Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
OpenAISkillopenai/openai-guardrails-python/.agents/skills/pr-draft-summary/SKILL.md
Create the required PR-ready summary block, branch suggestion, title, and draft description for openai-guardrails-python after runtime, tests, examples, build/test configuration, or behavior-impacting docs change.
OpenAISkillopenai/snap-o/skills/snap-o-network-inspector/SKILL.md
Inspect Android network captures and intercept HTTP calls with the Snap-O CLI for a selected device/socket. Use for request/response details, websocket events, API response overrides, mock responses, or delays with Python route handlers.
OpenAISkillopenai/snap-o/skills/snap-o-tweaks/SKILL.md
Inspect, stream, and explicitly adjust live Android UI tweak values or invoke app-owned actions through Snap-O. Use when a request mentions Snap-O Tweaks, tweak-enabled Android apps, runtime UI parameters, Compose tweak or action controls, tweak discovery, previously adjusted or currently inactive tweaks, applying all user-made tweak changes, typed values, defaults or resets, tweak batches, explicitly registered actions, the Tweaks REST/SSE API, or selecting between CLI, macOS tool, in-app overlay, and custom tweak interfaces.
OpenAISkillopenai/openai-guardrails-js/.agents/skills/code-change-verification/SKILL.md
Select and run Guardrails verification for code, dependency, test, tooling, documentation, or repository-workflow changes.
OpenAISkillopenai/openai-guardrails-js/.agents/skills/implementation-final-review/SKILL.md
Prepare independent review of a complete Guardrails change before pushing or updating a PR, using the repository adversarial-review procedure.
OpenAISkillopenai/openai-guardrails-js/.agents/skills/implementation-kickoff/SKILL.md
Start or resume a requested Guardrails implementation or PR takeover in the selected linked worktree with bounded scope and verification.
OpenAISkillopenai/openai-guardrails-js/.agents/skills/implementation-strategy/SKILL.md
Choose bounded implementation scope and existing owning modules before Guardrails runtime, configuration, client, resource, streaming, Agents, or SDK compatibility changes and feedback fixes.
OpenAISkillopenai/openai-guardrails-js/.agents/skills/pr-draft-summary/SKILL.md
Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.
OpenAISkillopenai/redcard/codex-skill/redcard/SKILL.md
Install, diagnose, and run the self-contained Red Card runtime through Codex in the ChatGPT macOS app from any task or project. Use when the user invokes $redcard or asks Codex to install, configure, troubleshoot, or run Red Card. Codex owns every shell command and requests scoped outside-sandbox execution for installation, dependency downloads, and real runs that need macOS hardware or app access; the user only handles required approval, macOS, Chrome, and Google-account UI actions.
OpenAISkillopenai/openai-developers-for-claude/plugins/openai-developers/skills/agents-sdk/SKILL.md
Use when the user wants to build, adapt, run, or evaluate an OpenAI Agents SDK app from Claude Code. Prefer a docs-first workflow and route API credential decisions through openai-platform-api-key before API-backed work.
OpenAISkillopenai/openai-developers-for-claude/plugins/openai-developers/skills/build-chatgpt-app/SKILL.md
Use when the user explicitly wants a ChatGPT App, Apps SDK project, MCP server plus widget UI, ChatGPT-compatible tool UI, or submission/deployment work for that surface. Build, scaffold, refactor, or troubleshoot those projects from Claude Code, consult openai-docs before generating code, and use openai-platform-api-key before any app path that requires live OpenAI API credentials.
OpenAISkillopenai/openai-developers-for-claude/plugins/openai-developers/skills/chatgpt-app-submission/SKILL.md
Use when a developer needs a ChatGPT Apps submission import file from an MCP server. Inspect the implementation, generate chatgpt-app-submission.json with app info, tool-hint justifications, positive and negative test cases, then report review findings and outputSchema warnings.
OpenAISkillopenai/openai-developers-for-claude/plugins/openai-developers/skills/openai-docs/SKILL.md
Use whenever the user asks anything about OpenAI products, APIs, models, or SDKs — including factual lookups, coding requests, latest/current/default model selection, prompting guidance, model upgrades, and citation requests. Invoke before calling any openaiDeveloperDocs MCP tool.
OpenAISkillopenai/openai-developers-for-cursor/skills/agents-sdk/SKILL.md
Use when the user wants to build, adapt, run, or evaluate an OpenAI Agents SDK app from Cursor. Prefer a docs-first workflow and route API credential decisions through openai-platform-api-key before API-backed work.
OpenAISkillopenai/openai-developers-for-cursor/skills/build-chatgpt-app/SKILL.md
Use when the user explicitly wants a ChatGPT App, Apps SDK project, MCP server plus widget UI, ChatGPT-compatible tool UI, or submission/deployment work for that surface. Build, scaffold, refactor, or troubleshoot those projects from Cursor, consult openai-docs before generating code, and use openai-platform-api-key before any app path that requires live OpenAI API credentials.
OpenAISkillopenai/openai-developers-for-cursor/skills/chatgpt-app-submission/SKILL.md
Use when a developer needs a ChatGPT Apps submission import file from an MCP server. Inspect the implementation, generate chatgpt-app-submission.json with app info, tool-hint justifications, positive and negative test cases, then report review findings and outputSchema warnings.
OpenAISkillopenai/openai-developers-for-cursor/skills/openai-docs/SKILL.md
Use whenever the user asks anything about OpenAI products, APIs, models, or SDKs — including factual lookups ("what is the newest model", "does X support Y"), build/coding requests ("write a script using the Responses API"), latest/current/default-model prompting guidance, model migrations, and citation requests. Invoke before calling any openaiDeveloperDocs MCP tool.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
