notque/vexjoy-agent / skills/meta/docs-sync-checker
docs-sync-checker
VerifiedDetect documentation drift against filesystem state.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.6 KB |
| references/documentation-structure.md | markdown | 3.0 KB |
| references/integration-guide.md | markdown | 2.8 KB |
| references/sync-rules.md | markdown | 2.1 KB |
| scripts/generate_report.pyexecutable | script | 10.4 KB |
| scripts/parse_docs.pyexecutable | script | 10.9 KB |
| scripts/scan_tools.pyexecutable | script | 14.1 KB |
| scripts/validate.pyexecutable | script | 8.2 KB |
references/sync-rules.md
View on GitHub# Documentation Sync Rules
Rules for which doc must list which tool, how issues are scored, and how they are fixed. Targets and formats: `documentation-structure.md`.
## Primary documentation rules
| Tool | Rule | Severity when absent |
|------|------|----------------------|
| Skill | Every public, non-promoted `skills/*/*/SKILL.md` appears in `docs/skills.md` | HIGH |
| Agent | Every public `agents/*.md` with frontmatter `name` appears in the `## AGENTS` table of `docs/routing-map.md` | HIGH |
| Command | Every `commands/*.md` appears in a `## Slash Commands` table of `docs/REFERENCE.md` | HIGH |
| Any | A doc entry whose file is gone | MEDIUM (stale) |
A missing primary doc is an error (exit 2), not an empty list. It means this skill's target list has drifted; fix `PRIMARY_DOCS` in `scripts/parse_docs.py` and the tables in this skill.
## Fixing issues
- Generated catalogs (`docs/skills.md`, `docs/routing-map.md`): rerun the generator. A hand edit is overwritten and fails the CI `--check`.
- If a skill or agent still does not appear after regenerating, its frontmatter is the cause: check `name`, `description`, and `promoted_to`.
- `docs/REFERENCE.md`: add or remove the `/command` row, using the command's frontmatter `description`.
- Commit the tool change and its doc change together.
## Description source
The YAML `description` field is authoritative. The generators copy it; for `docs/REFERENCE.md`, use it as the Purpose cell.
## Sync score
```
sync_score = (total_tools - total_issues) / total_tools * 100
```
`total_tools` counts every discovered skill, agent, and command; `total_issues` counts missing plus stale entries. Target 100%; one missing entry hides a tool from users.
## Exceptions
- `promoted_to` skills and symlinked (private) skills or agents are never expected in a catalog.
- `agents/*.md` files without frontmatter (a shared prompt, for example) are not agents. The shared worker prompt lives at `skills/shared-patterns/base-instructions.md`, and the repo ships no agents since the retirement in plans/009.
- There is no ignore file. To hide a tool, promote or remove it.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 470k | Updated | Claude CodeCodex | Verified | Install |
| 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: 197k | Updated | Claude CodeCodex | Verified | Install |
| 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: 197k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 197k | Updated | Claude CodeCodex | Verified | Install |