oliver-kriska/claude-elixir-phoenix / .claude/skills/docs-check
docs-check
VerifiedCONTRIBUTOR TOOL - Validate plugin against latest Claude Code documentation. Catches breaking changes, deprecations, discovers new features. Run before releases or periodically. NOT part of the distributed plugin.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.2 KB |
| references/doc-pages.md | markdown | 2.2 KB |
| references/validation-rules.md | markdown | 5.7 KB |
references/doc-pages.md
View on GitHub# Documentation Pages
Maps plugin component types to Claude Code doc pages used for validation.
## Source
All docs available at `https://code.claude.com/docs/en/{page}.md`
Index at `https://code.claude.com/docs/llms.txt`.
## Pages Fetched (All, Always)
| Page | Component | Why |
|------|-----------|-----|
| `sub-agents.md` | Agents | Frontmatter schema, tool names, model/permission values |
| `skills.md` | Skills | SKILL.md format, frontmatter fields, directory structure |
| `hooks.md` | Hooks | Event names, hook types, schema, matcher syntax |
| `hooks-guide.md` | Hooks | Hook patterns, examples, best practices |
| `plugins-reference.md` | Plugin config | plugin.json schema, field inventory |
| `plugins/marketplace-reference.md` | Marketplace | marketplace.json schema, plugin entries |
| `plugins/dependencies.md` | Plugin config | `dependencies`, version ranges, `{name}--v{version}` tags |
| `plugins/cli-reference.md` | Tooling | `claude plugin validate/tag/details/eval` flags |
| `plugins/measure.md` | Budget | Always-on vs on-invoke token cost |
| `plugin-evals.md` | Evals | `claude plugin eval` cases, graders, ablation |
| `plugins.md` | General | Plugin creation guidance, directory conventions |
| `settings.md` | Config | Permission mode semantics, global settings |
| `mcp.md` | MCP | MCP server configuration in plugins |
Total: 13 pages. All fetched on every run. Cached for 24h. `plugin-marketplaces.md`
is now the "Create a marketplace" guide; the schema moved to `plugins/marketplace-reference.md`.
## Fetch Strategy
The `scripts/fetch-claude-docs.sh` script handles everything:
- **Default**: Fetch all 13 pages, skip if cached within 24h
- **`--force`**: Re-download regardless of cache age
- **`--quick` mode**: Skill skips fetching entirely (structural checks only)
No conditional fetching. No partial downloads. Always all pages.
## Cache Location
`.claude/docs-check/docs-cache/` (gitignored). The orchestrator reads
from cache and crashes if files are missing.
## Size
Individual pages: 5-80KB each. Total: ~420KB.
Each validation worker gets 1-2 pages (~8-20K tokens) — well within
the 200K context limit. No indexing or compression needed for docs.
**NEVER fetch `llms-full.txt`** (~500KB+ single file with all 57+ pages).
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: 471k | 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: 198k | 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: 198k | 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: 198k | Updated | Claude CodeCodex | Verified | Install |