Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Expert React specialist mastering React 18+ with modern patterns and ecosystem. Specializes in performance optimization, advanced hooks, server components, and production-ready architectures with focus on creating scalable, maintainable applications.
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent readiness", "agent-ready score", "MCP server card", "agent skills index", "markdown for agents", "content signals", "web bot auth", "agent discovery", "RFC 9727", "RFC 8288", "RFC 9728", "SEP-1649", "WebMCP", "ARD", "ai-catalog", "x402", "UCP", "ACP", or wants to make a website discoverable and usable by AI agents.
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when implementing self-critique and reflection loops; building evaluator-optimizer pipelines for quality-critical generation; creating test-driven code refinement workflows; designing rubric-based or LLM-as-judge evaluation systems; adding iterative improvement to agent outputs (code, reports, analysis); or measuring and improving agent response quality.
Create free Agnes video generation tasks and retrieve video results through Agnes-Video-V2.0, including text-to-video, image-to-video, multi-image video, keyframe animation, async polling, and video download. Use when the user asks for 免费视频, 免费的视频模型, free video API, Agnes video, Agnes-Video-V2.0, text-to-video, image-to-video, keyframes, or wants a free video model Agent skill.
Comprehensive patterns for AI-powered audio generation including text-to-music, voice synthesis, text-to-speech, sound effects, and audio manipulation using MusicGen, Bark, ElevenLabs, and more. Use when "music generation, text to music, AI music, voice cloning, text to speech, TTS API, ElevenLabs, MusicGen, Bark, audio synthesis, sound effects generation, voice synthesis, AudioCraft, " mentioned.
Analyze project and generate or enhance build automation file (Makefile, Taskfile.yml, Justfile, Magefile.go). If a build file already exists, improves it by adding missing targets and best practices. Use when user says "generate makefile", "create taskfile", "add justfile", "setup mage", or "build automation".
Use when verifying that requirements/specs/PRDs and their implementation plans match — before starting work, after a spec or plan update, or when suspecting coverage gaps, scope creep, or design drift between intent and action documents. Needs both documents; not for checking code against a spec.
Diagnoses ClickHouse INSERT performance, batch sizing, part creation patterns and materialized-view overhead on inserts. Use for slow inserts, failed inserts, micro-batching, high part creation rate, Buffer table flushes and data pipeline issues.
Checks ClickHouse system log tables for freshness, TTL, disk footprint, upgrade leftovers and crash records. Use when system tables eat the disk, query_log or part_log has no recent data, retention for system.*_log needs review, or the server appears to have crashed.
Use when creating, repairing, converting, packaging, or verifying app icons for any platform from briefs, references, brand marks, SVG/logo/text assets, generated concepts, or existing icons; use the optional Apple adapter when Icon Composer output is requested
Architecture Decision Records with a four-phase lifecycle (RESEARCH -> DRAFT -> HOLD -> MERGE). Use this skill whenever the user needs to make a technology choice, choose a database, select a framework, define system boundaries, record architectural decisions, review or evaluate an existing ADR, create or update ARCHITECTURE.md, or inventory decision points for a new project. Triggers on: "choose a database", "architecture decision", "ADR", "which technology should we use", "is this ADR ready to merge", "review this architecture decision", "what decisions do we need to make", "tech stack decision", "define system boundaries", "record this decision". Enforces research-before-writing and explicit merge authorization. NOT for: code review (use code-review), implementation decisions within established patterns, or design system choices (use design-system).
Trigger this skill when an AI agent needs to organize legal reasoning results into a complete, self-consistent, persuasive argument structure. Typical trigger scenarios include but are not limited to: - Writing the argumentative sections of legal documents such as legal opinions, statements of agency, defense statements, and statements of defense - Answering complex legal questions raised by users that require multi-step reasoning and presentation of conclusions - Systematically analyzing the focus of a dispute, requiring construction of a complete reasoning path from facts to law to conclusion - Constructing alternative chains of argument when rebutting the opposing party's views - Comprehensively analyzing multiple legal issues, requiring each argument to be logically consistent and mutually non-contradictory - Presenting analytical conclusions in a legal research memorandum. Trigger signal keywords: argument, analysis, reasoning, why, proof, grounds, discussion, presenting a viewpoint, legal analysis
Astro web framework patterns for content-driven sites. Covers content collections with Zod schemas and loaders, island architecture with selective hydration directives, view transitions with ClientRouter, server-side and hybrid rendering modes, server islands, Astro DB with astro:db, middleware with onRequest, and framework integrations (React, Svelte, Vue). Use when building content-driven websites, configuring island hydration strategies, setting up view transitions, choosing between static and server rendering, integrating UI framework components, defining content collection schemas, or adding middleware.
Binding audio analysis data to visual parameters including smoothing, beat detection responses, and frequency-to-visual mappings. Use when creating audio visualizers, music-reactive animations, or any visual effect driven by audio input.
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
Browse and retrieve SCAPI OpenAPI schema specifications. Use this skill whenever the user needs to list available SCAPI APIs, inspect endpoint paths or request/response shapes, explore data models for products or orders, check which fields an API returns, or understand SCAPI versioning. Also use when looking up API details before building an integration -- even if they just say 'what fields does the product API return' or 'show me the SCAPI endpoints'.
Use when defining voxel blocks in RON (`name`, `textures`, `flags`), building a runtime palette mapping `BlockId -> BlockDef`, baking per-block textures into a KTX2 atlas (`ktx2` + `zstd_rust` features), or binding the atlas as `StandardMaterial.base_color_texture` with an `ImageSampler` so meshed quads sample by face index. Generic Bevy 0.20 voxel-data patterns — no game-specific data baked in.
SOLUTIONING GATE — validates cohesion across planning artifacts before any implementation begins. Cross-references PRD (or tech-spec), architecture document, and epics/stories for coverage consistency and missing pieces. Returns a verdict of PASS, CONCERNS, or FAIL with specifics. Does NOT touch code. Use when the user says: - "check if we're ready to build" / "are we ready to implement?" - "validate planning" / "gate check" / "readiness check" - "run the solutioning gate" / "check implementation readiness" - "is the architecture complete?" / "do requirements match architecture?" - "sign off on planning" / "planning done, check it" - "validate PRD against architecture" / "cross-reference planning docs" Intents supported: Validate (primary). Track-adaptive: works for Quick Flow (tech-spec + architecture), BMad Method (PRD + architecture + epics), and Enterprise (all of the above + optional security/DevOps addenda).
Creates a 3D exploded-view animation for a reel. A phone floats against a dark studio backdrop, comes apart layer by layer (glass, screen, frame, board and battery, back), and each part gets a thin leader line and a label. Use when the user runs /breakdown or asks for an exploded view, a “what's inside” teardown, or a labeled 3D breakdown of a device.
Generate camoufox configuration for the `browse` CLI by INTERVIEW, not hand-edited JSON — an AskUserQuestion-guided flow that turns a chosen preset (stealth, fast-scraping, Google-safe, or a fully custom walkthrough) into a valid `browse.json` camoufox section or a named `.browse/camoufox-profiles/<name>.json`, using camelCase keys, merging without clobbering existing fields, and writing proxy credentials to file only. Use to create or tune an anti-detection browse profile before stealth browsing.
Set up and integrate Circle Onramp, the hosted widget that lets end users buy crypto with fiat (bank transfer, debit card, Apple Pay, Google Pay) delivered to their wallet, using App Kit (`@circle-fin/app-kit`, `kit.onramp`) or the standalone Onramp Kit (`@circle-fin/onramp-kit`). Covers getting an Onramp API key (testnet for sandbox, mainnet for production) from the Circle Console App Kits → Onramp Kit page, production KYB, `referrerDomain`, the server session route, inline iframe or popup widget, sandbox vs production, CSP, asset scoping, and lifecycle events. Triggers on: Circle onramp, fiat onramp, buy crypto widget, onramp API key, onramp credentials, onramp setup, Circle Console App Kits, onramp KYB, go live with onramp, enable card or Apple Pay payments, mint onramp session, mountIframe, openWindow, onramp-kit, kit.onramp.
CRITICAL: EXCELLENT at parsing BOTH PDF documents and IMAGES (including LONG SCREENSHOTS, scanned documents, and standard images). Extract structured Markdown content (text, tables, images). MUST use this skill WHENEVER a user wants to parse, read, OCR, or extract content from ANY PDF file, image file, or long screenshot. Also trigger this automatically when users share a local file path, URL, or TOS path pointing to a PDF or image, even if they don't explicitly say 'parse'.
Cavekit specification-driven development methodology — the Hunt lifecycle (Draft → Architect → Build → Inspect → Monitor) and how to apply it. Use when starting a Cavekit project, structuring an existing codebase as kits/plans, or routing between sub-skills.
Comprehensive Cloud Foundry CLI (cf CLI v8) assistant for generating commands, automating app deployments, managing services, and troubleshooting errors. Use this skill whenever the user mentions "cf", "cf cli", "Cloud Foundry", "cf push", "cf login", "cf target", app deployment to CF, service binding, buildpacks, routes, domains, orgs and spaces, manifests, or any task involving the Cloud Foundry command line — even if they just say something like "push my app" or "how do I bind a service". Also trigger when the user asks about scaling apps, managing environment variables in CF, creating user-provided services, rolling deployments, SSH into app containers, or writing CF manifests.
Build or refactor agent-facing CLI tools with non-interactive commands, stable --help and --json contracts, idempotent operations, and --dry-run previews. Use for CLI design, agent-friction refactors, output/exit-code debugging, or automation safety. Do not use for GUI/TUI design, conversational tools, MCP server design, or general API architecture; use api-design-and-evolution for the latter.
Detects framework-specific anti-patterns, convention violations, and idiom misuse across PHP/Laravel, React/Next.js, and Python/Django/FastAPI codebases. Loads framework-specific reference guides and checks against framework conventions. Generates severity-scored findings with copy-pasteable fix prompts. Trigger phrases: "framework review", "framework check", "laravel best practices", "react best practices", "framework audit", "framework-specific review".
Audits code for SOLID principle violations — Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion. Identifies classes and methods that violate these principles and generates fix prompts. Trigger phrases: "SOLID check", "solid review", "SRP violation", "dependency inversion".
Expert in designing and implementing visceral, satisfying combat systems. Masters hitbox/hurtbox design, frame data, combo systems, enemy archetypes, damage feedback, and the invisible craft that makes players feel powerful. Draws from fighting games, character action games (DMC, Bayonetta), and Souls-like design to create combat that is readable, responsive, and endlessly replayable. Use when "combat system, combat design, hitbox, hurtbox, frame data, hitstop, screen shake, input buffer, coyote time, i-frames, invincibility frames, combo system, attack cancel, recovery frames, punishment window, souls-like combat, action game combat, fighting game, damage feedback, enemy design, boss design, attack telegraph, parry system, stamina system, poise system, weapon feel, game feel combat, melee combat, combat juice, combat, action-game, fighting-game, hitbox, frame-data, game-feel, souls-like, character-action, melee, enemy-design, boss-design, combo, parry, i-frames" mentioned.
Identify a domain's real search competitors from shared rankings, then map keyword, content, backlink, and traffic-channel gaps with a prioritised closing plan. Use when the user asks who competes with them in search, which keywords or content they are missing, or how they compare against a named competitor
Use when you need to compare supplied competitor messaging with your approved product facts and find a credible point of difference. Trigger phrases include "how are competitors positioned?", "compare our message to theirs", "where are we different?", "audit these competitor pages", and "what should we not say?". Do not use this to make unverified claims about competitors, copy their language, or write the final brand message in isolation; use agent-reach to collect public sources, positioning-audit to decide your message, and campaign-brief to apply it
Point Cowork at a folder of resumes plus a job description -- screens every candidate against the actual requirements, produces a ranked shortlist with evidence, drafts advance/decline emails, and builds interview kits for the top picks. Pairs with hiring-scorecard for the interview stage.
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.