Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis
Discover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation.
Run LLMs and AI models on Cloudflare's global GPU network with Workers AI. Includes Llama, Flux image generation, BGE embeddings, and streaming support with AI Gateway for caching and logging. Use when: implementing LLM inference, generating images with Flux/Stable Diffusion, building RAG with embeddings, streaming AI responses, using AI Gateway for cost tracking, or troubleshooting AI_ERROR, rate limits, model not found, token limits, or neurons exceeded. Keywords: workers ai, cloudflare ai, ai bindings, llm workers, @cf/meta/llama, workers ai models, ai inference, cloudflare llm, ai streaming, text generation ai, ai embeddings, image generation ai, workers ai rag, ai gateway, llama workers, flux image generation, stable diffusion workers, vision models ai, ai chat completion, AI_ERROR, rate limit ai, model not found, token limit exceeded, neurons exceeded, ai quota exceeded, streaming failed, model unavailable, workers ai hono, ai gateway workers, vercel ai sdk workers, openai compatible workers, workers ai vectorize
Use when the user asks to review code, review changes, review a commit, review a PR, audit code quality, check for security issues, or generate a code review report. Trigger on phrases like "review my changes", "코드 리뷰", "check my code", "review the last commit", "what do you think of this diff", "compare branches", "code audit", "HTML 리뷰 보고서", "styled review report", "/code-review", or "$code-review" — even if they don't say "code review" explicitly. Produces severity-tagged findings as a Markdown report plus a self-contained bilingual HTML report under `.reviews/`, opened in a browser. For a Markdown-only artifact use `code-review-md`.
Generate a DeepWiki-style structured wiki for any codebase to accelerate developer onboarding. Use this skill whenever a user wants to understand, document, or onboard into an unfamiliar repository — including requests like 'explain this codebase', 'generate documentation for this repo', 'help me understand this project', 'create an onboarding guide', 'map out the architecture', or 'how does this codebase work'. Also trigger when a user provides a repo URL or file tree and asks for analysis, or when onboarding new team members into existing codebases. Even if the user doesn't say 'wiki' or 'onboarding', trigger this skill if they want a structured understanding of a codebase.
The Checkout — payment-only mode (integrating Checkout for payments while owning the rest of the flow), full hosted checkout (checkoutFlow), widget integration via @commercetools/checkout-browser-sdk, configuration, PSP connector setup (Stripe, Adyen, Mollie), and webhook handling. Use when integrating Checkout (the product) into a storefront or headless app — not for generic cart-to-order patterns (see commercetools-storefront).
Find decision-makers at a specific company using Fiber, Crustdata and PDL people search inside the GooseWorks coworker. Given a company name and target titles, returns a list of contacts with name, title, LinkedIn URL, and location.
Refactor high-complexity React components in Langflow frontend. Use when manual complexity assessment shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexity reduction; avoid for simple/well-structured components, third-party wrappers, or when the user explicitly wants testing without refactoring.
Starts a reviewing-code review of an optional diff target, as a short alias for that skill. Use when the user explicitly invokes cr, optionally followed by a branch, PR, commit range, or pasted diff. Never infer from a plain review request; reviewing-code handles that.
Use this skill when the user asks to create, modify, debug, validate, or scaffold a MoviePilot local plugin. Covers version-aware V3/V2 plugin development, _PluginBase implementations, package.v3.json/package.v2.json/package.json metadata, plugins.v3/plugins.v2/plugins source layout, PLUGIN_LOCAL_REPO_PATHS local plugin sources, plugin APIs, Vuetify JSON forms/pages/dashboards, Vue module federation remote components, get_render_mode, get_sidebar_nav, plugin sidebar pages, get_agent_pets assistant avatars, commands, services, workflow actions, agent tools, and local install/reload flows. Also use for Chinese requests mentioning 编写插件、本地插件源, 插件开发, V3插件, V2插件, 插件市场, 本地安装插件, 插件热加载, 前端联邦, 侧栏入口, Vue插件页面, 助手形象.
Scaffold a new Dart or Flutter project from a Very Good CLI template, covering the flutter_app, dart_package, flutter_package, flutter_plugin, dart_cli, flame_game, and docs_site templates, inferring the right one from what the user wants to build and then installing dependencies. Use when the user says "create a new project", "start a new flutter app", "scaffold a package", "create a new package", "initialize a dart cli", "new flame game", or "generate a plugin". Use it for bare, vague, or under-specified scaffolding requests too — "create a new package for me", "make me a new app", "I need a new project", "set one up" — including ones that name no template, no project name, and no organization, or that only hint at what is being built. Missing or ambiguous details are a reason to use this skill, not a reason to skip it: it asks the clarifying questions and picks the template.
Author, review, or refactor a skill for the SAP Fiori Tools / open-ux-tools ecosystem. Use this skill whenever the user wants to create a new skill, rewrite an existing one, add references, split an oversized SKILL.md, enforce the `sap-fiori-<feature>` naming convention, validate frontmatter, add CAP/RAP samples, declare OData V2 vs V4 requirements, mark a skill as internal (developer-facing) or external (public), or produce a verification checklist — even if the user does not explicitly say "skill". Enforces host-agnostic tooling, canonical fallbacks, explicit scope boundaries, and progressive-disclosure chunking (<500 lines per file).
Discover all URLs on a website without fetching content — fast, low-cost URL inventory via sitemap.xml + link extraction BFS. Use when you need to know which pages exist before deciding what to scrape or crawl: "list all pages", "find URLs on this site", "discover links", "what pages does this site have", "map the site". Step 3 of the crw workflow ladder.
Parse a local or remote FILE (PDF) into markdown or structured JSON with fastCRW. Use when the source is a file on disk — "parse this PDF", "extract text from this document", "read this report", "convert PDF to markdown". Routing rule: URL → use crw-scrape; file on disk → use crw-parse. Step 5 of the crw workflow ladder.
Reconnaissance methods specific to CTF Web challenges. Use when facing a CTF target range and needing to quickly discover attack entry points. Unlike real-world pentest recon — CTF is a single application with intentional clues, and recon should be completed within 2-3 rounds. Covers source code leaks, backup files, hidden paths, and extracting clues from pages
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use this skill whenever the user mentions integrating, installing, or writing code against the Cursor SDK; whenever they say `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; whenever they ask to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or any other code that isn't the Cursor IDE itself; and whenever they want to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors from an SDK agent. Also trigger when a user is wiring Cursor into an automation, writing a bot that runs Cursor, or porting REST `/v1/agents` calls to the SDK, even if they don't explicitly name the package. Use this eagerly rather than answering from memory; the SDK surface evolves and this skill plus its references are the source of truth for the external package
Evaluate whether customer, sales, investor, partner, or product meetings produced real commitment and advancement instead of polite interest. Use when interpreting meeting outcomes, stalled leads, trial requests, letters of intent, preorders, warm intros, case-study offers, unclear next steps, or compliments after a pitch.
Narrow broad customer categories into specific, reachable who-where segments for customer discovery, positioning, traction tests, sales outreach, or SEO personas. Use when feedback is inconsistent, the market is too broad, personas are vague, users request too many different features, or the team does not know where to find target customers.
When the user wants to implement or optimize cycle counting programs, improve inventory accuracy, or design physical inventory processes. Also use when the user mentions "inventory accuracy," "physical inventory," "stock counting," "ABC cycle counting," "perpetual inventory," "inventory reconciliation," or "variance analysis." For inventory optimization, see inventory-optimization. For warehouse operations, see warehouse-design.
Use when designing, planning, implementing, or reviewing data synchronization workflows, ERP imports, incremental syncs, backfills, reconciliation jobs, or scheduled ingestion. Covers source of truth, checkpoints, idempotency, deduplication, retries, repair, evidence, and operational controls. Do not use for one-off pure CRUD code.
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do NOT use for simple lookups, debugging, or questions answerable with 1-2 searches.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".
Design and create a simulation persona for testing an AI agent. Guides through use case selection, voice and language configuration, behavior prompt crafting, and interruption calibration. Use when user says "create a persona", "design a persona", "set up a test persona", "configure simulation persona", or "build a caller profile".
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.