bestdeejay-design/agent-skills / skills/docs-project
docs-project
VerifiedProject (engineering) documentation branch — the 'how': README, ENTRY, AGENT/DELIVERY runbooks, and docs/ (REFERENCE map, ARCHITECTURE, ADR, SAGA, TEST_CASES, DEV_GUIDE, IMPROVEMENTS, TROUBLESHOOTING, BACKLOG, REVIEW, STATUS) plus contracts/ (OpenAPI/AsyncAPI — machine truth written BEFORE code). The map rule: every doc gets a card in REFERENCE.md. Full catalog + checklist in references/project-docs.md. Triggers: 'проектная документация', 'архитектура документация', 'adr', 'engineering docs', 'документация разработчика', 'контракты openapi', 'project docs', 'инженерная документация'.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.3 KB |
| readme.ru.md | markdown | 1.3 KB |
| references/project-docs.md | markdown | 4.5 KB |
| skill.json | config | 1.6 KB |
| templates/project/ADR-000.tmpl | other | 1.1 KB |
| templates/project/ARCHITECTURE.tmpl | other | 1.8 KB |
| templates/project/BACKLOG.tmpl | other | 1.2 KB |
| templates/project/DEV_GUIDE.tmpl | other | 1.9 KB |
| templates/project/ENTRY.tmpl | other | 3.4 KB |
| templates/project/IMPROVEMENTS.tmpl | other | 1.8 KB |
| templates/project/README.tmpl | other | 1.9 KB |
| templates/project/REFERENCE.tmpl | other | 4.4 KB |
| templates/project/REVIEW.tmpl | other | 1.7 KB |
| templates/project/SAGA.tmpl | other | 1.6 KB |
| templates/project/STATUS.tmpl | other | 886 B |
| templates/project/TEST_CASES.tmpl | other | 2.0 KB |
| templates/project/TROUBLESHOOTING.tmpl | other | 2.5 KB |
templates/project/REFERENCE.tmpl
View on GitHub# REFERENCE — the documentation map
> **Purpose: THE MAP.** The permanent map of the whole documentation repository:
> the structure of every doc, key facts, conventions, and the links between them. An
> agent or dev **consults this first** for any doc work — it saves context and keeps
> facts from leaking. **Written LAST** (Phase 10), then maintained on every doc change.
>
> **Rule:** before reading/editing any `.md` — check its card in §3. Before creating a
> new doc — check it isn't already covered (§3), then add a card for it here.
## 1. Repository map
> The tree of the repo from docs' point-of-view, with one-line purpose per entry.
> (Point to the real layout — do NOT drift from actual folders.)
```
<repo>/
├── README.md # EN-overview, structure, status
├── ENTRY.md # entry point: topics → files (start here)
├── AGENT.md # runbook (agent phases, rules, DoD) (L2+)
├── DELIVERY.md # what ships, how to verify, what's NOT in (L2+)
├── docs/
│ ├── REFERENCE.md # ★ THIS FILE — map
│ ├── ARCHITECTURE.md # components, communication, data flow
│ ├── FEATURES.md # module/feature catalog + ✅/📋
│ ├── SAGA.md # cross-module scenarios (L3·microservices)
│ ├── TEST_CASES.md # Gherkin cases + coverage matrix
│ ├── DEV_GUIDE.md # local run/env/debug/add-module
│ ├── IMPROVEMENTS.md # known issues + fix plans
│ ├── TROUBLESHOOTING.md # error diagnostics E1…En + checklist
│ ├── BACKLOG.md # ideas/deferred/priorities
│ ├── REVIEW.md # doc audit + per-module status matrix
│ └── ADR/ADR-00N.md # ADR records (ADR-007 = canonical convention L2+)
├── contracts/ # machine truth — openapi/, asyncapi/ (L3)
└── services/ # implementation
```
## 2. Hierarchy of truth (canon)
> On any conflict the top wins. 🔻 rank 1 = highest authority.
1. **Canon ADR** (e.g. `docs/ADR/ADR-007.md`) — consolidated conventions.
2. **`AGENT.md` / `DELIVERY.md`** — operational rules, gate.
3. **`contracts/`** (openapi + asyncapi) — exact API/event truth.
4. **Narrative docs** (ARCHITECTURE, DEV_GUIDE, FEATURES, SAGA, TEST_CASES).
5. **Shared code types** (`@<scope>/shared`) — the code fact.
> A drift (README vs reality) is recorded in §5 + `docs/IMPROVEMENTS.md`, not silently.
## 3. Per-file documentation cards
> Format: **purpose → structure → key facts → links**. One short card per doc.
### 3.x `<doc>`
- **Purpose:** …
- **Structure:** …
- **Key facts:** … (numbers that must stay true — tests, counts)
- **Links:** points to …, is pointed by …
_(Add a card for each document you create — README/ENTRY/ARCHITECTURE/FEATURES/SAGA/
REVIEW/TEST_CASES/DEV_GUIDE/IMPROVEMENTS/TROUBLESHOOTING/BACKLOG + each ADR.)_
### 3.x ADR
| ADR | Topic | Status |
|-----|-------|--------|
| ADR-001 | … | active |
| ADR-007 | **canon** — supersedes 002…006 | **canon** |
## 4. Known drifts (doc-vs-fact) — control list
| # | Where | The drift | Who's right (source) |
|---|-------|-----------|----------------------|
| 4.x | e.g. README counts | deviates from actual grep | `docs/FEATURES.md` fact |
> Each drift has a fix plan in `docs/IMPROVEMENTS.md`; keep this table in sync.
## 5. Commands (reference; verify in DEV_GUIDE)
```bash
pnpm test # unit (no storage)
pnpm test:contract # conformance
docker compose --profile core up -d # infra
```
## 6. Routing table "where to look"
| Question | First place |
|----------|-------------|
| What is this project | `ENTRY.md` → `README.md` |
| Architecture/sagas | `ARCHITECTURE.md` → `SAGA.md` (see ADR-00N) |
| Conventions/canon | `ADR-00N` (canon) |
| API of module X | `contracts/openapi/<x>.yaml` |
| Events | `contracts/asyncapi/events.yaml` + `SAGA.md` |
| Feature status | `FEATURES.md` |
| How to run | `DEV_GUIDE.md` |
| Known problems / plan | `IMPROVEMENTS.md` |
| Error when running | `TROUBLESHOOTING.md` |
| Backlog | `BACKLOG.md` |
| Doc audit / per-module | `REVIEW.md` |
## 7. How to maintain this file
- Change any doc → update its card in §3.
- New drift → add a row in §4 + plan in IMPROVEMENTS.
- New ADR → add to §3.x table; new module → §4/(FEATURES) + §3 card
> Keep cards as echoes — the **compressed** structure/facts/links, not copies.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 |