paa-docs-header-first
Efficiently navigates and maintains documentation within the PAA repository.
Install
mkdir -p .claude/skills/paa-docs-header-first && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12913" && unzip -o skill.zip -d .claude/skills/paa-docs-header-first && rm skill.zipInstalls to .claude/skills/paa-docs-header-first
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use this skill when the task involves finding, choosing, or updating PAA repo documents.Key capabilities
- →Find current documents for a domain
- →Find documents by component
- →Find documents by lifecycle stage
- →Inspect one document header
- →Inspect document relationships
- →Lint governed documents
How it works
The skill uses a CLI tool to interact with PAA repository documents, prioritizing header-first discovery to efficiently find, inspect, and manage documentation.
Inputs & outputs
When to use paa-docs-header-first
- →Finding project documentation
- →Linting governed docs
- →Inspecting document relationships
About this skill
PAA Docs Header-First
Use this skill when the task involves finding, choosing, or updating PAA repo documents.
Goal
Default to header-first discovery instead of bulk-reading document bodies.
This skill exists to reduce:
- context waste
- stale-doc drift
- filename-memory dependence
- rereading of irrelevant prose
Default workflow
- Start with the doc CLI, not full document reads.
- Use header-only results to identify the smallest relevant doc set.
- Only then read the full body of the top 1 to 4 relevant docs.
Commands
Repo root:
/Users/billyweisberg/Repos/billyweisberg/paa-platform
CLI:
python scripts/docs/paa_docs.py
Discovery
- find current docs for a domain:
python scripts/docs/paa_docs.py current --root /Users/billyweisberg/Repos/billyweisberg/paa-platform --domain <domain>
- find by component:
python scripts/docs/paa_docs.py find --root /Users/billyweisberg/Repos/billyweisberg/paa-platform --component <ComponentName>
- find by lifecycle stage:
python scripts/docs/paa_docs.py find --root /Users/billyweisberg/Repos/billyweisberg/paa-platform --stage <design|plan|test|deploy>
- inspect one header:
python scripts/docs/paa_docs.py show --root /Users/billyweisberg/Repos/billyweisberg/paa-platform --path <doc-path>
- inspect relationships:
python scripts/docs/paa_docs.py related --root /Users/billyweisberg/Repos/billyweisberg/paa-platform --doc-id <doc-id>
Governance
- lint governed docs:
python scripts/docs/paa_docs.py lint --root /Users/billyweisberg/Repos/billyweisberg/paa-platform
- show stale governed docs:
python scripts/docs/paa_docs.py stale --root /Users/billyweisberg/Repos/billyweisberg/paa-platform
Authoring
- create a new governed doc:
python scripts/docs/paa_docs.py new-doc --root /Users/billyweisberg/Repos/billyweisberg/paa-platform --path <doc-path> --doc-type <type> --status <status> --summary <summary>
- add or normalize a header on an existing doc:
python scripts/docs/paa_docs.py set-header --root /Users/billyweisberg/Repos/billyweisberg/paa-platform --path <doc-path> --doc-type <type> --status <status>
Rules
- Do not bulk-read docs when the CLI can narrow the target set first.
- Prefer
current,find, andrelatedbefore opening full documents. - Treat docs without headers as legacy until upgraded.
- When writing a new governed doc, use
new-docorset-headerinstead of hand-authoring the header.
When not to use it
- →Do not bulk-read docs when the CLI can narrow the target set first
- →Do not treat docs without headers as governed
- →Do not hand-author headers for new governed docs
Prerequisites
Limitations
- →Prefer `current`, `find`, and `related` before opening full documents
- →Treat docs without headers as legacy until upgraded
How it compares
This workflow uses a dedicated CLI for header-first document discovery and governance, reducing the need to read full document bodies unnecessarily.
Compared to similar skills
paa-docs-header-first side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| paa-docs-header-first (this skill) | 0 | 2mo | No flags | Beginner |
| ml-paper-writing | 48 | 6mo | Review | Advanced |
| docs-review | 10 | 7mo | No flags | Beginner |
| claude-md-improver | 21 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
ml-paper-writing
davila7
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
docs-review
metabase
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.
claude-md-improver
anthropics
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
write-docs
tldraw
Writing SDK documentation for tldraw. Use when creating new documentation articles, updating existing docs, or when documentation writing guidance is needed. Applies to docs in apps/docs/content/.
update-docs
vercel
This skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what docs need updating", "sync docs with code", "scaffold docs for this feature", "document this feature", "review docs completeness", "add docs for this change", "what documentation is affected", "docs impact", or mentions "docs/", "docs/01-app", "docs/02-pages", "MDX", "documentation update", "API reference", ".mdx files". Provides guided workflow for updating Next.js documentation based on code changes.
wiki-architect
microsoft
Analyzes code repositories and generates hierarchical documentation structures with onboarding guides. Use when the user wants to create a wiki, generate documentation, map a codebase structure, or understand a project's architecture at a high level.