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. 79 870 files from 1 769 authors, of which 62 217 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.
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any code. Covers framework selection (LangChain vs LangGraph vs Deep Agents), agent archetypes, dependency setup, and which skills to load next based on your decisions.
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and which skill to load next.
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.
INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.
OpenAPI documentation and REST API design patterns
Database migration patterns and schema versioning
Best practices for Docker containerization and multi-stage builds
Modern React component patterns with hooks and TypeScript
Unit testing and integration testing best practices
Migrate to the next major version of @elevenlabs/client, @elevenlabs/react, and @elevenlabs/react-native. Use when updating code that uses Conversation, Input, Output, useConversation, ElevenLabsProvider, ConversationProvider, or related APIs from these packages. Also trigger when users mention upgrading ElevenLabs packages, fixing breaking changes after an npm update, moving to the latest ElevenLabs SDK, or encountering type errors or runtime errors after updating @elevenlabs/* dependencies.
> Verify PR readiness before requesting review or merging. Checks title format, description compliance with the team template, risk label alignment, review thread resolution, CI status, coverage report, and screenshot requirements. Reasons about each review comment to help the engineer understand what's being asked and decide how to respond — rather than auto-fixing blindly.
Update tools/scripts/generate_binary_build_matrix.py when a PyTorch release goes live. Advances CURRENT_STABLE_VERSION to the new stable, promotes the release-channel CUDA/ROCm arches to match the candidate/test channel, and regenerates the JSON test fixtures. Triggered by mentions of "release go live", "advance stable version", "promote release matrix", or "update binary build matrix" for a new PyTorch X.Y release.
Review a pytorch/pytorch pull request's changes and decide whether they are safe to land. Emits a single machine-readable verdict (LAND or NO_LAND) for the greenlight auto-land gate.
Pin (or re-pin) the Linux manywheel builder docker images used by the nightly/release binary build workflows in pytorch/pytorch to a fixed .ci/docker build. Takes the release version (e.g. 2.13) as input. Updates DOCKER_IMAGE_PIN in .github/scripts/generate_binary_build_matrix.py and regenerates the workflows. Triggered by mentions of "pin docker image", "update docker pin", "docker image pin", "pin builder images", or "bump the manywheel image pin" for a release branch.
Generate a PyTorch release validation checklist issue by pulling open/closed issues from a GitHub milestone and cherry-picks from a release tracker issue. Triggered by mentions of "validation issue", "validation checklist", "release validation", or "release checklist".
Generate (and optionally open) a PyTorch release tracker / cherry-pick tracking issue from a release announcement, like https://github.com/pytorch/pytorch/issues/180506. Triggered by mentions of "release tracker", "release tracking issue", "cherry-pick tracker", or "cut a release branch issue".
Disable or re-enable Cloudflare R2 (download-r2.pytorch.org) usage in manage_v2.py during R2 outages. Can toggle R2 off/on for nightly builds, prod/stable builds, or both. The affected packages are PT_FOUNDATION_PACKAGES (torch, torchvision, torchaudio, fbgemm_gpu, fbgemm_gpu_genai, triton, pytorch_triton, pytorch_triton_rocm, pytorch_triton_xpu).
Find reverts that landed on pytorch/pytorch main but are missing from a release branch (release/X.Y) because the reverted commit was already shipped in a release candidate, and open one cherry-pick PR per missing revert against the release branch (on a fork branch, never pushing to release/X.Y directly), optionally posting a cherry-pick nomination comment for each on the release tracker issue. Driven by tools/analytics/github_analyze.py --analyze-missing-reverts-from-branch (the "GitHub Analytics Daily" workflow). Triggered by "missing reverts", "analyze reverts for release", "cherry-pick missing reverts", "reverts not in release/X.Y", or pointing at a GitHub Analytics Daily run and asking to cherry-pick the flagged reverts.
Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/*.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed through _linux-build.yml / _linux-test.yml. Use when migrating a workflow off EC2 onto on-site data center / EKS-hosted self-hosted runners (OSDC / ARC), enabling the ARC experiment, or wiring up `use-arc` / `runner_prefix` / `ci-docker-hash` / `python-version` / `compiler` / `cuda-version` inputs.
Triage a failing vLLM Buildkite CI build for a PyTorch version-bump PR, isolate new regressions vs. pre-existing failures on main by comparing against recent "Full CI run - nightly/daily" builds, classify by root cause, and file one grouped issue per root cause in pytorch/pytorch (linked under an umbrella issue). Use when the user points at a Buildkite build for a torch/triton upgrade and asks "what's broken that isn't broken on main" or "file issues for each failure".
Execute the daily virtual trading process. Research markets, make trades, save snapshot, write diary and memory.
Keep Codex focused on requested and necessary work. Use for bounded changes, review-only tasks, scope creep, speculative hardening, unnecessary hashing or dependencies, repeated audit loops, or when the user invokes Stop That Shit.
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your own sessions.
Helps creators find topics grounded in their own experience, diagnose how a script may spread and whom it may attract, and compare its expected performance with their content baseline.
影视概念美术专家 & 视觉导演技能——从剧本/故事/世界观文字中提取并设计 AI 视频所需的标准化视觉资产提示词。当用户要求"从剧本提取角色/场景/道具/载具提示词"、"生成角色定妆照 prompt"、"生成场景空镜 prompt"、"生成道具/载具/机械资产设定图 prompt"、"为 AI 视频做视觉资产设计"、"拆解剧本出图清单"时使用本技能。产出角色定妆（全身/半身）、场景空镜、道具/载具/机械资产设定图四类提示词，中英双语，含影调定调与色彩科学方案。
规划、编写、审阅和修复由真实授权素材与 AI 生成镜头混合制作的电影级文旅宣传片。用于文旅短片创意简报、场景图筛选、首帧空间分析、分镜脚本、画面内容提示词、人物动作、导演级运镜、自然动机布光、转场与尾帧衔接、Seedance 2.0/可灵/Midjourney 提示词、生成结果诊断、时间线与合规风险检查；尤其适用于需要写实、辽阔、自由感和角色剧情连续性的项目。
miora 视频生成的可靠性与规格层——补内置技能未覆盖的部分：四必填参数闸门（模式/分辨率/时长/画幅缺一不可提交）、时长区间闸门、完成信号的判定与轮询等待、官方规格口径与本通道实测差异（时长/分辨率/参考图上限）、文生/首尾帧/参考生三种模式的参数事实、提示词的自动修正边界、生成状态向用户的同步。当用户要生成视频、动效、短视频，或提到参考生视频/首尾帧/图生视频、miora 视频、minimax h3、视频生成进度、视频怎么还没出来时使用。
动作打戏 AI 视频提示词设计技能。当用户需要设计具备电影级运镜、节奏感、打击感的武打/战斗片段提示词时使用——覆盖双角色对打、女主 vs 怪兽、近身格斗、载具追逐战、群战、一镜到底、巨型生物/机甲大场面等场景。核心方法论：时序拆段（15 秒拆成 2-3 秒阶段）、动作因果链、环境反馈、视觉资产锁定与参考图映射、音效层。触发词：动作打戏、打戏提示词、武打镜头、战斗片段、打击感、fight scene、对打、动作设计、追车战、群殴、一镜到底。
>- End-to-end 3D printing for Bambu Lab printers. Finds models online (MakerWorld, Printables), generates them with AI (text-to-3D, image-to-3D) or as exact-dimension parametric CAD, checks and repairs printability, converts textures to AMS multi-color, renders previews, opens them in Bambu Studio for the user to print, and reads printer status, AMS filaments and print progress. Use this whenever the user wants to 3D print something, design or model an object for printing, work with STL/3MF/OBJ/GLB files for a printer, check on a Bambu Lab printer (A1, A1 Mini, A2L, P1S, P2S, X1C, X1E, X2D, H2C, H2S, H2D, H2D Pro), or asks about AMS filament, slicing or print progress, even if they don't say "Bambu".
Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work. Use this whenever the user asks to spin off, offload, or delegate a task to Antigravity, agy, Gemini, or an "external agent"; wants a second opinion or independent review from a different model; wants intensive repo work (audits, large refactors, research sweeps) run in the background while you keep working; or says things like "have Antigravity do it", "spin up a sub-agent for this", or "get more done in parallel". Also use it proactively when a task is a good fit for parallel delegation and the user has expressed a preference for using Antigravity workers.
CesiumJS materials and post-processing — Material, Fabric JSON, MaterialAppearance, ImageBasedLighting, PostProcessStage, PostProcessStageLibrary, bloom, depth of field, ambient occlusion, FXAA, tonemapping, BlendingState. Use when defining Fabric materials for entities or primitives, configuring PBR image-based lighting, or adding screen-space post-processing effects.
CustomShader authoring — vertexShaderText and fragmentShaderText against VertexInput, FragmentInput, FeatureIds, Metadata, czm_modelMaterial. Use when reading EXT_mesh_features or EXT_structural_metadata property textures/tables, vertex displacement, or shading VoxelPrimitive.
CesiumJS camera control - Camera, flyTo, lookAt, setView, ScreenSpaceCameraController, CameraEventAggregator, flight animation. Use when positioning the camera, creating flyTo animations, constraining user navigation, tracking entities, or converting between screen and world coordinates.
CesiumJS 3D Tiles - Cesium3DTileset, compressed and CAD-style glTF content, MVTDataProvider, styling, metadata, feature picking, voxels, point clouds, I3S, Gaussian splats, clipping. Use when loading 3D Tiles or Mapbox Vector Tiles, rendering KHR meshopt/CAD content, styling or querying features, working with voxels or point clouds, or clipping spatial data.
CesiumJS imagery layers - ImageryProvider, ImageryLayer, ImageryLayerCollection, WMS, WMTS, Bing, OpenStreetMap, ArcGIS, Mapbox, tile discard policies. Use when adding or swapping base map layers, configuring imagery providers, layering multiple map sources, or creating split-screen imagery comparisons.
CesiumJS interaction and picking - ScreenSpaceEventHandler, multi-key KeyboardEventModifier input actions, Scene.pick, Scene.drillPick, Scene.pickPosition, mouse and touch events. Use when handling user clicks on the globe, selecting entities or 3D Tiles features, registering modifier-key shortcuts, implementing hover effects, or building drag-based interactions.
CesiumJS core utilities and networking - Resource, Color, Event, Request, RequestScheduler, error handling, helper functions, feature detection. Use when fetching remote data, managing HTTP requests, working with colors, handling events, debugging errors, or using utility functions like defined, clone, or buildModuleUrl.
CesiumJS entities and data sources - Entity, EntityCollection, DataSource, GeoJsonDataSource, KmlDataSource, CzmlDataSource, Graphics types, PathGraphics, PathMode, Visualizers. Use when adding points, labels, models, polygons, polylines, or time-segmented paths, loading GeoJSON/KML/CZML/GPX data, or working with the high-level Entity API.
CesiumJS models, glTF, and particle effects - Model, KHR_meshopt_compression, CAD glTF extensions, EdgeDisplayMode, ModelAnimation, ModelNode, ParticleSystem, emitters, GPM extensions. Use when loading compressed or CAD-style glTF/GLB models, controlling edge rendering, playing model animations, positioning particles, or working with geospatial positioning metadata.
CesiumJS terrain, globe, and environment - TerrainProvider, Globe, sampleTerrain, atmosphere, sky, fog, lighting, shadows, panoramas. Use when configuring terrain providers, querying terrain heights, customizing atmosphere or sky rendering, adding panoramas, or adjusting scene lighting and shadows.
CesiumJS primitives and geometry - Primitive, GeometryInstance, Appearance, BufferPrimitive collections, GeoJsonPrimitive, Billboard/Label/PointPrimitive collections, built-in geometry shapes, ground primitives, classification. Use when rendering performance-critical static or vector geometry, loading GeoJSON without entities, creating custom shapes, batching draw calls, or using low-level collections.
CesiumJS spatial math - Cartesian3, Cartographic, Matrix4, Quaternion, Transforms, Ellipsoid, BoundingSphere, projections, coordinate conversions. Use when converting between coordinate systems, computing positions on the ellipsoid, performing spatial intersection tests, building model matrices, or working with geographic projections.
CesiumJS viewer setup - Viewer, CesiumWidget, widgets, Ion token, Scene configuration, SceneMode, factory helpers, geocoders, platform services. Use when initializing a CesiumJS application, configuring viewer widgets, setting Ion access tokens, creating default terrain or imagery, or bootstrapping a 3D globe.
CesiumJS time, properties, and animation - Clock, JulianDate, TimeInterval, Property, SampledProperty, CallbackProperty, PathMode, interval and sampled path materials, interpolation, splines, CZML temporal data. Use when making entity attributes or path materials time-dynamic, configuring the simulation clock, interpolating positions, or working with sampled, interval, or callback properties.
Use when starting any conversation involving CesiumJS development - provides orientation on available domain skills and how they activate
Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl. Use for recurring competitive intelligence, pricing tier extraction, feature change tracking, or structured competitor alerts.
Extract structured company lists from directories with Firecrawl. Use for scraping YC, Crunchbase, Product Hunt, G2, startup directories, category directories, or custom company databases into JSON, CSV, CRM-ready lists, or research tables.
Ingest public or authenticated knowledge bases and docs portals with Firecrawl browser. Use for JS-heavy docs, login-gated portals, paginated help centers, support knowledge bases, or structured JSON/markdown extraction from documentation sites.
| findings, contrarian views, open questions, and full sources. Use only when the user needs rigorous synthesis of a complex topic (scientific, technical, policy, or market-analytical) that cannot be answered with a short search, and wants a formal written report, not a recommendation list. Do not use for product picks, top-N lists, quick lookups, or routine "find out about X" tasks. If the request does not clearly need this kind of report, do not use this skill.
Pull metrics from analytics dashboards and internal web tools with Firecrawl browser. Use when the user needs dashboard reporting, cross-platform metric summaries, authenticated analytics extraction, date-range reports, or structured metrics from web dashboards.
Generate structured lead lists from prospect databases and web directories with Firecrawl browser. Use for finding prospects by role, company type, industry, stage, location, technologies, or other criteria and exporting CRM-ready JSON or CSV.
Walk through a product's key flows with Firecrawl browser and produce a structured UX/product walkthrough. Use for signup, onboarding, pricing, docs, dashboard, product demo prep, UX teardown, and first-run experience analysis.
Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors, topic corpora, or LLM-ready markdown organized from web sources.
Find and synthesize research papers, whitepapers, PDFs, technical reports, and academic sources with Firecrawl Research, using semantic paper search, related-paper expansion, and in-body verification. Use when the user wants a literature review, paper summary, research landscape, or sourced synthesis from PDFs and scholarly/industry publications.
Extract any website's design system into an agent-ready DESIGN.md using Firecrawl scrape evidence. Use when the user wants colors, fonts, spacing, components, layout patterns, or brand/UI guidance from a website so AI agents can create new websites, clone a look, or build pages inspired by that design.
Produce pre-meeting lead intelligence briefs with Firecrawl. Use when the user needs company research, person research, recent news, talking points, pain points, or outreach preparation before a sales call, partnership meeting, investor conversation, or customer interview.
Claude Skills — questions
Answers built from the skills we actually parsed.