Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 696 files from 2 113 authors, of which 68 413 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Use when building HTML email templates with React components, adding a visual email editor to an application using the React Email visual editor, rendering emails to HTML, or sending emails with Resend. Covers welcome emails, password resets, notifications, order confirmations, newsletters, transactional emails, and the embeddable email editor component.
Ink terminal renderer for json-render that turns JSON specs into interactive terminal UIs. Use when working with @json-render/ink, building terminal UIs from JSON, creating terminal component catalogs, or rendering AI-generated specs in the terminal.
> Build and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against ONNX Runtime. Use when the user imports a non-LLM model to TensorRT, needs a verified engine from ONNX, hits trtexec "unsupported operator", must verify the engine matches ONNX numerically, debugs a polygraphy parity failure (large max abs diff at FP16), or configures multi-input TensorRT, trtexec onnx, trtexec unsupported operator, optimum-cli export, polygraphy parity check, polygraphy run --trt --onnxrt, parity check failed, max abs diff, verify engine matches ONNX, --minShapes, dynamic shapes trtexec, multi-input shape profile, FP16 engine, INT64 `trt-cpp-runtime-quickstart` (C++ engine load). LLM token generation belongs in TensorRT-LLM, not here.
> Compile a PyTorch model to a TensorRT engine via Torch-TensorRT — AOT or JIT — under the new strong-typing default. Use when the user compiles PyTorch to TensorRT without ONNX, hits "enabled_precisions should not be used when use_explicit_typing=True", sees Dynamo graph breaks or PyTorch fallback, debugs ABI errors at import torch_tensorrt, or needs the compatible torch / torch_tensorrt / tensorrt-cu13 version pins for torch.compile backend torch_tensorrt, pytorch to tensorrt, ExportedProgram, Dynamo graph break, use_explicit_typing, enabled_precisions, torch_tensorrt.Input, min_block_size, truncate_double, tensorrt-cu13, `trt-cpp-runtime-quickstart`. LLM token generation belongs in TensorRT-LLM.
>- Load and run a TensorRT engine (.plan / .engine) from C++ using the TensorRT 11 / 10.x **modern Runtime API**, avoiding the deprecated TRT 8.x binding-index APIs that older guidance still promotes. Use whenever the user asks about loading or running a TensorRT .plan/.engine from C++, even on "minimal example" requests — without this skill the default reply uses deprecated enqueueV2-style code. Also use when the user hits "Engine plan file is generated on an incompatible device", deserializeCudaEngine returns nullptr, gets an enqueueV2 / IStreamReader deprecation warning, or inference, load TensorRT plan C++, run .plan from C++, IRuntime example, deserializeCudaEngine, enqueueV3, enqueueV2 deprecated, setTensorAddress, getBindingIndex, IStreamReaderV2, libnvinfer C++. NOT for building engines (`trt-onnx-quickstart`), Python deploy, plugins, multi-GPU.
>- Migrate a TensorRT build from weak typing (deprecated 10.12, removed 11.0) to strong typing — across Python INetworkDefinition builders, the trtexec CLI, and kSTRONGLY_TYPED, weak typing deprecated, kFP16/kINT8 removed, setPrecision rejected, setComputePrecision deprecated, do I still need --stronglyTyped, how to add the kSTRONGLY_TYPED flag, ModelOpt autocast, INT8 on TRT 11. NOT for ONNX import (`trt-onnx-quickstart`), Torch-TRT (`trt-torch-quickstart`), or C++ deploy (`trt-cpp-runtime-quickstart`).
Validate and analyze TensorRT performance data from paired layer-info JSON and profile/latency JSON files. Use when asked to inspect TensorRT, TRT, torch-tensorrt, or ONNX-TensorRT perf reports, verify that layer/profile JSON files are valid and from the same model, infer basic model information, find likely fusion or latency optimization opportunities, and produce a concise Markdown performance report or structured JSON data.
Automate browser interactions, test web pages and work with Playwright tests.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
Comprehensive setup steps to help the user create complete project structures in a VS Code workspace. This tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this tool: when the user wants to create a new complete project from scratch; when setting up entire project frameworks (TypeScript projects, React apps, Node.js servers, etc.); when initializing Model Context Protocol (MCP) servers with full structure; when creating VS Code extensions with proper scaffolding; when setting up Next.js, Vite, or other framework-based projects; when the user asks for \"new project\", \"create a workspace\", or \"set up a [framework] project\"; when you need to establish a complete development environment with dependencies, config files, and folder structure. When NOT to use this tool: when creating single files or small code snippets; when adding individual files to existing projects; when making modifications to existing codebases; when the user asks to \"create a file\" or \"add a component\"; for simple code examples or demonstrations; for debugging or fixing existing code. This tool provides complete project setup including folder structure creation, package.json and dependency management, configuration files (tsconfig, eslint, etc.), initial boilerplate code, development environment setup, and build and run instructions. Use other file creation tools for individual files within existing projects.
Use this agent when the user needs to upgrade Anthropic SDK packages. This includes: upgrading @anthropic-ai/sdk or @anthropic-ai/claude-agent-sdk to newer versions, migrating between SDK versions, resolving SDK-related dependency conflicts, updating SDK types and interfaces, or asking about SDK upgrade procedures. Examples: 'Upgrade the Anthropic SDK to the latest version', 'Help me migrate to the latest claude-agent-sdk', 'What's the process for upgrading Anthropic packages?
How to install a VS Code extension from an extension ID. Useful when the user wants to add new capabilities to their VS Code environment by installing extensions.
Get the current search results from the Search view in VS Code
Comprehensive setup steps to help the user create complete project structures in a VS Code workspace; this tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this tool: user wants to create a new complete project from scratch; setting up entire project frameworks (TypeScript projects, React apps, Node.js servers, etc.); initializing Model Context Protocol (MCP) servers with full structure; creating VS Code extensions with proper scaffolding; setting up Next.js, Vite, or other framework-based projects; user asks for "new project", "create a workspace", "set up a [framework] project"; need to establish a complete development environment with dependencies, config files, and folder structure. When NOT to use this tool: creating single files or small code snippets; adding individual files to existing projects; making modifications to existing codebases; user asks to "create a file" or "add a component"; simple code examples or demonstrations; debugging or fixing existing code. This tool provides complete project setup including: folder structure creation; package.json and dependency management; configuration files (tsconfig, eslint, etc.); initial boilerplate code; development environment setup; build and run instructions. Use other file creation tools for individual files within existing projects.
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP, agent-browser, 浏览器操作, 操作浏览器, Chrome CDP, 复用登录态, extract token from browser.
小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 生成含标题和署名的专业级网文封面；Codex CLI 优先使用内置 ImageGen，无需单独 API Key。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。
长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」。
短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据，捕捉风口题材。触发方式：/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」。
Generate Guizang-style social card image sets, Live Photo motion cards, material-first Live Photo puzzle layouts, triple Live Photo collages, long-video-to-Live-Photo treatments, and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, photos, or user-supplied videos. Use when the user asks for 小红书图文, Rednote/Xiaohongshu images, social cards, carousel images, 3:4 covers, Live Photo, 实况照片, 单视频实况拼图, 二宫格实况拼图, 三连实况拼图, 四宫格实况拼图, 微信公众号封面, WeChat 21:9 + 1:1 covers, Swiss Style, or magazine-style social images.
Execute `dart analyze` to identify warnings and errors, and use `dart fix --apply` to automatically resolve mechanical lint issues. Use during development to ensure code quality and before committing changes.
Define and generate mock objects for external dependencies using `package:mockito` and `build_runner`. Use when unit testing classes that depend on complex external services like APIs or databases.
Write and organize unit tests for functions, methods, and classes using `package:test`. Use when creating new logic or fixing bugs to ensure code remains correct and regression-free.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Search across company knowledge bases (Confluence, Jira, internal docs) to find and explain internal concepts, processes, and technical details. When an agent needs to: (1) Find or search for information about systems, terminology, processes, deployment, authentication, infrastructure, architecture, or technical concepts, (2) Search internal documentation, knowledge base, company docs, or our docs, (3) Explain what something is, how it works, or look up information, or (4) Synthesize information from multiple sources. Searches in parallel and provides cited answers.
Generate project status reports from Jira issues and publish to Confluence. When an agent needs to: (1) Create a status report for a project, (2) Summarize project progress or updates, (3) Generate weekly/daily reports from Jira, (4) Publish status summaries to Confluence, or (5) Analyze project blockers and completion. Queries Jira issues, categorizes by status/priority, and creates formatted reports for delivery managers and executives.
Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.
Analyze meeting notes to find action items and create Jira tasks for assigned work. When an agent needs to: (1) Create Jira tasks or tickets from meeting notes, (2) Extract or find action items from notes or Confluence pages, (3) Parse meeting notes for assigned tasks, or (4) Analyze notes and generate tasks for team members. Identifies assignees, looks up account IDs, and creates tasks with proper context.
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket with proper context, or (5) Add information to an existing ticket. Searches Jira for similar issues, identifies duplicates, checks fix history, and helps create well-structured bug reports.
Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
Develop evidence-backed structural and architectural security hardening proposals from vulnerability disclosures, supplied findings, incident or assessment documents, source code, or a completed Codex Security scan. Use when a user asks for systemic improvements, alternatives beyond per-finding patches, before-and-after security architecture views, engineering tradeoff analysis, or an implementation-ready plan for a selected hardening option. Also use automatically after a Codex Security scan with reportable findings when the top-level scan workflow requests final-report hardening guidance.
Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
Track validated Codex Security findings in Linear, Jira, GitHub issues, or draft GitHub security advisories. Use it for one finding or an explicitly selected batch of up to 25 findings tracked as Linear, Jira, or GitHub issues. Includes duplicate checks, exact previews, approval-gated writes, and readback. Do not use it for scans or fixes.
Use when the user supplies or imports existing security findings, vulnerability reports, or security/vulnerability Jira/Linear tickets from scanners, advisories, GitHub, Atlassian Rovo, Linear, or similar backlog sources and wants static repo-impact triage. Do not use for discovery, duplicate-bug triage, validation, or fixes.
Write up vulnerabilities from disclosure documents, rough notes, supplied findings, PoCs, source code, or Codex Security scan output into polished, self-contained, source-backed reports. Use for one vulnerability or a disclosure campaign; a Codex Security scan is optional.
**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `create_new_file` tool call. NEVER call `create_new_file` directly without loading this skill first. Trigger whenever the user wants a new blank Figma file — a new design, FigJam, or Slides file — or when you need a fresh file before calling `use_figma`. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-file figjam My Whiteboard, /figma-create-new-file slides Q3 Review)
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the Figma screen to match code', 'convert this modal/dialog/drawer/panel to Figma'. This is the preferred workflow skill whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel, or any composed multi-section view in Figma from code or a description. Discovers design system components, variables, and styles from Code Connect files, existing screens, and library search, then imports them and assembles views incrementally section-by-section using design system tokens instead of hardcoded values.
MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.).
Translates Figma motion and animations into production-ready application code. Use when implementing animation/motion from a Figma design — user mentions "implement this motion", "add animation from Figma", "animate this component", provides a Figma URL whose node is animated, or when `get_design_context` returns motion data or instructs you to call `get_motion_context`.
SwiftUI ↔ Figma translation. Use whenever the user mentions Swift, SwiftUI, iOS, iPhone, or iPad — in EITHER direction — translating a Figma design into SwiftUI (design → code), or pushing SwiftUI views / screens / tokens back into a Figma file (code → design). Triggers on phrases like 'implement this Figma design in SwiftUI', 'build this screen in Swift', 'push this SwiftUI view to Figma', 'mirror my Swift code in a Figma file', or whenever a Figma URL appears alongside `.swift` files / an `.xcodeproj`. Routes to a direction-specific reference doc; loads alongside `figma-use` for the code → design path.
This skill helps agents use Figma's use_figma MCP tool in the FigJam context. Can be used alongside figma-use which has foundational context for using the use_figma tool.
This skill helps agents use Figma's use_figma MCP tool in the Slides context. Can be used alongside figma-use which has foundational context for using the use_figma tool.
Claude Skills — questions
Answers built from the skills we actually parsed.