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. 86 961 files from 2 125 authors, of which 68 678 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.
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
当你有规格说明或需求用于多步骤任务时使用，在动手写代码之前
当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用
Fetches URLs and PDFs, then summarizes or returns clean Markdown. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.
Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.
Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.
Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing, localizing, or cutting AI tone. Not for code comments or commit messages.
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
Produces distinctive production UI and screenshot-grounded visual polish. Use when building or restyling pages, components, or typography. Not for backend logic or data pipelines.
Core Native SDK guide for AI agents. Read this before explaining the Native SDK or changing a Native SDK app. Covers the mental model (native-rendered apps by default, WebView shells as a coexisting architecture), project structure, app.zon, App and Runtime patterns, frontend integration, web engines, JavaScript bridge commands, permissions, windows, WebViews, dialogs, packaging, debugging, testing, and when to load deeper references. For authoring native-rendered UI (Native markup .native views, Model/Msg/update, UiApp), load the native-ui skill. Use when the user asks what the Native SDK is, how to build or modify an app, how to package or debug it, or how to add native capabilities.
Zig 0.16 idioms for Native SDK code, indexed by compile error. Load when `zig build` fails on std APIs with errors like "struct 'fs' has no member named 'cwd'", "struct 'array_list.Aligned(u8,null)' has no member named 'init'", "struct 'std' has no member named 'io'", "no member named 'GeneralPurposeAllocator'", "no member named 'getEnvMap'", or "invalid format string" - the signature of code written for Zig 0.15 or earlier. Covers main(std.process.Init), std.Io file IO and writers, ArrayList, process spawning, environment, clocks and sleep, sockets, custom formatting, and build.zig module shapes, each as this SDK writes them.
Discovery skill for the Native SDK, the complete toolkit for building native desktop applications - views are declarative Native markup (.native), logic is plain Zig, and the toolkit's own engine renders every pixel, with WebView surfaces as the optional web-content path. Use when the user asks what the Native SDK is, how to build a Native SDK app, author native UI, scaffold an app, configure app.zon, add bridge commands, embed web content, package an app, test a running app, or automate a Native SDK app.
Authoring guide for native-rendered Native SDK apps - declarative Native markup (.native) views plus Zig logic on the UiApp loop. Use when building or modifying native UI (widgets, layout, bindings, messages), writing .native files, wiring Model/Msg/update, testing markup views, or verifying a native app through the automation harness.
Automation and verification guide for running Native SDK apps. Use when the user asks to test a running app, inspect runtime state, list windows, wait for readiness, drive widgets, take deterministic screenshots, send bridge commands, debug why automation is not connected, create smoke tests, or verify a Native SDK example in a GUI-capable session.
Authoring guide for TypeScript app cores - Model, Msg, update, and the pure functions they call, written in the closed app-core subset, checked by the @native-sdk/core frontend, and compiled ahead-of-time to native code by the external core compiler. Use when writing or modifying a src/core.ts app core, fixing subset checker errors (NS1001-NS1060), or deciding how to express state, messages, text (bytes and the byte-text string methods), text input, continuous controls (sliders, scroll), effects (Cmd), subscriptions (Sub), the host-event wiring channels (frameMsg, keyMsg, appearanceMsg, chromeMsg, envMsgs, app.zon assets), derived values, the view_unbound lint opt-out, local mutation of owned arrays, or how to split a core into modules under src/ (relative imports, namespace imports, @native-sdk/core/text, @native-sdk/core/events).
Use when debugging a Pysa false negative (missing taint issue), comparing two Pysa output directories, or finding where taint flow is lost.
Use when you need to understand the Pyre or Pysa codebase architecture, find where specific functionality is implemented, or navigate the source directory structure. Use when working on OCaml code, debugging type checking or taint analysis issues, or exploring the codebase.
Use when creating commits or diffs to apply the correct title prefix, reviewer, and test plan based on the area of the codebase being changed.
Use when reading, writing, or debugging Pysa JSON model output (.models files). Use when working with taint models that describe sources, sinks, TITO, sanitizers, or issues in JSON format.
Use when running, debugging, updating, or creating Pysa end-to-end integration tests. Use when taint analysis tests fail, when expected output files need updating, or when working with .models, .cg, .hofcg, .overrides files under `source/interprocedural_analyses/taint/test/integration`.
Interact with iOS simulator or Android emulator/device using snapshot-based coordinates. Uses accessibility tree snapshots for precise element targeting, with screenshot verification as fallback. Use when navigating the app on a simulator/emulator.
Full workflow for fixing a GitHub issue - understand the problem, reproduce, diagnose root cause, fix, test on iOS/Android simulators, review, and raise a PR
Review a FlashList PR or branch, run unit tests, test on iOS simulator, and verify RTL/LTR behavior. Shared context with fix-github-issue skill.
Triage a GitHub issue — classify priority (P0/P1/P2), search for duplicates, and apply labels.
Analyze agent feedback artifacts from GitHub Actions workflow runs, extract actionable learnings, and incorporate them into skill files and CLAUDE.md. Tracks scan progress to avoid re-processing.
Create a GitHub PR for FlashList. Ensures no AI/Claude attribution in commits or PR body, follows repo conventions for title, description, and test plan.
Upgrade the React Native fixture app to a new version. Covers JS deps, Android (Gradle, Kotlin, SDK), iOS (Podfile, pbxproj), Metro config, and third-party libraries.
Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, SysML / MBSE diagrams (block definition, internal block, requirement, parametric), BPMN business process diagrams, swimlane / cross-functional flowcharts, network topology, cloud architecture from Terraform or Kubernetes manifests, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Best suited when the diagram needs custom styling, rich shape vocabulary, swimlanes, or exportable images (PNG/SVG/PDF/JPG). Generates .drawio XML and exports locally via the native draw.io desktop CLI.
> Add or review structured error logging in EdenFS daemon (C++) — the ErrorLogger / EdenErrorInfo system that feeds the edenfs_errors table. Use when exception_wrapper / .thenError), instrumenting a failure path, or debugging a wrong stack trace or wrong component. Covers throw-site trace rules, component choice, errorType, noise filtering, gating, and testing.
> This guide explains how to create new EdenAPI/SLAPI endpoints, covering both streaming and non-streaming patterns.
> Load FIRST before searching code in eden/. Contains component-to-file maps, key type names, and architecture diagrams for EdenFS, Sapling, and Mononoke. Tells you exactly which files to read for any task. References contain per-component quick reference tables.
Triage systemd-managed EdenFS issues on Linux devservers and OnDemands. Use when investigating EdenFS service failures, unexpected restarts, systemctl errors, edenfs_upgrade/edenfs_restarter problems, or when a user reports EdenFS is down on a systemd-enabled host. Also use when someone asks how systemd-managed EdenFS works, how to monitor it, or how to check its health. Use when asked to build a timeline of EdenFS lifecycle events, show edenfs restart history, or understand how edenfs reached its current state. Trigger on mentions of edenfs systemd, edenfs@ service, edenfs_upgrade timer, edenfs auto-restart, eden status --debug, systemctl edenfs, edenfs lifecycle management, edenfs timeline, edenfs restart history, or "what happened to edenfs".
Create a Mononoke server-side hook with 3-diff split (tests, wiring, implementation), unit tests, and integration tests
Use when the user provides Warp commit SHA(s) and GitHub issue number(s) to assess, draft issue comments, post progress updates, or recommend whether issue threads should stay open or close.
Generate a starting-point GitHub release notes draft for an upcoming Warp release (feature or bugfix, auto-detected from the version). Run from a release branch, or pass a branch / git ref as the argument.
Audit Warp CHANGELOG.md before a release: recover lost entries, sort by user impact, refine entry language, line-wrap, and (release-branch mode) bump compare refs.
Generate a Warp release audit report (pre-release or RC, auto-detected from version string and head ref).
>- a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; seconds of compiling before real work begins; JIT modules recompiling on every run or every CI job. Only applies when the code being optimized uses Warp kernels. Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build times.
> Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small launches, host fallbacks, or large intermediates. CPU-only code and absent GPU dependencies are normal unless NVIDIA is prohibited. Exclude required cross-vendor or CPU-only deployment, vendor-lowered dense or NN layers, general Warp API questions, and already-selected Warp kernels. Contribution policy alone is not exclusion.
>- Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on wp.Tape gradients, so treat any misbehavior of such a workflow as a gradient problem until proven otherwise — use this when training diverges or NaNs, won't train at all, stalls or plateaus above the expected loss, converges to a wrong or biased answer, is worse than a reference implementation, works at small scale but fails at production scale, or fails a QA/validation recheck. Also for explicit symptoms — exploding, NaN/inf, zero, or subtly wrong gradients, suspected wp.Tape/backward issues, gradcheck failures — but users usually describe only the surface symptom ("the sim explodes", "the fit gets dragged toward outliers") without mentioning problems, or autograd issues in other frameworks without Warp.
Proactive threat hunt over web/application logs — no alert in hand. Profiles the corpus, runs a hypothesis-driven hunt loop with a mandatory written ledger, confirms suspects in source, detonates a local PoC, and writes INCIDENTS.json + INCIDENT_REPORT.md. Use when asked to "hunt the logs", "find the campaign", "look for signs of compromise", or "run dnr-hunt". The no-alert entry to the detection & response track; /dnr-respond is the lead-in-hand entry.
Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner output and writes TRIAGE.json + TRIAGE.md sorted by what actually needs engineering attention. Use when asked to "triage findings", "validate scanner output", "prioritize vulns", or "review the backlog". Runs interactively by default; pass --auto to skip the interview.
>- application owner through the four-question framework and produces a threat model from their answers; "bootstrap" derives a threat model from the code plus past vulnerabilities (CVEs, git history, pentest reports) when no owner is available; "bootstrap-then-interview" chains the two when both owner and codebase are present. All write THREAT_MODEL.md in a shared schema. Use when asked to "threat model", "build a threat model", "map the attack surface", or "what should we be worried about in this codebase".
Generate candidate fixes for verified security findings. Consumes TRIAGE.json (preferred), VULN-FINDINGS.json, INCIDENTS.json, or a vuln-pipeline results directory. Pipeline input is delegated to the execution-verified `vuln-pipeline patch` ladder; static-analysis input gets a per-finding patch subagent + independent reviewer and is written as inert diffs for human review. Writes PATCHES/bug_NN/{patch.diff,patch_result.json}, PATCHES.md, and PATCHES.json. Use when asked to "fix the findings", "patch these vulns", "generate fixes", or "close the loop on triage".
Adapt this C/C++ ASAN vulnerability pipeline to a different vulnerability class, target shape, language, or detection mechanism. Use when the user wants to port, migrate, retarget, customize, or fork the pipeline for something other than C/C++ memory-safety bugs — web apps, smart contracts, deserialization, ML systems, or any other domain.
>- intro, then an offer to walk you through your first run on the canary cites where it looked, and hands you the next command. Use for "how do I…", "why does…", "where is…", "can this…", or just "/quickstart" to get oriented.
Incident response workup for a lead in hand — an alert, an IOC, or a /dnr-hunt finding. Scopes the lead across the logs, verdicts whether the attack succeeded, quantifies blast radius, confirms root cause in source with a local PoC, and writes a proposed (never executed) containment/remediation/recovery plan. Use when asked to "respond to this alert", "work this incident", "how bad is this", or "run dnr-respond". /dnr-hunt is the no-alert entry to the same track.
>- Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .md for /triage to consume. Read-only — no building, running, or network. For execution-verified crashes, use vuln-pipeline instead. Use when asked to "scan for vulns", "review this code for security issues", "find bugs in <dir>", or as the step between /threat-model and /triage.
> Port a PyTorch model to use pyrefly's tensor shape type system (Tensor[[B, C, H, W]], Int[T]). Use this skill whenever the user wants to add shape annotations to a PyTorch model, type a model with tensor dimensions, port a model to use shape tracking, or annotate model forward methods with tensor shapes. Also use when the user mentions tensor shape ports, Int types for PyTorch, or pyrefly shape checking on a model file. Invoke BEFORE starting any model port — the skill's gated workflow prevents common failure modes.
Use when Pyrefly computes a wrong tensor shape (or is missing one that can't be expressed in a stub signature) and you need to add or fix a shape-DSL rule. Requires a Pyrefly checkout (fbsource or a clone); not usable from a pip/site-packages install.
Build UIs with @nuxt/ui v4 — 125+ accessible Vue components with Tailwind CSS theming. Use when creating interfaces, customizing themes to match a brand, building forms, or composing layouts like dashboards, docs sites, and chat interfaces.
>- Skill to run xcodebuild tests on iOS Simulator while recording a video walkthrough, dynamically selecting the highest available OS and device. Most useful for running XCUITests.
Orchestrates a strict TDD loop across subagents to build features.
Ensure code is styled and commits follow Conventional Commits.
Use deepsec (an AI-powered vulnerability scanner) — running scans, configuring projects, writing matchers, and authoring plugins. Activates when the user asks how to scan, configure, or extend deepsec in a project that has deepsec installed.
Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.
Use this skill for camera control and immediate-mode drawing in melonJS — following a target, viewport bounds, shake and fade, secondary cameras and what each one draws, and drawing shapes, lines and gradients inside a custom draw(). Covers world versus screen coordinate conversion, clipping and masking, baking with CanvasRenderTarget, and reading pixels back. Triggers on: Camera2d, viewport, follow, offset, look ahead, setBounds, minimap, second camera, split screen, cullMask, visibilityLayer, hide from a camera, shake, fadeIn, fadeOut, worldToLocal, localToWorld, colorMatrix, renderer.fill, renderer.stroke, Rect, Ellipse, Polygon, Line, Gradient, clipRect, mask, CanvasRenderTarget, NoiseTexture2d, lookAt, setBasis, toImageData, getImageData, toBlob, toDataURL, screenshot, read pixels.
Use this skill when packaging, shipping or scaffolding a melonJS game — starting a project with create-melonjs, building for the web, wrapping as a native app with Capacitor or Cordova, publishing to WeChat Mini Games or Facebook Instant Games, browser support and transpiling. Triggers on: create-melonjs, scaffold, new project, build, deploy, publish, Capacitor, Cordova, native app, iOS, Android, WeChat, Instant Games, browser support, transpile, ES2022, bundle size, tree-shaking.
Claude Skills — questions
Answers built from the skills we actually parsed.