Make Documentation
Use when writing READMEs, architecture, changelogs, release notes, runbooks, notebook docs, install docs, or security articles; produces docs. Do not trigger for API docs, AGENTS.md, or diagrams.
- Скачивания
- 0
- В избранном
- 0
- Комментарии
- 0
- Просмотры
- 2
Установить скилл
Добавьте инструмент одной командой или скачайте проверенный архив версии.
npx skills add callicrate/skills --skill make-documentation- Версия
- 1.0.0+18c2d2fd52f3
- Автор
- Владимир Ломтев
- Репозиторий
- callicrate/skills
Как установить
- 1Скопируйте команду из блока установки.
- 2Запустите её в терминале из каталога проекта.
Документация
Make Documentation
When to Use
- Writing or updating a README.md, architecture note, changelog, or release notes
- Auditing existing project docs before adding missing documentation
- Drafting customer-facing security guidance or partner-sensitive article prose from source material
- Writing live access, reproduction, lab interface, workstation/server, or operator runbooks
- Documenting notebooks, generated notebooks, or table-producing notebook workflows
- Writing WSL, local, Docker, or environment-specific install docs
- Writing agent operation manuals, role files, peer-status contracts, or AI-readable workflow docs
- Producing diagram documents only when the user explicitly asks or the project already uses them
When NOT to Use
- Writing API reference documentation
- Creating or updating AGENTS.md. Use
agents-md, even when the broader request also includes other docs. - Generating diagram files by default when prose or tables are sufficient
Workflow
- Run scripts/audit_documentation.py for new docs, large rewrites, doc moves, missing-doc investigations, or unclear structure. For tiny explicit edits, inspect the target file and nearby docs directly.
- Choose only the deliverables justified by the user's request and the audit. Do not generate a fixed documentation bundle by default.
- Route by document type: use references/guide-readme.md for
README.md, references/guide-architecture.md fordocs/architecture.mdor the repo's existing equivalent, references/guide-ai-ingestion.md when the user says the document is for agents/AI ingestion, references/guide-agent-ops-docs.md for role/workflow docs consumed by agents, references/guide-access-runbook.md for live access, reproduction, operator, lab interface, or capability ledgers, references/guide-notebook-documentation.md for notebook explanations, references/guide-install-runbook.md for WSL/local/Docker install docs, references/guide-security-article.md for partner-sensitive security articles, and references/guide-changelog.md forCHANGELOG.mdor release notes. If AGENTS.md becomes part of scope, switch that file toagents-mdinstead of expanding this skill. - Use references/guide-diagrams.md only when the user explicitly asks for diagram docs or the project already maintains them.
- For large docs, iterative reports, feature inventories, concept framing, or evidence-audit amendments, load references/source-discovery-and-heading-stability.md before writing.
- For concept or strategy docs, include a visible first usable workflow before architecture depth so the reader can execute a small slice before absorbing the model.
- Keep the output source-backed and terse. Preserve user-provided terminology and avoid generic rewrites that change domain meaning or connotation.
- Preserve earlier requested documentation when later implementation work touches the same notebooks, docs, or folders. Re-open touched docs before finishing if there is a risk an unrelated implementation change removed prior documentation.
- Review the result with references/review-checklist.md before finishing.
Anti-Patterns
- Wrong: summarize a notebook from a generated README, review packet, AI commentary, or stale comments. Correct: trace executable cells, imports, widgets, SQL, configs, and outputs, then write the short explanation.
- Wrong: write folder-contract docs after a move from memory. Correct: audit the tree and update parent and child docs together.
- Wrong: duplicate validators, schemas, CLIs, table lists, or source-of-truth modules while documenting around implementation. Correct: scan for existing source-of-truth assets and link to them.
- Wrong: leave workflow docs tied to VS Code, one editor, or one UI unless the user explicitly requested that. Correct: state editor-independent start state and execution plane.
- Wrong: keep meta labels such as
review packet,AI-generated summary, oranalysis artifactin human-facing docs unless they are required schema fields. Correct: use natural section names that match the audience. - Wrong: label demo-only flags or filters as future product interfaces. Correct: separate test scaffolding from durable user or agent interfaces.
Deterministic Tools
| Tool | Use When | Outcome |
|---|---|---|
| scripts/audit_documentation.py | You need a deterministic inventory before writing docs | Current-state documentation audit |
References
- references/guide-readme.md - README workflow
- references/guide-architecture.md - architecture documentation
- references/guide-ai-ingestion.md - compact machine-ingestion documentation mode
- references/guide-agent-ops-docs.md - role, directive, peer-status, and execution-plane docs for agents
- references/guide-access-runbook.md - live access, reproduction, interface, and capability ledgers
- references/guide-notebook-documentation.md - notebook explanation and runnable-order preservation
- references/guide-install-runbook.md - environment-specific install docs
- references/guide-security-article.md - partner-sensitive security article workflow
- references/guide-changelog.md - changelog and release notes
- references/guide-diagrams.md - opt-in diagram workflow only
- references/review-checklist.md - review pass before finishing
- references/source-discovery-and-heading-stability.md - large-doc source discovery and stable heading checks
- references/ascii-art-standards.md - diagram formatting standards when diagrams are in scope
Требования и возможности
Источник пакета
https://github.com/callicrate/skills/tree/18c2d2fd52f3597f38f93dd18aba15804c2704f9/make-documentation
Файлы версии
| Путь | Размер | SHA256 |
|---|---|---|
| SKILL.md | 6818 | 70822edc9496247a... |
| agents/openai.yaml | 335 | 18820c64dc40e426... |
| references/ascii-art-standards.md | 1591 | 22676da5038c5795... |
| references/guide-access-runbook.md | 1926 | 39243db17512cb42... |
| references/guide-agent-ops-docs.md | 1732 | 3e763e22983ac6ff... |
Частые вопросы
- Как установить Make Documentation?
- Используйте команду
npx skills add callicrate/skills --skill make-documentationили скачайте ZIP-архив. - Можно ли скачать Make Documentation бесплатно?
- Да, опубликованную версию можно скачать из маркетплейса бесплатно.
Похожие инструменты
Смотреть всеReact DoctorUse when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.Argent Android Emulator SetupSet up and connect to an Android emulator using argent MCP tools. Use when starting a new session on Android, booting an emulator, getting a device serial, or before any UI interaction task.Fireworks Tech GraphCreate technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF motion, or offline interactive HTML. Treat direct requests such as "Generate a GIF", "生成 GIF", or "制作 GIF" as motion requests, and use this skill when the user asks to visualize a system or engineering concept. Do not use for photos, raster artwork, or quantitative data charts.
Комментарии
Войдите, чтобы оставить комментарий.
Комментариев пока нет.