Skip to content

ShipfoxHQ/shipfox / .agents/skills/readme-writer

readme-writer

Verified

Use this skill to write or revise a README.md for a Shipfox workspace package (libs/*, tools/*). It applies the shared package README standard and repository prose policy. Trigger on write a README, draft README, rewrite README, document this package, or improve the README.

README Writer

Use this workflow to document one package. It does not apply to the repository root README, design documents, or RFCs.

Before drafting a package README, read the package README standard. It owns the required structure, prose style, public-surface rules, development guidance, and license section for human and agent authors.

When deciding whether detail belongs in the package README, read the engineering documentation map. It owns documentation placement and canonical ownership.

Gather the package contract

Read the public package surface in this order:

  1. package.json for its name, exports, binaries, scripts, and dependencies.
  2. The root export entry point for consumer-visible symbols.
  3. Additional source files only as needed to understand those exports.
  4. A sibling *-dto package when it owns public DTO or event names.
  5. drizzle/ or migrations/ when the package owns persistent data.

Do not document symbols that the package does not export or ship.

Workflow

  1. Apply the package README standard, including only the sections that fit the package.
  2. Use the inspected public contract for the package description, setup, and runnable usage example. Link to schemas or configuration sources instead of copying fast-changing values.
  3. Check nearby package READMEs only for local conventions or comparable examples. They do not override the shared standard.
  4. Run mise exec -- turbo verify --filter=@shipfox/prose-policy and review its warnings and suggestions for the README.
  5. Apply the guidance in WRITING.md to improve the result, then reread the README as a package consumer.

Report the public sources inspected, the sections included, and the prose-policy result.

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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexUnverifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall