agent-skills
Health Warn
- License — License: Apache-2.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 5 GitHub stars
Code Fail
- rm -rf — Recursive force deletion command in .github/actions/post-release-subjects/action.yml
- rm -rf — Recursive force deletion command in .github/workflows/post-release-evidence.yml
Permissions Pass
- Permissions — No dangerous permissions requested
No AI report is available for this listing yet.
Public Agent Skills for Codex operations, Cursor operations, Claude operations, repo maintenance, skill maintenance, productivity, and engineering workflows.
Agent Skills
Reviewed workflows for Codex, Cursor, Claude Code, and portable engineering tasks.
Browse the catalog
·
Open the ChatGPT plugin
·
Explore public skills
·
Contribute
Public skills are reviewed before promotion. Draft and experimental workflows stay in the incubator until they have enough evaluation proof and a clear maintenance path.
Quick start
List the public catalog without installing anything:
npx skills@latest add stark-ai-de/agent-skills --list
Install one skill into the agent detected for the current project:
npx skills@latest add stark-ai-de/agent-skills --skill architecture-compass
Update installed skills:
npx skills@latest update
Install the Codex bundle
npx skills@latest add stark-ai-de/agent-skills --skill codex-memory-curator codex-spec-interviewer animated-readme-logo architecture-compass codegraph-ast-grep drawio-diagrams -g -a codex -y
Install the Cursor bundle
npx skills@latest add stark-ai-de/agent-skills --skill cursor-memory-curator cursor-spec-interviewer animated-readme-logo architecture-compass codegraph-ast-grep drawio-diagrams -g -a cursor -y
Install the Claude Code bundle
npx skills@latest add stark-ai-de/agent-skills --skill claude-memory-curator claude-spec-interviewer animated-readme-logo architecture-compass codegraph-ast-grep drawio-diagrams -g -a claude-code -y
Bundles use explicit, version-controlled manifests. The Codex bundle is the ordered six-skill allowlist in plugins/stark-ai-developer.source.json, and its install command below is checked against that manifest. The bundles install globally; remove -g for a project-local install. Avoid --skill '*' when targeting one runtime because it also selects skills built specifically for other runtimes.
The -a option selects the host where a skill is installed; it does not change that skill's target contract. An intentionally cross-host install preserves target-specific evidence and output while adapting collaboration controls to the selected host.
stark AI Developer plugin distributions
The repository's six-skill stark AI Developer bundle is explicit and
generated from plugins/stark-ai-developer.source.json:
plugins/stark-ai-developer/is the portable
Agent Plugins projection for compatible clients and direct local testing.dist/openai/*.zipis the OpenAI-native harness-first submission archive,
generated from ephemeral adapter staging at package time.dist/skills/*.zipcontains optional one-skill standalone archives.
Listing copy lives in docs/listing/openai/ and is not bundle
membership or part of the adapter archive tree.
First-publication portal observations live indocs/listing/openai/stark-ai-developer-first-publication.md.
plugins/stark-ai-developer.source.json
holds membership and plugin identity. Catalog version stays in package.json.
The repository marketplace and any personal or workspace marketplace are local
testing/distribution catalogs. They do not, by themselves, prove submission,
approval, or public-directory publication. The public ChatGPT plugin page is
the shared ChatGPT/Codex catalog card. The package has no backend, MCP server,
connectors, authentication, telemetry, analytics, hidden network calls, or
runtime downloads.
These are separate installation routes:
- ChatGPT plugin: chatgpt.com/plugins/plugins_6a85d98a7bc48191879aedd91610271e. Account, workspace, and plan eligibility still apply.
- Repository/local plugin: the portable projection through a compatible
local or repository marketplace. - Standalone ChatGPT skill: upload, share, or workspace-install an
individual skill where the account and client support that route. - Standalone Codex or IDE skill: install an individual skill through the
supported Codex/IDE skill path or the standalone archive. npx skills: the existing canonical repository catalog and CLI
installation path.
Choose a skill
| When you need to… | Use | Scope |
|---|---|---|
| Turn a fuzzy coding request into an implementation-ready spec | codex-spec-interviewer, cursor-spec-interviewer, or claude-spec-interviewer |
Runtime-specific |
| Review, plan, or clean persistent agent context | codex-memory-curator, cursor-memory-curator, or claude-memory-curator |
Runtime-specific |
| Set up or audit ADR governance and plan or run governed refactors | architecture-compass |
Cross-runtime |
| Set up, update, or diagnose CodeGraph and ast-grep for coding agents | codegraph-ast-grep |
Cross-runtime |
| Create, edit, validate, or export an editable diagram | drawio-diagrams |
Engineering workflow |
| Audit, create, transform, or animate a verified README logo pipeline | animated-readme-logo |
Engineering workflow |
See the complete public catalog for exact trigger descriptions and skill-evals/ for maintainer proof.
How the catalog works
| Path | Purpose | Published? |
|---|---|---|
skills/ |
Reviewed skills discoverable through npx skills |
Yes |
incubator/skills/ |
Candidate, experimental, or not-yet-public skills | No |
skill-evals/ |
Activation cases, comparisons, and promotion evidence | Maintainer proof only |
site/ |
Astro source for the generated catalog | GitHub Pages |
Promotion is a folder move from incubator/skills/<category>/<skill>/ to skills/<category>/<skill>/, backed by demonstrated value, activation tests, a reusable use case, manageable maintenance, and reviewable evaluation proof. See the spec policy for public-contract updates.
Development
pnpm install
Select checks from changed contracts and owning boundaries under ADR-0041 (Long, canonical · Guide). Run the local npm run validate aggregate for release intent or another mandatory gate; hosted Validate remains required for every pull request. OpenAI-native adapter packaging is proven with npm run validate:openai-plugin or hosted validate:release-proof, not by writing adapters/.
| Command | Purpose |
|---|---|
npm run list |
List promoted public skills |
npm run list:incubator |
List incubator skills |
npm run validate |
Validate skills, ADRs, scripts, and repository contracts |
npm run sync:agent-plugin |
Regenerate plugins/stark-ai-developer/ from canonical skills |
npm run validate:projections |
Check the committed portable Agent Plugin projection |
npm run validate:openai-plugin |
Stage, validate, and discard the OpenAI-native adapter |
npm run package:openai-plugin |
Write dist/openai/*.zip from ephemeral adapter staging |
npm run validate:archives |
Build and inspect release archives |
npm run verify:release-reproducibility |
Compare two isolated deterministic builds |
npm run build:release-subjects |
Local fallback for the hosted final release subject artifact |
npm run validate:release-proof |
Archive, reproducibility, and endpoint release proof |
npm run smoke:fingerprint |
Fingerprint the exact clean-copy candidate set read-only |
npm run smoke:install |
Test clean-copy discovery and exact host destinations |
npx skills@latest add ./skills --list |
Check local public skill discovery |
pnpm --filter ./site build |
Build the generated catalog |
pnpm format:check |
Check formatting |
pnpm lint |
Lint repository scripts |
npm run release:validate |
Validate release readiness |
Scaffold a skill only when its destination is clear:
npm run scaffold repo-maintenance/my-new-skill
npm run scaffold:incubator engineering-workflows/my-candidate-skill
Documentation
| Topic | Reference |
|---|---|
| Naming, safety, and review rules | Contributing |
| Validation and CI | Validation |
| Publishing and release flow | Publishing |
| Specs and durable decisions | Spec policy · ADR index |
| Domain language and boundaries | Glossary · Out of scope |
| Logo animation and fallback behavior | Motion specification |
- Agent Skills specification
- Agent Skills evaluation guide
- Agent Skills description optimization
- Vercel skills CLI
Compatibility and safety
This repository follows the open Agent Skills specification. Individual compatibility varies by skill and host; read a skill's SKILL.md before installing it. Runtime-specific skills stay in their runtime category, while reusable workflows live under engineering-workflows.
Skills are executable context. Helper scripts are read-only unless their documentation explicitly says otherwise. Never add secrets, tokens, customer data, private repository paths, or internal hostnames to public skills, references, assets, tests, or examples.
License
Apache-2.0 for the skills and repository material published here.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found