Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Search scholarly works across arXiv, conferences, journals, and books via OpenAlex. Returns citation counts, reconstructed abstracts, venue, open-access PDF links, and external IDs (arXiv/DOI/PMID). No API key required. Use when the user says "search scholar", "search papers", "find papers with citations", "papers by author", "cross-discipline search", or "papers from <venue>". Complements arxiv-search (preprints-only).
Generate durable, re-runnable validation scripts from testing intent. Supports TypeScript, Python, and Bash with auto-detection, enforces context-optimal PASS/FAIL + /tmp log output, and auto-documents scripts in CLAUDE.md. Triggers on phrases like "turn this into a script", "I want to test/validate X end-to-end", "wrap this in a re-runnable script", or whenever an agent needs durable validation instead of throwaway commands
Generate scroll-stopping viral hook video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants viral content, TikTok hooks, Instagram Reels openers, YouTube Shorts, attention-grabbing video, scroll-stopper, pattern interrupt, or any short-form video designed to maximize retention and views. Triggers on any mention of viral, hook, scroll-stop, retention, views, engagement, short-form, TikTok, Reels, Shorts.
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup.
Optimize a webpage for search engines by analyzing on-page elements, improving technical performance, and implementing structured data for maximum visibility. Use when the user requests seo optimization or provides relevant inputs for this workflow.
Design a single-point rubric with one criterion and open columns for evidence. Use for student self-assessment, peer feedback, teacher formative feedback, or pre-task planning. Works with any learning target, with or without a band system.
Create, update, validate, or reorganize repo-local Agent Skills under .agents/skills, including SKILL.md frontmatter, first-level references, compatibility symlinks, and validation scripts. Use only for skill-tree maintenance, skill taxonomy changes, or agent-guidance validation work.
Generate a comprehensive, structured learning guide for any technical topic or technology. Use this skill whenever a user wants to learn a new technology, programming language, framework, tool, or concept—even if they phrase it casually (e.g., “teach me Rust”, “how do I get started with Kubernetes”, “I want to learn React”, “help me understand GraphQL”, “give me a roadmap for learning Docker”). This skill covers concept identification and categorization, weekly study schedules, local dev setup, concept explanations with examples, exercises, popular libraries, project ideas, and resources. Trigger for any “how do I learn X”, “roadmap for X”, “getting started with X”, “study plan for X”, or “teach me X” request—even if they don't explicitly ask for a guide or roadmap.
Comprehensive guide for developing Telegram Mini Apps with any web framework (React, Vue, Svelte, vanilla JS, etc.). Covers the Telegram Web App SDK, theming, UI components, navigation, data validation, and platform best practices.
Token optimization dashboard with two sections - (1) Workspace file compression for ALL .md files in context, (2) AI model audit that detects current models and suggests cheaper alternatives. Shows "possible savings" until optimizations are applied. Triggers on "optimize tokens", "reduce AI costs", "model audit", "save money on AI".
Official Topview AI creative skill. Generate and edit images, videos, music, speech, talking avatars, product-avatar images, cloned voices, and background-removed assets through the unified host MCP `topview-mcp`. Use for creative generation, board organization, and Topview credit checks. Do not use for Amazon, Shopee, TikTok Shop, or YouTube KOL research; route those requests to the matching Topview ops skill.
Risk Manager. Checks every proposed order against your limits before it can reach the broker and blocks anything over them: blocked tickers, max order size, minimum order, max position percent after the fill, the cash buffer, margin, short sales, options and crypto (off unless allowed), malformed orders, duplicates and a daily order limit. Prints PASS or BLOCK with the reason for each order and records the verdicts so trader-broker only shows an order that passed. Use when the user says "check my orders", "is this safe", "risk check", "does this break my rules", "can I place this", or before /trader-broker, always.
Diagnose and fix ngrok errors and connection problems. Looks up the ERR_NGROK code (or the error message) in ngrok's error docs, then checks the account's live state - endpoints, agents, traffic, limits - to find the specific cause. Covers offline endpoints (ERR_NGROK_3200), upstream connection failures (ERR_NGROK_8012), agent authentication and session limits, Traffic Policy errors, and TLS errors. Use when an ngrok URL returns an error, an agent won't start or stay connected, or the user pastes an ngrok error code or message. Use when the user says "ngrok says endpoint offline", "ERR_NGROK_3200", "my tunnel isn't working", "why is my ngrok URL down", or "what does this ngrok error mean".
Write or revise Turkish text so it sounds natural and human-written. Use when the user asks to “humanize,” “humanize et,” “remove the AI feel,” or “translate into natural Turkish”; requests a check for translation-like phrasing or TDK errors; or needs Turkish blog posts, articles, corporate writing, social media content, or technical documentation.
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, Claude Agent SDK, and TypeSafe. Use for provider-specific TS work; do not use for core-only changes.
A meta skill that teaches AI agents how to discover, install, and use skills from the findskill.md ecosystem. Use when you need to extend capabilities by finding specialized skills, when a user asks to perform tasks that would benefit from specialized skills, or when explicitly asked to find or install skills.
Select, integrate, and operate multi-model video-generation gateways — hosted inference aggregators such as fal.ai, Replicate, and WaveSpeed that expose many third-party video (and video-adjacent audio) models behind one account, one API surface, and one bill. Use when deciding whether to route video generation through a gateway versus a direct model-provider API; when comparing gateways on catalog, async/queue job design, webhooks, pricing, schema discovery, and version pinning; and when operating gateway workloads in production — spend controls, retries, cross-gateway failover, content-safety differences, data retention, and commercial-rights passthrough of the underlying model. Not for direct model-provider APIs, local/self-hosted inference, model training/fine-tuning, or image-only gateway use.
Use when writing an article, newsletter, blog post or long social post that must genuinely be the user's own writing. Triggers on "voiceprint", "write this in my voice", "turn my recording into an article", "cut my transcript down", "make this actually mine", "write from my video". Turns the user's own spoken words into a finished piece by cutting, never by composing.
This skill should be used when the user asks to "create a blueprint", "write a blueprint", "blueprint this feature", "plan this implementation", "make a plan", "create an implementation plan", "design the architecture", "design this feature", "break this down into steps", "plan this refactoring", or "help me plan".
Dependency upgrades: outdated/vulnerable deps planned into semver waves (patch/minor batched, majors gated and changelog-read), applied incrementally with lockfiles regenerated and tests green after each. Runs on green main. Triggers on "absolute upgrade", "upgrade our dependencies", "bump deps", "update packages", "move off the deprecated X", "clear the Dependabot backlog".
Use when implementing, reviewing, or debugging a Gherkin acceptance-test pipeline with mutation testing. Covers parser, JSON IR, generator, runtime, step handlers, test runner, mutator, value mutation rules, execution, result classification, reporting, project layout, conformance, and agent setup. Based on Uncle Bob's Acceptance Pipeline Specification. Trigger even when the user mentions Gherkin parsing, acceptance test generation, mutation testing for acceptance tests, or building a portable test pipeline.
Create accounts for an agent at third-party services with AgentID, using an AgentMail inbox as the agent's identity, and see where each inbox already has an account. Use for ANY request like "create an account at Firecrawl", "sign my agent up for Turso", "get my agent a web search API", "log my agent back in to Firecrawl", "sign in with the auth token this page shows", "which services is this inbox signed up for?", or browsing the AgentID app marketplace. Do not use for sending or reading mail (agentmail-send-email, agentmail-check-email), inbox lifecycle on its own (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
When the user wants to build programmatic SEO with AI, create competitor alternative pages, optimize for AI Overviews, or scale content production. Also use when the user mentions 'SEO,' 'programmatic SEO,' 'AI content,' 'competitor alternative pages,' 'AI Overviews,' 'search optimization,' 'DataForSEO,' 'content at scale,' 'keyword strategy,' or 'organic traffic.' This skill covers AI-powered SEO strategy from keyword research through programmatic page generation.
Alibaba Cloud Milvus full-stack Skill for two planes: control-plane instance management via aliyun CLI, and data-plane Milvus operations via pymilvus. Use when users want to create, inspect, scale, configure, network-enable, or whitelist Alibaba Cloud Milvus instances; or connect to Milvus and perform collection management, vector insert/search, hybrid search, full-text search, index management, partition/database management, or RBAC with Python.
Provide Alibaba Cloud SLS / Aliyun Log SDK installation, quickstart, usage guidance, and SDK selection advice across languages. Use when users ask how to install or use SLS SDKs, choose an SDK for a scenario, write logs, consume logs, query logs, or integrate application logs with Producer, Consumer, or logging framework Appender libraries.
Two modes: ① Direct conversation: When the user says “Talk with Musk,” “Analyze this product from Jobs’ perspective,” or “What would Confucius think about this?”, immediately activate the corresponding person’s cognitive operating system and respond as that person, without requiring any Python environment. ② Distill a new person: When the user says “create a skill,” “distill XX,” “turn these materials into a skill,” “analyze this video and generate a skill,” or uploads a file asking to extract someone’s thinking patterns, run the distillation pipeline to generate a new SKILL.md. Trigger keywords: talk with XX, from XX’s perspective, what does XX think, create a skill, distill, generate a skill, extract thinking patterns
API testing patterns with supertest, MSW, and Vitest. Covers integration testing for REST APIs, HTTP request mocking with Mock Service Worker v2, response assertions, schema validation, test organization, and framework-specific patterns for Express, Fastify, and Hono. Use when writing integration tests for REST APIs, mocking HTTP requests, or testing API endpoints. Use for api-test, supertest, msw, mock-service-worker, integration-test, http-mock, endpoint-test, request-test.
Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel. Use when the user asks "why are my imports failing?", "what's broken with my sources?", "why is my warehouse data stale?", or wants a one-shot triage of source/sync health before deciding where to dig in. Produces a prioritized report grouped by severity, with recommended next steps. For materialized-view health use `auditing-warehouse-view-health`; for a single failing sync use `diagnosing-failed-warehouse-syncs`.
Implement background state persistence for Even Hub G2 plugins — automatically analyzes existing plugin code, identifies state that needs to survive background/foreground transitions, and inserts setBackgroundState + onBackgroundRestore calls. Use when a plugin loses state after the phone goes to the background and returns.
Use when creating or changing a Bagisto admin theme — a theme package, admin layouts, Blade component overrides, or the Vite asset pipeline for the admin panel. Trigger phrases include "admin theme", "admin layout", "admin panel styling", "theme package", "vite", "tailwind", "publish views", "custom layout".
Use when a task requires interacting with a website beyond just reading it — clicking elements, filling forms, submitting data, navigating through multi-step flows, taking screenshots, or any workflow where the user needs a real browser with actions like click, type, scroll, or select. Also use for managing browser bookmarks, history, or tabs. Trigger whenever the user mentions browseros, browseros-cli, or BrowserOS. Do NOT use when simply fetching or reading page content would suffice — use curl, fetch, or WebFetch for that instead.
Break down an A-share company's business model into segments, customers, products, regions, projects, and order pipeline quality. Use this skill when testing whether reported growth is supported by real delivery, healthy customers, and cash collection. All outputs must include accessible source links.
Use this skill when the business, not developers, should own decision rules—eligibility, risk, routing, discounts—and change them without a code release or audit which rule fired, even if DMN or decision tables aren't mentioned. Authors and validates DMN decision tables for Camunda 8. Not for requests to write a function or script in a programming language
Use when maintaining legacy Canvas theme-global regions, region JSON, or a project-level Region-based layout. Also consult for existing region-based site chrome. Region APIs are deprecated; new integrations should use page variants and composed page trees instead.
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.
