Skip to content

stark-ai-de/agent-skills / incubator/skills/skill-maintenance/skill-repo-curator

skill-repo-curator

Verified

Maintain a public Agent Skills repository. Use when updating skill catalogs, validating SKILL.md files, preparing a release, deprecating skills, reviewing install commands, checking README consistency, or keeping a skills repo ready for npx skills installation.

references/agent-skills-release.md

View on GitHub
# Agent Skills Repository Release

Use this reference when preparing a release in `stark-ai-de/agent-skills`. For
other repositories, prefer their local publishing contract.

## Scope and authority

This repository records feature impact in ordinary pull requests, lets Release
Please generate the root version pull request, and publishes through a protected
GitHub environment. Do not push, dispatch a mutating workflow, approve an
environment, create a tag or release, or update OpenAI without explicit
maintainer approval.

Use `docs/publishing.md` and `docs/validation.md` as the source of truth. This
file is the skill-facing route through that finite workflow.

## Feature pull request

- Increase every materially changed skill's `metadata.version`.
- Increase `plugins/stark-ai-developer.source.json#version` when a bundled skill
  changes, then run `npm run sync:agent-plugin`.
- Do not change the root package version, `.release-please-manifest.json`, or
  root `CHANGELOG.md`.
- Record the intended impact without writing release files:

```bash
npm run release:manage -- impact --kind patch --skill SKILL_NAME
npm run release:intent -- --base-ref origin/main
npm run release:validate -- --base-ref origin/main
```

`npm run release:prepare` is a refuse-redirect. Release Please is the sole
writer of root release metadata.

## Generated release pull request

After feature work merges, start or inspect the App-owned draft through
`npm run release:manage -- release-pr --confirm` or the `Release Please`
workflow in GitHub Actions. The generated PR may change only:

- `.release-please-manifest.json`;
- `package.json` version;
- one newest `CHANGELOG.md` release section.

Merge it only after hosted Validate proves its exact content and App ownership.

## Protected publication

Use the read-only dry run before publication:

```bash
npm run release:manage -- publish-plan --confirm
```

For a real publication, dispatch `publish --confirm` or use the GitHub
`Publish Release` workflow with `dry_run: false`, then approve the waiting
`release` deployment by exact run ID:

```bash
npm run release:manage -- publish --confirm
npm run release:manage -- approve --run-id RUN_ID --confirm
```

The hosted workflow owns the annotated tag, three direct assets, ZIP
attestations, Latest state, and explicit post-release evidence dispatch. Local
commands never create tags or releases.

## Evidence and OpenAI handoff

If evidence needs an explicit retry, dispatch only the exact tag:

```bash
npm run release:manage -- post-release --tag vX.Y.Z --confirm
```

After the exact-tag Evidence run succeeds, use the read-only handoff check:

```bash
npm run release:manage -- openai-handoff --tag vX.Y.Z
```

Download the direct GitHub Release asset `openai.zip`; do not rebuild or repack
it. Follow the portal icon, light/dark logo, composer-icon, propagation, and
directory checks in `docs/publishing.md`.

## Required local proof

Select checks from the changed contracts. A release-intent candidate requires
the focused release gates and one final frozen `npm run validate`, followed by
`pnpm format:check`, `pnpm lint`, and `git diff --check`. Report local, hosted,
publication, post-release, and OpenAI evidence as separate layers.
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: 472kUpdated 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