openai/skills▌

Create, repair, validate, preview, and package Codex-compatible animated pets and pet spritesheets from character art.

Install Codex skills from curated lists or custom GitHub repositories into your local skills directory. \n \n List available skills from the default curated collection or experimental/custom paths; installed skills are annotated in the output \n Install individual skills by name from the curated list, or install multiple skills from any GitHub repo (public or private) using repo paths or URLs \n Supports git sparse checkout as a fallback for authentication-protected repos; uses existing git cred

Create and scaffold Jupyter notebooks for experiments and tutorials with bundled templates. \n \n Two notebook kinds: experiment for exploratory analysis and hypothesis-driven work, tutorial for instructional step-by-step content \n Helper script new_notebook.py generates clean notebooks from templates, avoiding manual JSON authoring \n Workflow emphasizes small, focused code cells paired with markdown explanations, with reference guides for experiment patterns, tutorial structure, and safe edit

Use PptxGenJS for slide authoring. Do not use python-pptx for deck generation unless the task is inspection-only; keep editable output in JavaScript and deliver both the .pptx and the source .js.

Access current OpenAI developer documentation with MCP tools and model-selection guidance. \n \n Prioritizes the OpenAI Developer Docs MCP server for all queries; falls back to web search only on official OpenAI domains if MCP returns no results \n Includes reference files for model selection, GPT-5.4 upgrade planning, and prompting guidance; always verifies recommendations against live docs before answering \n Covers seven core OpenAI products: Apps SDK, Responses API, Chat Completions, Codex,

Iterative web game development with Playwright-based testing, screenshot validation, and deterministic time-stepping. \n \n Provides a structured workflow: implement small changes, run automated Playwright tests with controlled input bursts and frame pauses, capture screenshots and text state, then inspect and adjust \n Requires window.render_game_to_text() to expose game state as JSON and window.advanceTime(ms) for deterministic frame stepping during automated tests \n Includes a Playwright cli

Use this skill when the quality of the work depends on art direction, hierarchy, restraint, imagery, and motion rather than component count.

Locate and address review comments on GitHub PRs using gh CLI with user-guided workflows. \n \n Fetches all comments and review threads from the open PR for the current branch, displaying them with summaries of required fixes \n Requires gh CLI authentication with elevated permissions (workflow/repo scopes); prompts re-authentication if rate limits or auth errors occur mid-run \n Presents numbered comment list to user for selection, then applies fixes to chosen comments \n Handles sandboxing con

yeet

Choose the right ASP.NET Core application model, compose the host and request pipeline correctly, and implement features in the framework style Microsoft documents today.

Use this skill for WinUI 3 and Windows App SDK work that needs grounded setup guidance, app bootstrap, modern Windows UX decisions, or concrete implementation patterns.

Manage Linear issues, projects, and team workflows with structured MCP integration. \n \n Provides 20+ tools across issue management, project planning, documentation search, and team collaboration \n Supports eight practical workflows including sprint planning, bug triage, workload balancing, release planning, and retrospectives \n Requires Linear MCP server setup with OAuth authentication; includes Windows/WSL configuration guidance \n Executes operations in logical batches: read first for cont

Read, create, and edit DOCX files with visual layout validation and professional formatting. \n \n Use python-docx for structured document creation and editing (headings, styles, tables, lists). \n Convert DOCX to PDF to PNG for visual inspection of layout, tables, diagrams, and pagination fidelity before delivery. \n Includes bundled scripts/render_docx.py helper for rendering; falls back to text extraction if visual tools are unavailable. \n Requires python-docx , pdf2image , and system tools

Generate or edit images via OpenAI's API with a bundled CLI for deterministic, reproducible runs. \n \n Supports three workflows: generate new images, edit existing images (inpainting, masking, background replacement, object removal), and batch runs across multiple prompts or variants \n Defaults to gpt-image-1.5 and requires OPENAI_API_KEY for live API calls; uses the bundled scripts/image_gen.py CLI for all operations \n Includes a structured decision tree and prompt augmentation template to c

Capture conversations and decisions into structured, linkable Notion pages for wikis, how-tos, FAQs, and decision logs. \n \n Supports six content types: decisions, how-to guides, FAQs, wiki entries, learning notes, and documentation pages, each with dedicated database templates and schemas. \n Includes a five-step workflow: define capture purpose, locate the target database, extract and structure content, create or update the Notion page, and link from related hub pages. \n Provides reference g

Scaffold ChatGPT Apps SDK implementations with a docs-first, example-first workflow, then generate code that follows current Apps SDK and MCP Apps bridge patterns.

Deploy applications to Render with Git-backed services or prebuilt Docker images via Blueprint or direct creation. \n \n Supports two deployment methods: Blueprint (Infrastructure-as-Code via render.yaml) for multi-service apps, and Direct Creation (MCP tools) for single services \n Analyzes codebases to determine runtime, build/start commands, environment variables, and required datastores (databases, Redis, cron jobs) \n Generates render.yaml configurations with automatic service type selectio

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and platform services. \n \n Covers 40+ Cloudflare products organized by use case: compute (Workers, Pages, Durable Objects, Workflows), storage (KV, D1, R2, Queues), AI/ML (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), and security (WAF, Bot Management, Turnstile) \n Includes decision trees to route users to the right product based on their need (run code, store data, add AI, networking, security, or

Deploy applications to Vercel as preview or production environments. \n \n Supports both Vercel CLI and fallback script-based deployment methods, with automatic framework detection and packaging \n Always deploys as preview by default unless user explicitly requests production deployment \n Returns preview URL immediately and claim URL for fallback deployments to manage the deployment \n Requires 10-minute timeout for build completion; escalates network permissions only if sandbox blocks outboun

Map git repository ownership to people and files, compute bus factor for sensitive code, and export graph artifacts for visualization. \n \n Builds a bipartite people-to-file ownership graph from git history with optional co-change clustering (Jaccard similarity) to identify files that move together \n Flags sensitive code paths (auth, crypto, secrets) by default; customize with a CSV config and query by tag, bus factor, or staleness \n Outputs CSV nodes/edges, JSON summaries (orphaned sensitive

Read-only Sentry API queries for production error inspection and health summaries. \n \n Requires SENTRY_AUTH_TOKEN with read-only scopes ( project:read , event:read , org:read ); supports optional org, project, and base URL environment variables \n Core commands: list unresolved issues, fetch issue details, retrieve events for an issue, and inspect individual event data with automatic PII redaction \n Defaults to 24-hour time range, production environment, and 20-result limit (max 50); supports

Convert Notion specs into linked implementation plans, tasks, and progress tracking. \n \n Automates the workflow from spec discovery through task creation: search and fetch specs, parse requirements, generate implementation plans, and create tracked tasks in Notion. \n Includes templates for quick vs. full implementation plans, task creation patterns, and progress update cadences to match project scope. \n Provides reference guides for requirement extraction, task sizing (1–2 day chunks), depen

Deploy web projects to Netlify with automatic authentication, site linking, and framework detection. \n \n Handles full deployment workflow: authentication verification, site linking or creation, dependency installation, and preview or production deploys \n Supports both browser-based OAuth and API token authentication; guides users through login if needed \n Automatically detects project configuration from netlify.toml or prompts for build command and publish directory based on framework \n Inc

Text-to-speech generation for narration, voiceovers, IVR prompts, and accessibility reads via OpenAI Audio API. \n \n Supports single clips and batch processing; defaults to gpt-4o-mini-tts-2025-12-15 with built-in voices (cedar, marin, and others) \n Includes instruction augmentation for voice affect, tone, pacing, emotion, and emphasis; instructions supported only on GPT-4o mini TTS models \n Enforces 4096-character input limit per request and 50 requests/minute rate cap; splits longer text in

AI video generation and management for Sora models with character references, editing, and batch workflows. \n \n Supports video creation, editing, extension, character reference uploads, and asset downloads (video/thumbnail/spritesheet) via bundled CLI with structured prompt augmentation \n Defaults to sora-2 model; supports sora-2-pro for higher fidelity and larger resolutions up to 1920x1080 \n Handles async job polling, local multi-job queues, and official Batch API planning for offline rend

Transcribe audio files to text with optional speaker diarization and known-speaker hints. \n \n Supports fast text transcription via gpt-4o-mini-transcribe and speaker-labeled diarization via gpt-4o-transcribe-diarize \n Accepts multiple audio formats and optional known-speaker references (up to 4 speakers) to improve diarization accuracy \n Outputs as plain text, JSON, or diarized JSON with configurable output directories to prevent overwrites \n Requires OPENAI_API_KEY environment variable; us

Research Notion content and synthesize into structured briefs, reports, or comparisons with citations. \n \n Search and fetch Notion pages using targeted queries, then organize findings by theme with inline source citations and a references section \n Choose from four output formats (quick brief, research summary, comparison, comprehensive report) based on scope and user goal \n Create and update Notion pages using built-in templates; link sources directly and track changes as new information ar

Repository-grounded threat modeling that maps trust boundaries, assets, and abuse paths to concrete code evidence. \n \n Enumerates entry points, data flows, and trust boundaries anchored to actual repository structure and configuration \n Derives realistic attacker goals tied to specific assets (credentials, PII, integrity-critical state, compute resources) rather than generic checklists \n Prioritizes threats using likelihood and impact reasoning, with explicit assumptions about deployment, au

Debug and fix failing GitHub Actions checks in pull requests using gh CLI inspection and log analysis. \n \n Inspects PR checks via GitHub CLI, fetches GitHub Actions logs, and summarizes failure context with actionable log snippets \n Requires prior gh authentication with repo and workflow scopes; verifies status before proceeding \n Drafts a fix plan (using create-plan skill if available, otherwise inline) and implements only after explicit user approval \n Treats external CI providers (Buildk

PDF reading, creation, and validation with visual rendering and programmatic generation. \n \n Render PDF pages to PNG for visual inspection of layout, spacing, and typography before delivery using Poppler ( pdftoppm ) \n Generate PDFs programmatically with reportlab for reliable formatting; extract text and metadata with pdfplumber or pypdf \n Enforce quality standards: no clipped text, overlapping elements, broken tables, or rendering artifacts; ASCII hyphens only, human-readable citations \n

Language and framework-specific security reviews with actionable vulnerability detection and fix guidance. \n \n Supports Python, JavaScript/TypeScript, and Go with framework-specific best practices loaded from a references directory \n Operates in three modes: secure-by-default code generation, passive vulnerability detection during development, and full security audit reports with severity prioritization \n Generates detailed markdown reports with line-number references, impact statements, and

$23

Terminal-driven browser automation with element snapshots and interactive UI workflows. \n \n Operates via playwright-cli wrapper script (requires npx ); supports headless and headed modes for visual debugging \n Core workflow: open page, snapshot for stable element references, interact using refs, re-snapshot after navigation or DOM changes \n Includes form filling, clicking, typing, multi-tab management, screenshot/PDF capture, and trace recording for flow debugging \n Element refs (e.g., e3 ,

Translate Figma designs into production-ready code with pixel-perfect visual fidelity. \n \n Structured seven-step workflow: extract node IDs from Figma URLs, fetch design context and screenshots, download assets, translate to project conventions, and validate against Figma specs \n Integrates with Figma MCP server (remote or desktop) to access layout properties, typography, colors, design tokens, and component structure \n Emphasizes design system reuse, design token mapping, and 1:1 visual par

Create, edit, analyze, and visualize spreadsheets with formula preservation and cached recalculation. \n \n Supports .xlsx , .csv , and .tsv files with formula-aware editing via openpyxl and pandas for analysis workflows \n Includes native Excel chart creation, cell formatting, and visual rendering via LibreOffice and Poppler when available \n Recalculates formulas before delivery and renders sheets for visual review to catch layout issues, formula errors, and styling inconsistencies \n Enforces

Fetch design context, screenshots, and assets from Figma, then translate designs into production code. \n \n Provides three core commands: get_design_context for structured node representation, get_screenshot for visual reference, and asset download via localhost endpoints \n Requires a mandatory workflow: fetch design context, retrieve screenshot, download assets, then implement using project conventions and design tokens \n Outputs React + Tailwind as a design representation; implementation mu

OS-level desktop and window screenshot capture with flexible save locations and region selection. \n \n Supports full-screen, app/window, active-window, and pixel-region captures across macOS, Linux, and Windows \n Automatically routes to OS default screenshot location, user-specified paths, or temp directory based on context \n Includes platform-specific helpers (Python for macOS/Linux, PowerShell for Windows) with preflight permission checks on macOS to reduce repeated sandbox prompts \n Prior

Prep meetings by pulling Notion context, tailoring agendas/pre-reads, and enriching with Codex research.

$22