Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to “open a website”, “fill out a form”, “click a button”, “take a screenshot”, “scrape data from a page”, “test this web app”, “login to a site”, “automate browser actions”, or any task requiring programmatic web interaction.
Create custom agents for Claude Code including YAML frontmatter, system prompts, tool restrictions, and discovery optimization. Use when creating, building, or designing agents, or when asked about agent creation, subagent configuration, Task tool delegation, or agent best practices.
AGENTS.md / CLAUDE.md best-practices advisor. For users asking about agents markdown, AGENTS.md, CLAUDE.md, Claude Code memory, or the format, structure, and best practices of AI coding agent instruction files; also for reviewing, diagnosing, rewriting, optimizing, or creating from scratch agent instruction files such as AGENTS.md, CLAUDE.md, CLAUDE.local.md, and .claude/rules. Not for general README writing, unless the goal is to give an AI coding agent project context.
Add persistent memory to AI coding agents — file-based, vector, and semantic search memory systems that survive between sessions. Use when a user asks to "remember this", "add memory to my agent", "persist context between sessions", "build a knowledge base for my agent", "set up agent memory", or "make my AI remember things". Covers file-based memory (MEMORY.md), SQLite with embeddings, vector databases (ChromaDB, Pinecone), semantic search, memory consolidation, and automatic context injection.
A security testing methodology for AI Agent systems. Triggers when the target system uses AI Agents for tool invocation, multi-agent collaboration, or autonomous decision-making. Covers the OWASP Agentic AI Security Top 10 (ASI01-ASI10): goal hijacking, tool misuse, identity and privileges, supply chain, code execution, memory poisoning, multi-agent communication, cascading failures, human-agent trust exploitation, and rogue agents.
Provision dedicated AI agents on AgentBox via x402 payment ($5 USDC on Solana). Use when creating cloud instances running OpenClaw AI gateways with HTTPS and web terminal. Requires Node.js and a Solana wallet.json with USDC funds. Covers: provisioning new instances, polling status, interacting via OpenAI-compatible chat completions, extending, and listing instances.
Design agentic workflows, AI agent operating loops, delegation patterns, human gates, tool boundaries, handoffs, evals, memory, review checkpoints, failure recovery, observability, and autonomy levels for product, engineering, research, support, marketing, operations, and skill-factory work. Use when creating repeatable workflows for AI agents or improving multi-step agent execution quality.
Create, update, reduce, or verify repository-scoped AGENTS.md from repository facts, including inherited and nested instructions, and keep a CLAUDE.md mirror (symlink, or an equal copy where symlinks are unavailable) beside every managed file. Use for agent instructions, not README.md or CONTRIBUTING.md. Russian discovery terms: инструкции агентам.
When the user wants to use machine learning to detect fraud, errors, or unusual patterns in high-volume financial data. Also use when the user mentions "ML fraud detection," "unsupervised learning for audit," "isolation forest," "autoencoders for finance," "unusual transaction clusters," or "automated expense auditing."
Mandatory coding discipline rules that prevent common AI coding anti-patterns. MUST be loaded for ALL code writing, editing, reviewing, bug fixing, and testing tasks. Trigger on: writing code, editing code, fixing bugs, writing tests, implementing features, refactoring, code review, creating functions, adding error handling, debugging. This skill enforces fail-fast principles, proper error propagation, meaningful tests, and disciplined debugging workflows. Always active when Claude writes or modifies code.
Expert in applying AI to education - AI tutors, personalized learning paths, content generation, automated assessments, and adaptive learning systems. Covers practical implementation of AI to enhance (not replace) human instruction. Use when "ai tutor, ai for learning, personalized learning, adaptive learning, ai assessment, generate course content, ai education, " mentioned.
Generate professional AI product photography and commercial images. Models: FLUX, Imagen 3, Grok, Seedream for product shots, lifestyle images, mockups. Capabilities: studio lighting, lifestyle scenes, packaging, e-commerce photos. Use for: e-commerce, Amazon listings, Shopify, marketing, advertising, mockups. Triggers: product photography, product shot, commercial photography, e-commerce images, amazon product photo, shopify images, product mockup, studio product shot, lifestyle product image, advertising photo, packshot, product render, product image ai
Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: images, videos, reels, shorts, thumbnails, captions, hashtags. Tools: FLUX, Veo, Seedance, Wan, Kokoro TTS, Claude for copywriting. Use for: content creators, social media managers, influencers, brands. Triggers: social media content, tiktok, instagram reels, youtube shorts, twitter post, content creator, ai influencer, social content, reels, shorts, viral content, thumbnail generator, caption generator, hashtag generator, ugc content
Design, redesign, build, audit and validate distinctive production websites with cinematic scroll reveals, product films, burst or exploded-view effects, reference-led design systems, purposeful motion and multi-pass refinement. Use for landing pages, product sites, portfolios, interactive storytelling, premium or immersive web experiences, scroll-controlled product inspection, assembly or disassembly sequences, camera moves, image/video-led recreation, hero refinement, motion graphics, and anti-generic visual polish in Astro, React, Next.js, Vue, Svelte or static HTML/CSS. Infer cinematic intent from the requested experience or reference; the user does not need to say "wow" or name a tool.
Implement Statistical Process Control charts to monitor production process stability. Use this skill when the user needs to detect process shifts, set control limits, or distinguish common cause from special cause variation — even if they say 'process monitoring', 'control chart', or 'is our process in control'.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Use when the user needs to generate a log collection configuration file (OpenTelemetry Collector or Elastic Beats / Filebeat) that writes logs to Alibaba Cloud Elasticsearch or self-managed Elasticsearch. Covers file logs, log API ingestion (OTLP / HTTP webhook), and Kafka log topics. Also matches natural requests such as: write a filebeat.yml, generate an otelcol config, send logs to ES, collect nginx or Java application logs to Elasticsearch, or sync Kafka logs to ES. Always output one configuration file targeting Elasticsearch; never mix technology stacks or emit non-ES outputs.
This skill should be used when the user asks about "film pitch", "treatment writing", "pitch deck", "lookbook", "mood board", "film proposal", "funding application", "act as a film pitch developer", "film pitch mode", "pitch package", "film financing", "producer pitch", "story treatment", "concept development", "film grant application", or needs expertise in film treatments, pitch packages, lookbooks, mood boards, and funding proposals for film projects. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
This skill should be used when the user asks about "pre-production", "shot list", "storyboard", "shooting schedule", "call sheet", "script breakdown", "scene breakdown", "production planning", "act as a pre-production planner", "pre-production mode", "location scouting", "crew planning", "shooting day schedule", "camera setup list", or needs expertise in pre-production planning, shot design, script breakdowns, and shooting logistics. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
This skill should be used when the user asks about "VFX", "visual effects", "compositing", "green screen", "chroma key", "After Effects", "Nuke", "CGI", "motion tracking", "rotoscoping", "act as a VFX supervisor", "VFX mode", "visual effects pipeline", "matte painting", "particle effects", "3D integration", "VFX breakdown", or needs expertise in compositing workflows, visual effects planning, Nuke/After Effects pipelines, and CGI integration. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
This skill should be used when the user asks about "soundtrack", "film scoring", "background music", "scene music", "mood music", "instrumental generation", "content scoring", "video music", "podcast music", "ambient music", "transition music", "stinger", "musical identity", "music licensing", "soundtrack library", "act as a soundtrack composer", "soundtrack composer mode", "score a scene", "music for video", "emotional music", "cinematic score", "Suno instrumental", "MIDI export for scoring", "negative prompt scoring", "section editing cue", "sample to song", "Suno Studio", "re-score segment", "temp track", "loops", or needs expertise in creating instrumental music and soundtracks for visual content using Suno. Part of the AlterLab FC Skills collection (GenAI pack).
This skill should be used when the user asks about "video essay", "visual essay", "narration script", "essay film", "argument-driven editing", "video analysis", "act as a video essay creator", "video essay mode", "YouTube essay", "voiceover script", "visual argument", "essay film structure", "film criticism video", or needs expertise in writing, structuring, and producing argument-driven video essays. Part of the AlterLab FC Skills collection (New Media & Communication department).
This skill should be used when the user asks about "literature review", "systematic review", "source evaluation", "annotated bibliography", "literature mapping", "research gap", "database searching", "Google Scholar", "JSTOR", "Scopus", "Web of Science", "act as a literature reviewer", "literature reviewer mode", "finding sources", "academic sources", "peer-reviewed articles", "citation management", "reference list", "literature search strategy", "inclusion criteria", "exclusion criteria", "PRISMA", "thematic analysis of literature", "source credibility", "research synthesis", "scoping review", "narrative review", "meta-analysis planning", "literature matrix", or needs expertise in finding, evaluating, organizing, and synthesizing academic literature. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
This skill should be used when the user asks about "thesis structure", "dissertation", "thesis writing", "chapter organization", "research proposal", "thesis outline", "defense preparation", "thesis defense", "committee management", "thesis timeline", "writing productivity", "argument architecture", "thesis introduction", "literature review structure", "methodology chapter", "findings chapter", "discussion chapter", "thesis conclusion", "act as a thesis architect", "thesis architect mode", "dissertation proposal", "thesis pipeline", "academic writing structure", "thesis formatting", "thesis revision", "writing schedule", "thesis advisor", "research proposal writing", "thesis planning", "chapter drafting", "thesis feedback", "defense slides", "viva preparation", or needs expertise in structuring, planning, writing, and defending a thesis or dissertation. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
This skill should be used when the user asks about "photo editing", "image editing", "retouching", "photo retouching", "photo essay", "photo curation", "AI photo editing", "color grading photography", "Lightroom", "Photoshop", "image compositing", "photo narrative", "editorial photography", "act as a photo editor", "photo editor mode", "image correction", "exposure adjustment", "white balance", "skin retouching", "photo story", "picture editing", "batch editing photos", "RAW processing", "photo selection", "editing ethics", "portrait retouching", "product photography editing", or needs expertise in image editing direction, retouching briefs, photo essay curation, and AI-assisted editing. Part of the AlterLab FC Skills collection (VCD department).
This skill should be used when the user asks about "typography", "type design", "font selection", "font pairing", "typographic hierarchy", "typographic grid", "type scale", "readability", "legibility", "kerning", "leading", "tracking", "typeface classification", "serif vs sans-serif", "modular scale", "act as a typographer", "typographer mode", "type system", "web typography", "variable fonts", "responsive typography", "paragraph spacing", "baseline grid", or needs expertise in type selection, typographic hierarchy design, font pairing strategies, and readability optimization. Part of the AlterLab FC Skills collection (VCD department).
Amap Maps API (via MCP). Geocoding (address↔coordinates), IP location, weather, POI search, route planning (cycling/walking/driving/transit), distance measurement. Triggers: '高德', 'amap', '地理编码', 'geocoding', '经纬度', 'POI', '路线规划', '导航'. NOT for: Amap JSAPI front-end development (use AMap-Web/amap-skills).
Add CSS animations to HTML elements, React/JSX components, or WordPress PHP templates using Animate.css (v4.1.1). Use this skill whenever the user wants to animate UI elements, add entrance/exit effects, attention-seeker animations, or any CSS-based motion to their markup. Trigger on phrases like "add animation", "animate this", "make it bounce/fade/slide/zoom", "add transitions", "CSS animations", or any request to bring elements to life visually. Works with raw HTML snippets, full HTML files, React JSX, and WordPress PHP templates. Claude picks the most contextually appropriate animation — no guesswork needed from the user.
Use this skill when the user asks to "find CVEs for", "check if my domain is breached", "threat intel on", "OSINT on", "security news about", "attack surface of", "is this IP malicious", "what vulnerabilities affect", "security advisory for", "monitor threats for", "threat actor research", "recent exploits for", "data breach check", "security posture of", "what's the threat landscape for", "investigate [domain/IP/software]", "is [company] exposed", or any request involving vulnerability research, breach detection, threat actor profiling, or security intelligence. Requires Apify CLI or Apify MCP server.
Scaffold a new production application with the full agentic-AI guardrail canon baked in from commit #1: a uniform 7-gate interface (lint, typecheck, test, coverage, build, e2e, audit) on each stack's native runner, strict types, maximal static analysis, coverage thresholds with teeth plus seed tests, pre-commit hooks, hardened CI with optional SonarCloud, supply-chain pinning, and an agent-ready AGENTS.md — every gate verified green before the first commit. Native adapters: Next.js, NestJS, Django, Go, Rust, Spring Boot; a discovery method maps the canon to other stacks. USE FOR: creating or scaffolding a new app, service, or API from scratch; bootstrapping a greenfield repo that AI agents will build in. DO NOT USE FOR: retrofitting an existing codebase or scaffolding a new package into an existing monorepo (both assume repo-root ownership), LLM-safety or content-moderation guardrails, or adding a single tool to an existing project.
Use Apple’s `container` CLI on Apple silicon macOS for Linux containers, OCI image builds, registries, volumes, networks, port forwarding, host access, persistent `container machine` Linux environments, and experimental local Kubernetes clusters. Use this skill whenever the user asks to replace Docker Desktop with Apple Container, run Linux commands on macOS, build/run/inspect Apple containers, debug Apple Container service/network/build failures, use Container Machines, or use `container k8s`.
Guide users through creating, designing, signing, distributing, and updating Apple Wallet passes using the PassKit framework. Use this skill whenever the user mentions Wallet passes, .pkpass files, boarding passes, event tickets, store cards, coupons, loyalty cards, membership cards, NFC passes, or anything related to Apple Wallet integration. Also trigger when the user asks about "Add to Wallet" badges, pass signing certificates, pass updates via push notifications, or barcode/NFC-based redemption flows. Even if the user just says "I want to create a digital ticket" or "loyalty card for my app", this skill applies.
Writing or reviewing code that handles untrusted input, secrets, outbound requests, rendered content, or third-party dependencies — the OWASP Top 10:2025 lens in two modes, writing secure-by-default code and judging the risk a change introduces. Triggers on "is this safe", "secure by default", "harden", "security", "secret", "privacy", "PII", "XSS", "injection", "SSRF", "safe fetch", "access control", or a dependency review. Covers secrets and environment variables, input validation, output encoding, SSRF, access control and data exposure, and supply-chain risk.
Interactively guides the documentation of arc42 Section 7 (Deployment View). Asks about infrastructure, environments, and software-to-hardware mapping before generating C4 PlantUML deployment diagrams and environment comparison tables. Iterates until the user is satisfied.
Interactively guides the documentation of arc42 Section 10 (Quality Requirements). Elaborates quality goals from Section 1.2 into concrete, measurable scenarios grounded in Q42 quality criteria (quality.arc42.org). Coaches against vague metrics and checks coverage against architectural decisions. Iterates until the user is satisfied.
Interactively guides the documentation of arc42 Section 11 (Risks and Technical Debt). Pre-populates candidates from Sections 9 and 10, works through risk categories systematically, and generates a prioritized risk register and debt backlog with mitigation strategies. Iterates until the user is satisfied.
Interactively guides the documentation of arc42 Section 12 (Glossary). Scans other sections for undefined terms, asks about domain vocabulary and ambiguous terminology, and generates a structured glossary with consistent preferred terms. Iterates until the user is satisfied.
Turn artifact photos, artifact descriptions, or existing sketches into a cultural relic drawing workflow that conforms to archaeological report standards, generation prompts, image production execution, and drawing review criteria. Use when Codex needs to create, edit, critique, prompt, or generate cultural relic drawings, artifact report plates, orthographic line drawings, vessel profiles, half-section views, stone tool multi-view drawings, openwork ornament drawings, or black-and-white technical illustrations from photos or descriptions. Triggers include: 文物绘图、考古绘图、器物线图、器物剖面图、半剖面、正投影、文物照片转绘图、器物照片转绘图、cultural relic drawing, archaeological drawing, artifact illustration, orthographic artifact drawing, pottery profile drawing.
Guides architecture decisions about service/module boundaries, system trade-offs, ADRs, data flow, rendering strategy, scaling strategy, API protocols, persistence choices, and code organization. Use when the user asks "how should I structure this", "what's the right approach", or needs a decision that affects multiple modules, teams, deployment boundaries, or future reversibility. Do not use for routine React implementation, PR review, or simple refactors unless the user is making an architectural decision.
Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.
Build a compilable type-level skeleton from a high-level architecture spec before writing any implementation logic. Use when you have an architectural assessment, design doc, or restructuring plan and need to prove the new architecture is sound before migrating code. Also use when asked to "scaffold the new architecture", "create type stubs", "build the shell", "flesh out this spec", "skeleton the modules", or any request to turn architectural intent into verified structure. This skill follows the "Human Builds the Shell" paradigm: types are hard constraints that the compiler enforces, so if the skeleton compiles, the architecture is structurally sound. Especially valuable for large refactors where you don't trust agents to maintain coherence.
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.