skills
github.com/openai/skills
Skill | Added | Review |
|---|---|---|
yeet Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`). | 72 1.22x Agent success vs baseline Impact 75% 1.22xAverage score across 3 eval scenarios Securityby  Passed No known issues Reviewed: Version: e6afb0d | |
spreadsheet Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) with formula-aware workflows, cached recalculation, and visual review. | 80 1.73x Agent success vs baseline Impact 80% 1.73xAverage score across 15 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
speech Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope. | 100 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: e6afb0d | |
sora Use when the user asks to generate, edit, extend, poll, list, download, or delete Sora videos, create reusable non-human Sora character references, or run local multi-video queues via the bundled CLI (`scripts/sora.py`); includes requests like: (i) generate AI video, (ii) edit this Sora clip, (iii) extend this video, (iv) create a character reference, (v) download video/thumbnail/spritesheet, and (vi) Sora batch planning; requires `OPENAI_API_KEY` and Sora API access. | 88 Impact Pending No eval scenarios have been run Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction. | 70 1.03x Agent success vs baseline Impact 55% 1.03xAverage score across 6 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
screenshot Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed. | 72 3.63x Agent success vs baseline Impact 69% 3.63xAverage score across 5 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
notion-spec-to-implementation Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them. | 95 1.49x Agent success vs baseline Impact 97% 1.49xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
notion-research-documentation Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations. | 88 1.45x Agent success vs baseline Impact 89% 1.45xAverage score across 7 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
notion-meeting-intelligence Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees. | 91 1.31x Agent success vs baseline Impact 97% 1.31xAverage score across 7 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
notion-knowledge-capture Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking. | 95 1.43x Agent success vs baseline Impact 95% 1.43xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
gh-fix-ci Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL. | 78 1.00x No change in agent success vs baseline Impact 33% 1.00xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
gh-address-comments Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in. | 71 Impact Pending No eval scenarios have been run Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
doc Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks. | 75 1.43x Agent success vs baseline Impact 66% 1.43xAverage score across 5 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
transcribe Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings. | 93 4.42x Agent success vs baseline Impact 93% 4.42xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
sentry Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command. | 83 2.93x Agent success vs baseline Impact 91% 2.93xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
figma Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting. | 90 2.12x Agent success vs baseline Impact 100% 2.12xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
netlify-deploy Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys. | 87 1.36x Agent success vs baseline Impact 90% 1.36xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
security-best-practices Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks. | 86 1.18x Agent success vs baseline Impact 97% 1.18xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
figma-implement-design Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`. | 81 1.00x No change in agent success vs baseline Impact 92% 1.00xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
linear Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear. | 78 1.50x Agent success vs baseline Impact 92% 1.50xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
vercel-deploy Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". | 96 2.23x Agent success vs baseline Impact 96% 2.23xAverage score across 3 eval scenarios Securityby Critical Do not install without reviewing Reviewed: Version: e6afb0d | |
security-threat-model Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work. | 89 2.54x Agent success vs baseline Impact 94% 2.54xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
playwright Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script. | 92 4.09x Agent success vs baseline Impact 86% 4.09xAverage score across 3 eval scenarios Securityby Risky Do not use without reviewing Reviewed: Version: e6afb0d | |
render-deploy Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform. | 90 1.09x Agent success vs baseline Impact 100% 1.09xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: e6afb0d | |
openai-docs Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains. | 94 1.84x Agent success vs baseline Impact 94% 1.84xAverage score across 3 eval scenarios Securityby Critical Do not install without reviewing Reviewed: Version: e6afb0d | |
jupyter-notebook Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook. | 89 1.49x Agent success vs baseline Impact 88% 1.49xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
security-ownership-map Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions. | 90 4.57x Agent success vs baseline Impact 96% 4.57xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
cloudflare-deploy Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare. | 85 1.34x Agent success vs baseline Impact 89% 1.34xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
develop-web-game Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text. | 86 2.65x Agent success vs baseline Impact 93% 2.65xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e6afb0d | |
imagegen Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas. | 94 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 0ed2046 | |
linear Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear. | 80 1.50x Agent success vs baseline Impact 92% 1.50xAverage score across 5 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: aac2078 | |
create-plan Create a concise plan. Use when a user explicitly asks for a plan related to a coding task. | 85 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: aac2078 | |
codex-readiness-unit-test Run the Codex Readiness unit test report. Use when you need deterministic checks plus in-session LLM evals for AGENTS.md/PLANS.md. | 79 Impact Pending No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: aac2078 | |
codex-readiness-integration-test Run the Codex Readiness integration test. Use when you need an end-to-end agentic loop with build/test scoring. | 75 Impact Pending No eval scenarios have been run Securityby Advisory Suggest reviewing before use Reviewed: Version: aac2078 |