would a reader who hasn't seen the code find this helpful or confusing? If confusing, rewrite in terms of observable behaviour.
Note: API tables, "Where it lives", "Card file format", and developer-reference sections intentionally use implementation names — leave those alone.
D. CLAUDE.md convention drift
Check that no doc contradicts a rule in CLAUDE.md:
- Naming: product is Hangar, data dir is
.hangar/, env prefix isHANGAR_* - Never mention the old name "FleetView"
- Docs live in
docs/— no standalone doc files in the repo root
E. Threat model drift (THREAT_MODEL.md only)
For each row in the Attack Surface table, verify the route still exists in
server/src/index.ts. Flag routes that were added or removed.
Check the Security Controls — Required list: have any been implemented since the last model update? Move them to Implemented if so.
Report
Group findings under the five categories above. For each finding state:
- File + section where the issue lives
- What's wrong (one sentence)
- Proposed fix (exact text to add/change/remove, or a clear description)
If no issues are found in a category, say so in one line. Report findings for all four docs before asking to apply.
After the report, ask: "Apply these fixes?"
- Yes → make all edits, then commit with
docs: <short summary>. Do not run typecheck (docs-only change). - No → stop; leave the files as-is.
- Selective → the user may name specific findings to apply; apply only those.
When editing, preserve the existing style: sentence case, terse, no trailing summaries. Prefer removing noise over adding words.
Note on screenshots
docs/screenshots/ is managed by npm run screenshots (the Playwright script), not by this
skill. If screenshots appear obviously outdated (UI elements renamed, layout changed), note it
as a finding but do not attempt to update them here — direct the user to run
npm run screenshots instead.
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.

