Skip to content

notque/vexjoy-agent / skills/meta/docs-sync-checker

docs-sync-checker

Verified

Detect documentation drift against filesystem state.

FileKindSize
SKILL.mdskill md11.6 KB
references/documentation-structure.mdmarkdown3.0 KB
references/integration-guide.mdmarkdown2.8 KB
references/sync-rules.mdmarkdown2.1 KB
scripts/generate_report.pyexecutablescript10.4 KB
scripts/parse_docs.pyexecutablescript10.9 KB
scripts/scan_tools.pyexecutablescript14.1 KB
scripts/validate.pyexecutablescript8.2 KB

references/documentation-structure.md

View on GitHub
# Documentation Structure Reference

Where each tool type is documented, in what format, and how a drift gets fixed. `scripts/parse_docs.py` (`PRIMARY_DOCS`) is the source of truth for the targets; `scripts/validate.py` fails if any target is missing.

## Primary docs

| Tool type | Filesystem | Primary doc | Maintained by | Fix a drift |
|-----------|------------|-------------|---------------|-------------|
| Skill | `skills/<category>/<name>/SKILL.md` | `docs/skills.md` | `scripts/generate-skills-doc.py` | Rerun the generator |
| Agent | `agents/<name>.md` | `docs/routing-map.md` (`## AGENTS` table) | `scripts/generate-routing-map.py` | Rerun the generator |
| Command | `commands/<name>.md` | `docs/REFERENCE.md` (`## Slash Commands` tables) | Hand-written | Add or remove the row |

There is no `agents/README.md` or `commands/README.md`. Never create one to satisfy this check.

## Formats the parser reads

`docs/skills.md`: one table per category; the first cell is the backticked skill name.

```markdown
| Skill | Description | Invoke |
|-------|-------------|--------|
| `deploy` | Deploy and infrastructure: web deploy, cron, package install, shell configuration. | `/deploy` |
```

`docs/routing-map.md`, `## AGENTS (N)` section: the first cell is the bare agent name. The repo ships no agents since plan 009, so rows appear only for private overlay agents.

```markdown
| name | when to call (description) | triggers | FORCE | not_for | pairs_with |
|---|---|---|---|---|---|
| my-overlay-engineer | Go development: features, debugging, code review, performance | go, golang | | ... | programming |
```

`docs/REFERENCE.md`, `## Slash Commands` section: the first cell is the backticked `/command`. Rows whose first cell is not a `/command` (for example the "Available via `/do` Routing" table) are ignored.

```markdown
| Command | Purpose |
|---------|---------|
| `/retro` | Routing and review telemetry from learning.db: route health, route stats, errors, evidence, review false positives |
```

## Who is expected in each doc

| Tool | Expected in primary doc | Why |
|------|-------------------------|-----|
| Skill with `promoted_to` | No | `generate-skill-index.py` drops it from the index, so the catalog omits it |
| Skill or agent reached through a symlink | No | Private component; the generators strip private names |
| Every other skill, agent, and command | Yes | Missing entry, HIGH |
| Doc entry with no file on disk | — | Stale entry, MEDIUM |

## Root README.md

Narrative, not a catalog. The parser records its `/command` and `*-engineer` mentions for the report but never flags them.

## Related CI checks

The generated catalogs are already gated in `.github/workflows/test.yml`:

- `python3 scripts/generate-skills-doc.py --check` — `docs/skills.md` matches a fresh render.
- `python3 scripts/generate-routing-map.py --check` — `docs/routing-map.md` matches a fresh render.
- `python3 scripts/validate-doc-links.py`, `validate-doc-counts.py`, `validate-doc-commands.py` — links, count claims, and script paths named in docs.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall