bestdeejay-design/agent-skills / skills/docs-system
docs-system
VerifiedMeta-guide + router for documentation: the two branches (docs-product for 'why/what', docs-project for 'how'), the phase order, completeness levels L1/L2/L3, and the completeness checklist. Load a branch directly when the task is clearly product or engineering; load this skill for the big picture, ordering and completeness gates. Triggers: 'документация', 'набор документации', 'каталог документов', 'документация структура', 'полная документация', 'docs catalog', 'documentation structure', 'какую документацию писать'.
| File | Kind | Size |
|---|---|---|
| ROADMAP.md | markdown | 4.7 KB |
| SKILL.md | skill md | 3.4 KB |
| evals/evals.json | config | 570 B |
| examples/example-monorepo/README.md | markdown | 5.8 KB |
| readme.ru.md | markdown | 1.1 KB |
| references/completeness.md | markdown | 3.1 KB |
| references/levels.md | markdown | 5.0 KB |
| references/order.md | markdown | 3.4 KB |
| skill.json | config | 1.7 KB |
references/completeness.md
View on GitHub# Completeness Checklist — the delivery gate
Run this before declaring documentation "done". Every item must pass at the
**chosen level** (`references/levels.md`); if the set has no explicit level,
default to L1 and grow later. L2/L3 ownership: every unchecked box is a blocking
inconsistency.
> **RU:** прогоняется перед сдачей документации. Каждый пункт должен сходиться
> на выбранном уровне. Для L2/L3 несоблюдение пункта — блокер.
## A. Product side
- [ ] VISION (1 paragraph), audience, problem, out-of-scope, success criteria.
- [ ] PRD: goals + non-goals; every story has a priority; success metrics have
baseline → target; acceptance criteria are testable.
- [ ] ROADMAP: milestones ordered by value; each has date/target + a metric
proof (not a wishlist).
- [ ] FEATURES: every feature has a ✅/ / status that matches reality.
## B. Entry & navigation
- [ ] A reader/agent finds "what is this project?" in ≤30 seconds.
- [ ] One entry point routes "topic → file" (`ENTRY.md` at L2+, README at L1).
- [ ] No dead links: every doc referenced in the entry point exists; every doc
is reached from something above it.
## C. Truth & drift
- [ ] Hierarchy of truth declared (which doc wins on conflict) — in
`docs/REFERENCE.md` (L2+).
- [ ] Drift table populated: every known doc-vs-fact mismatch is either fixed or
has an explicit row. **No silent inconsistencies.**
- [ ] No fact duplicated in two docs unless one is the source and the other an
explicit link to it.
## D. Contracts & tests
- [ ] Contracts were written **before** code (API-first) and match implemented
endpoints/events — no route "invented" outside the spec.
- [ ] `TEST_CASES.md` (L2+) covers planned scenarios + coverage matrix; contract
conformance tests exist for each contract.
- [ ] L1: if only `TEST_PLAN.md` exists — its tests actually run and pass.
## E. Delivery & runbook
- [ ] `DEV_GUIDE.md` / README Quick start reproduce a successful run from a clean
clone (commands, env vars, migrations).
- [ ] Errors found while running have a `TROUBLESHOOTING.md` entry.
- [ ] `AGENT.md` (L2+ / agent-assisted): roles, phases, Definition of Done,
commit gate — present and referenced.
## F. Map (L2+)
- [ ] `REFERENCE.md` has a card for **every doc** (purpose, structure, facts,
links) — including a card for REFERENCE itself.
- [ ] ADR table lists every ADR with status (active/superseded); ADR tracking
works.
- [ ] The "how to maintain this file" section is up to date.
## G. Community & legal (public repos)
- [ ] `LICENSE`, `CONTRIBUTING.md`, `CODE_OF_CONDUCT.md`, `SECURITY.md` exist
and are linked from README.
## How to run
1. Fix in the order that unblocks the next item — product → entry → truth →
contracts/tests → delivery → map.
2. Every «No» ends either in a fix **or** an explicit drift-table row — never
silence.
3. Re-run until green. Green = "documentation set complete at this level",
ready for `docs/REFERENCE.md` sign-off.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 |