Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when writing any new code, adding features, or fixing bugs that require code changes. Enforces strict RED-GREEN-REFACTOR cycle with no production code without a failing test first. Triggers: new feature implementation, bug fix, refactoring existing code, adding behavior to existing modules.
Strategic guidance for choosing and implementing testing approaches across the test pyramid. Use when building comprehensive test suites that balance unit, integration, E2E, and contract testing for optimal speed and confidence. Covers multi-language patterns (TypeScript, Python, Go, Rust) and modern best practices including property-based testing, test data management, and CI/CD integration.
Use when choosing a testing approach for a project — selecting frameworks, defining coverage thresholds, setting up test infrastructure, and establishing testing patterns. Triggers: new project setup, CI/CD pipeline design, coverage audit, test framework migration, quality standard definition.
Comprehensive Three.js and React Three Fiber skill for creating 3D scenes, characters, NPCs, procedural generation, animation retargeting, and interactive experiences. Use when user asks to "create Three.js scene", "setup React Three Fiber", "add 3D character", "create NPC AI", "procedural 3D generation", "retarget animation", "setup avatar system", or "create 3D game".
Investigate distributed traces and spans in OpenSearch. Use this skill when the user wants to analyze traces, investigate slow spans, find error spans, track agent invocations, measure token usage, reconstruct trace trees, query service maps, or debug distributed systems through trace data. Activate even if the user says traceId, spanId, OpenTelemetry, OTel, distributed tracing, latency, span duration, service map, or trace investigation without mentioning OpenSearch.
Multi-agent trading analysis for a stock ticker. Runs technical, news, fundamentals, and macro analysts in parallel, then an adversarial bull/bear debate, then Research Manager, Trader, and Portfolio Manager to produce a final BUY/SELL/HOLD decision with entry, stop, and sizing.
Single-cell trajectory inference pipeline covering diffusion pseudotime (DPT), PAGA, RNA velocity with scVelo, and fate mapping with CellRank. Use when the user mentions pseudotime, trajectory, lineage, differentiation, RNA velocity, scVelo, CellRank, PAGA, diffusion map, fate probabilities, terminal states, spliced/unspliced, velocyto, order cells by development, cell differentiation path, cell fate, branching analysis, monocle, developmental trajectory, stem cell differentiation, progenitor to mature, how do cells differentiate, cell lineage tree, velocity arrows, fate mapping, transition probabilities, root cells, terminal states, absorption probabilities, or latent time.
Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.
Reason about translational research problems in HCLS — especially neurology and hypothesis validation. Use when the user asks to design a validation study, evaluate a target, qualify a biomarker, choose endpoints, critique a preclinical-to-clinical plan, pick a trial design (basket/umbrella/platform), plan multimodal data integration, or assess whether a hypothesis is ready to advance. Triggers include phrases like "validate target", "biomarker context of use", "bench to bedside", "T0/T1/T2/T3/T4", "proof of mechanism", "target engagement", "design a trial for", "preclinical model translates", "imaging-genetics", "is this ready for Phase 2", "mouse results to humans", "GWAS/eQTL/MR", "endpoint selection", "drug repurposing rationale", "fail fast".
Hotwire Turbo for Symfony UX -- SPA-like speed with zero JavaScript. Covers Drive (navigation), Frames (partial page sections), and Streams (multi-target updates). Use when building ajax navigation, lazy-loaded sections, inline editing, pagination without reload, modals from the server, flash messages via streams, or real-time updates via Mercure/SSE. Code triggers: turbo-frame, turbo-stream, data-turbo-frame, data-turbo, data-turbo-action, turbo-stream-source, TurboStreamResponse, <twig:Turbo:Frame>, <twig:Turbo:Stream:Append>, <twig:Turbo:Stream:Replace>, turbo:before-fetch-request. Also trigger when the user asks "how to update part of the page without reload", "how to make navigation feel like SPA", "how to lazy-load a section", "how to do inline editing", "how to push real-time updates from server", "how to use Mercure with Turbo". Do NOT trigger for client-side JS behavior (use stimulus), server-rendered reactive components (use live-component), or reusable static UI (use twig-component).
Browses, installs, configures, and manages plugins from the uni-app plugin market (ext.dcloud.net.cn) including component plugins, API plugins, and template plugins with dependency handling. Use when the user needs to find and install uni-app plugins, configure plugin settings, manage plugin dependencies, or integrate third-party components.
Unirest-Java 3.x HTTP client library for Java 8+. Use when making HTTP requests (GET/POST/PUT/DELETE), building REST API clients, handling JSON responses, file uploads/downloads, async requests, mocking HTTP calls for testing, configuring proxies, or caching responses. Covers Unirest 3.x (Apache HttpClient based, default GSON included, kong.unirest package) with object mapping, request/response interceptors, and migration guidance.
Unirest-Java 4.x HTTP client library for Java 11+. Use when making HTTP requests (GET/POST/PUT/DELETE), building REST API clients, handling JSON responses, file uploads/downloads, async requests, Server-Sent Events (SSE), mocking HTTP calls for testing, configuring proxies, or caching responses. Covers Unirest 4.x (requires Java 11+, modular dependencies, kong.unirest.core package) with GSON/Jackson object mapping, request/response interceptors, and migration from Unirest 3.x.
Unity async and coroutine correctness patterns. Catches common mistakes with Awaitable double-await, missing cancellation tokens, thread context after BackgroundThreadAsync, coroutine error swallowing, batch mode WaitForEndOfFrame, and Addressables handle leaks. PATTERN format: WHEN/WRONG/RIGHT/GOTCHA. Based on Unity 6.3 LTS documentation.
Unity game loop and progression design-to-code translation. Core loop scaffolding, session lifecycle, win/lose condition architecture, meta loop hooks, tunable difficulty, pacing & encounter timing. DESIGN INTENT format: INTENT/WRONG/RIGHT/SCAFFOLD/DESIGN HOOK. Based on Unity 6.3 LTS.
Unity New Input System correctness patterns. Catches common mistakes with action reading (triggered vs IsPressed vs WasPressedThisFrame), action map switching, rebinding persistence, InputValue lifetime, PassThrough vs Value, local multiplayer device assignment, and control scheme auto-switching. PATTERN format: WHEN/WRONG/RIGHT/GOTCHA. Based on Unity 6.3 LTS.
Updates README.md and README.zh-CN.md to reflect the project's current state. Use this skill whenever the user asks to "update the README", "sync the docs", "update documentation", "reflect latest changes in README", or wants both the English and Chinese READMEs to match the current project.
Evaluates market bubble risk through quantitative, data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when the user asks about bubble risk, valuation concerns, or profit-taking timing.
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows, or when the user asks for a motion collage or a scrapbook-style tribute. Triggers: "vox video", "collage video", "motion collage", "paper collage explainer", "make a collage ad", "turn this topic into a collage video".
Triage inbound vulnerability reports - GitHub Advisories (GHSA/CVE), bug bounty submissions, HackerOne/Bugcrowd/Intigriti exports, or a researcher's issue - to decide whether a finding is real, by-design, or noise. Reads the report offline, cross-references the project's documented intent and threat model (SECURITY.md, README, code, closed issues), statically audits any PoC without executing it, and emits a structured markdown triage report with a P0-P3 / By-Design severity and a recommended action. Use whenever the user asks to triage, assess, or score a vulnerability report, advisory, CVE, GHSA, or bug bounty submission, or asks "is this a real finding or by-design?".
Describes and safely edits the vvvv gamma .vl XML format, including document structure, IDs, nodes, pins, pads, links, visible help annotations, exact editor pin geometry, Help Browser registration, and human-preserving layout. Use when generating, parsing, validating, or modifying .vl files programmatically.
Web search and content extraction using ddgs (multi-engine metasearch). No API keys required. Use when: searching documentation, facts, current information, news, fetching web content. Triggers: search the web, look up, find information, web search, news search, fetch page.
Use when something moves in a three.js or React Three Fiber scene: rigs, clips, blending, retargeting, morph targets, crowds. NOT for scroll or UI motion (sheleg-design), rendered video (hyperframes) or Unity/Unreal. Opt out: no web3d, без web3d. Triggers - "AnimationMixer", "анимируй персонажа".
Use when building or fixing a realtime 3D web scene in three.js or React Three Fiber: WebGPU with WebGL2 fallback, TSL. NOT for page heroes (sheleg-design), assets (web3d-assets), animation (web3d-animation) or Quest (xr-dev). Opt out: no web3d, без web3d. Triggers - "3D-сцена тормозит".
Browser automation toolkit using Playwright MCP for testing web applications. Use when asked to navigate pages, click elements, fill forms, take screenshots, verify UI components, check console logs, debug frontend issues, or validate responsive design. Supports live browser interaction and accessibility snapshots.
Writing optimized, secure, multi-stage Dockerfiles with language-specific patterns (Python, Node.js, Go, Rust), BuildKit features, and distroless images. Use when containerizing applications, optimizing existing Dockerfiles, or reducing image sizes.
Quickly build WeChat automation bot applications. Use this skill when the user wants to create a WeChat bot, listen for WeChat messages, auto-reply, handle WeChat group messages, send WeChat messages, post to Moments, fetch Moments content, or has any need related to WeChat automation. Supports message listening, auto-reply, group management, friend management, Moments operations, full message listening, and more.
Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.
Use when an Agent controls Xiaomi Home devices through xgg cloud or authors and debugs Central Hub Geek Edition rules, including offline dynamic lighting formulas, Mi Home QR authorization, automatic gateway login, cloud/local verification, household habit learning, all 25 cards plus nop, event/state semantics, variables, logs, and backups
Use when marketing numbers look bad and the user needs to know WHY — layered root-cause diagnosis across tracking, delivery, creative, landing page, offer, and audience quality, 5-Whys, regional benchmarks for US, EU, SEA, and LATAM, and a 48-hour action plan. Covers dropshipping ROAS and BE-ROAS. Trigger on 'why is CPA so high', 'my ads are not converting', 'ROAS dropped', 'we are burning budget', 'performance is bad this month', 'diagnose the funnel'. Also use when the user pastes a screenshot of numbers with no question attached. Not for — full account configuration audit, see `21-ads-audit-global`; writing a report someone else reads, see `07-marketing-report-global`; turning a raw export into insight, see `13-data-analysis-global`
Map how a product or feature works across the full spectrum of human ability — not just 'can use' and 'can't use'. Use when planning accessibility coverage, identifying gaps, or communicating accessibility scope to stakeholders. Triggers on: ability spectrum, range of users, who can use this, who can't use this, accessibility coverage, accessibility scope, ability range, spectrum of needs.
Use this skill whenever the user wants detailed English prompts for AI image tools (NanoBanana / Gemini / DALL-E / Midjourney) to produce top-conference-quality academic figures — including framework diagrams, network architecture diagrams, pipeline flowcharts, module detail diagrams, comparison/ablation figures, and data pattern grids — especially when the user says "论文配图提示词", "生成论文配图", "学术论文生图", "架构图提示词", "框架图提示词", "顶会风格配图", "CVPR 风格图", "NeurIPS 风格图", "paper figure prompt", "academic diagram prompt", or provides a LaTeX/PDF/Word paper and asks for figure prompts. If the user has not specified a color scheme, present the 8 preset palette options and color tool links before generating any prompt.
Track and manage accessibility debt — known accessibility issues that have been deferred. Use when managing a backlog of accessibility issues, planning remediation, or when accessibility problems are accumulating faster than they're being fixed. Triggers on: accessibility debt, tech debt, known issues, backlog, deferred, we'll fix it later, remediation, accessibility backlog, accumulating issues, regression.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.