update-docs
Skill93 starsChanged 20 days agoMIT-0View on GitHub
Audit and update every documentation surface in the APEX repo against the current state of skills, steering workflows, README marker tables, and the Docusaurus site under misc/website/. After any change to a skill (rename, retire, add, edit description), walk the repo, re-run script-managed surfaces if their --check fails, and reason through every tracked prose *.md to catch references that need updating. Use after adding/removing/renaming a skill, after editing SKILL.md frontmatter, after editing README marker blocks, or before publishing a docs change. Also use when the user says "update docs", "sync docs", "check docs", "run update-docs", or mentions that documentation might be stale.
87 other projects use a version of this.
Adopted by
Most recently taken up by
- rmichak/claude-skillstheir own version, first seen Nov 8, 2026
- Eclipter/agentstheir own version, first seen Nov 8, 2026
- rvdbreemen/OTGW-firmwaretheir own version, first seen Nov 8, 2026
- jmusick/skillstheir own version, first seen Nov 8, 2026
- protokol11/skillstheir own version, first seen Nov 8, 2026
- OldemarJesus/connectlife-mcp-servertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use get-pr-reviews, push-everything 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.
saffron-healthSkillget-pr-reviews
Get nicely formatted output of the last review comments on a PR. Used internally by other skills.
Also in 3 projects that use this
saffron-healthSkillpush-everything
Stage ALL changes in the repository (not just session changes), commit, and push. Use when you need to commit all pending changes.
Also in 3 projects that use this
TheKREATORSSkillinstinct-export
Export instincts from project/global scope to a file
Also in 3 projects that use this
TheKREATORSSkillinstinct-import
Import instincts from file or URL into project/global scope
Also in 3 projects that use this
NVIDIASkillgenerate-spec
Produce a feature specification covering API changes, backward compatibility, cross-language impact, performance, and a file-level change plan. Use when designing a new feature, planning a significant change, or the user asks to spec something out.
Also in 3 projects that use this
belokonmSkillfullstack-developer
End-to-end feature expert specializing in frontend-backend integration, system architecture, and complete application development
Also in 4 projects that use this
- +1 more from saffron-health
- +1 more from TheKREATORS
Other versions87 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 87
- vercel/next.js★ 143ksame name
- pipecat-ai/pipecat★ 17ksame name
- anyproto/anytype-ts★ 9.1ksame name
- vladmandic/sdnext★ 7.4ksame name
- ArcReel/ArcReel★ 6.3ksame name
- dotnet/sdk★ 3.2ksame name
- meta-pytorch/OpenEnv★ 2.8ksame name
- huggingface/OpenEnv★ 2.8ksame name
- man-group/ArcticDB★ 2.6ksame name
- fabro-sh/fabro★ 1.8ksame name
77 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 repository28 other files it gives its agents.
- rules/AGENTS.mdAGENTS.md
- apexSkill
- dotnet-aws-ecsSkill
- ecs-architectSkill
- ecs-buildSkill
- ecs-devopsSkill
- ecs-genaiSkill
- ecs-modernizeSkill
- ecs-observabilitySkill
- ecs-operation-reviewSkill
- ecs-reconSkill
- ecs-securitySkill
- eks-best-practicesSkill
- eks-buildSkill
- eks-cost-intelligenceSkill
- eks-designSkill
- eks-genaiSkill
- eks-ingress-migrationSkill
- eks-mcp-serverSkill
- eks-operation-reviewSkill
- eks-platform-engineeringSkill
- eks-reconSkill
- eks-securitySkill
- eks-upgrade-checkSkill
- eks-well-architected-reviewSkill
- graviton-migrationSkill
- skill-creatorSkill
- terraform-skillSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 81 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Before opening a PR that touches skills/
- Distinctive: line 32
If the user specifies a different scope ("since my last commit", "just the rename I did"), adjust the base accordingly.
- Very specific: line 43
Run both --check commands.
- Distinctive: line 47
Read each file in the candidate set below.
- Very specific: line 66
Every skills/<name>/README.md where present
- Distinctive: line 94
Always end with a summary table:
“Common” is measured: kept by at least 6 in 10 of the 81 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
Update Docs
Walk the APEX repo after any content change and bring every documentation surface back into sync. Two categories of surface exist: script-managed (deterministic, re-runnable) and prose (requires reasoning). Handle both in a single pass.
When to use
- A skill was added, removed, renamed, or had its frontmatter edited
- A runbook under
skills/apex/runbooks/was added, removed, or renamed - README marker blocks were edited manually
- Before opening a PR that touches
skills/ - The user asks to "check docs", "update docs", or "sync documentation"
Modes
Coding-agent mode (default in Claude Code): walk the repo, re-run scripts, propose diffs, ask before writing user-facing prose. Auto-apply mechanical fixes (script outputs, simple name substitutions in fenced code blocks).
Chat-only mode (no file-write tools available): emit the PASS/STALE table + a fix checklist of one-line commands. No file edits.
Step 1: Detect the change set
Determine what changed. Default comparison base is origin/main:
git diff --name-status origin/main...HEAD -- 'skills/**/SKILL.md' 'skills/apex/runbooks/*/*.md' 'devops-agent/**'If the user specifies a different scope ("since my last commit", "just the rename I did"), adjust the base accordingly. Also include any paths the user explicitly names.
Step 2: Tier 1 — Script-managed surfaces
Two scripts own deterministic regeneration. Detect staleness and re-run them. Never duplicate their logic.
| Surface | Stale when | Fix |
| Marker blocks (README.md, skills/README.md) | ./misc/update-all-references.sh --check exits non-zero | ./misc/update-all-references.sh |
| Docusaurus wrappers, manifest, skills index | ./misc/update-pages.sh --check exits non-zero | ./misc/update-pages.sh |
Run both --check commands. If either exits non-zero, re-run the corresponding script. In coding-agent mode, apply the changes directly. In chat-only mode, emit the fix command.
Step 3: Tier 2 — Prose ripple
Read each file in the candidate set below. Hold the change set in mind and look for stale references.
What "stale" looks like
- A skill name in prose that no longer matches a
skills/<name>/directory - A frontmatter description that was edited, where the old phrasing still appears verbatim elsewhere
- A retired runbook still referenced in a list
- A skill count or coverage claim ("APEX ships six skills") that no longer matches reality
- A path link
skills/old-name/after a rename - A removed or renamed concept still mentioned in contributor guidance
Candidate set (tracked files only — use git ls-files)
In scope:
README.mdCONTRIBUTING.mdCODE_OF_CONDUCT.mdTHIRD_PARTY_NOTICES.mdskills/README.md- Every
skills/<name>/README.mdwhere present - Every
skills/<name>/SKILL.md - Every
skills/apex/runbooks/<skill>/*.md devops-agent/README.md- Every
devops-agent/<name>/SKILL.md misc/README.mdmisc/evals/README.mdmisc/evals/_template/README.md- Every
misc/evals/<skill>/README.md misc/website/docs/intro.mdmisc/website/docs/getting-started.mdmisc/website/src/components/skillCatalog.tsandmisc/website/src/pages/index.tsx(not markdown; skillCatalog.ts holds each skill's catalogue lines, index.tsx names the /apex router)- The
SKILL_METAtable inmisc/update-pages.sh(each skill's page title and summary, under 160 characters)
Excluded (generated by scripts — never hand-edit):
misc/website/docs/skills/*.mdmisc/website/docs/skills/index.mdmisc/website/static/manifests/skills.jsonmisc/website/static/llms.txtmisc/website/docs/skills/eks/index.mdmisc/website/docs/skills/ecs/index.md
For each file, if you find stale content:
- In coding-agent mode: propose the diff. For user-facing prose changes, ask before applying. For mechanical substitutions (path renames in code fences, skill-name swaps in lists), apply directly.
- In chat-only mode: add to the checklist with file, line, and what to change.
Step 4: Final output
Always end with a summary table:
| Surface | Status | Action taken | Confirm? |
|---|---|---|---|
| Marker blocks | PASS | — | — |
| Docusaurus wrappers | STALE | Re-ran ./misc/update-pages.sh | — |
| README.md | STALE | Proposed diff | yes (line 42 prose) |
| CONTRIBUTING.md | PASS | — | — |
| skills/README.md | PASS | — | — |
| misc/evals/*/README.md | PASS | — | — |
| ... | | | |Status values: PASS (no changes needed), STALE (changes applied or proposed), SKIP (file doesn't exist yet).
Rows marked Confirm? yes require the user's approval before the change is final. Wait for their response before moving on.
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.

