Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build, test, lint, and deploy commands for the Bitwarden Android project. Use when running tests, building APKs/AABs, running lint/detekt, deploying, using fastlane, or discovering codebase structure. Triggered by "run tests", "build", "gradle", "lint", "detekt", "deploy", "fastlane", "assemble", "verify", "coverage".
Fact-check claims and prove completed implementation against direct evidence. Use when claims need validation, cross-examination, or hardening, or completed work needs decisive command proof. Do not use as the owner of broad risk discovery, requirement conformance, or one-sided advocacy.
ByteHouse data asset and lineage analysis Skill. Directly queries system.tables / system.columns via clickhouse-connect to pull table structures, fields, engines and other metadata for a given database, generate a data asset catalog, auto-tag it, and identify lineage relationships and column similarity between Distributed/Local. Use this Skill when the user mentions "ByteHouse data assets", "data asset inventory", "table structure analysis", "lineage analysis", "field analysis", "table engine distribution", "metadata catalog", and the like.
ByteHouse multimodal search skill, supporting vectorized storage and multimodal hybrid retrieval of text, images and video (vector search, text-to-image search, image-to-text search, hybrid keyword + vector search). Use this skill when the user mentions "ByteHouse vector search", "multimodal search", "hybrid search", "text-to-image search", "image-to-image search", "text-to-video search", "multimodal knowledge base", "HNSW / vector index" and similar needs.
Converts and transcodes audio file formats and encoding parameters using Volcengine LAS. Audio format conversion between wav, mp3, flac, m4a, ogg, aac and other audio formats. Adjusts sample rate (resample, downsample, upsample), bit rate (bitrate), channels (mono, stereo, channel mixing), audio compression, and audio quality settings via ffmpeg parameters. Supports TOS cloud storage paths and local file upload. Use this skill when the user wants to convert audio format (wav/mp3/flac/m4a/ogg/aac), transcode or re-encode audio files, adjust audio sample rate, bitrate, channels, compress audio files, resample or downsample audio, prepare audio for downstream tasks, or do any audio preprocessing.
Guides developers through integrating and using Viking SDK, covering installation, authentication, API calls, and troubleshooting for the Viking vector database, knowledge base, and memory store. Use when users need to develop business code with Viking SDK or ask questions about Viking.
Entrypoint for managing Volcengine Flink (based on Apache Flink) workloads. Use it for developing and deploying streaming and batch jobs, diagnosing real-time issues (e.g., backpressure, checkpoint failures, OOM), troubleshooting resources, and performing SRE actions (stop/start/restart/scale/config changes). It intelligently routes requests to four specialized sub-skills and leverages flink-mcp for tool execution.
Upload finalized emails for sequencing and sending. Maps fields to lead schema, creates or finds campaigns, uploads leads with dedup, and provides a pre-send verification checklist. Triggers on: "upload to instantly", "run instantly", "send emails", "instantly campaign", "push to instantly", "start campaign", "load into instantly".
Turns a finished client project into a publishable case study in the canonical 12-section Case Study Kit structure: SME interview questionnaire → data collection → result-first narrative (snapshot → 3-type Challenge → 1:1 Solution → before→after Results → testimonial → CTA → SEO), plus a designer visual brief and a pre-launch checklist. Also outputs 3 derivative formats (website page, one-pager PDF outline, LinkedIn handoff). Built for B2B service companies (agencies, outsourcing, consulting). Use when the user says: "напиши кейс", "зроби case study", "оформи проєкт у кейс", "case study from this project", "перепиши кейс", "у нас є результат — треба кейс", or pastes project notes / a call transcript / an old case and asks to turn it into a proper case study. NOT for collecting testimonials or reviews (that is a separate outreach ask) and NOT for writing LinkedIn posts from scratch (use linkedin-post-writing; this skill only hands off a post-ready summary).
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output"
Applies Code Complete's defensive programming rules: barricade design, assertion vs error-handling selection, input validation policy, and correctness-vs-robustness strategy for the current context. For hardening code at trust boundaries; not for diagnosing an active failure (use cc-debugging) or post-completion verification (use aposd-verifying-correctness).
Inject structured reasoning blocks into prompts to encourage step-by-step thinking. Use when tasks require complex problem-solving, multi-step reasoning, planning, analysis, or when you need the model to show its work and reflect on decisions before providing answers.
Create, edit, and deliver editable chart cards in Feishu Docs when preparing reports. Supports 30+ built-in chart types, including bar/column (stacked, grouped, percentage, overlapping comparison), line, area, scatter/bubble, dual-axis, pie/doughnut, rose, radar, funnel, word cloud, Sankey, heatmap, Treemap/Sunburst, as well as business charts such as waterfall/bridge, Mekko, bullet, dumbbell, butterfly, and small-multiple panels. Chart types, annotations, and editing capabilities broadly match ThinkCell. By default, follows MBB (McKinsey/BCG/Bain) consulting-style charting standards and offers report-grade analytical annotations such as difference labels (total, hierarchical, compound growth rate), trendlines, reference lines/regions, and highlight coloring. Supports connecting to Feishu Sheet/Base/Fengshen data sources and keeping them synced; recreating charts from reference images; creating new Feishu Docx documents or inserting/replacing Chart Assistant cards in existing documents; exporting transparent-background PNGs and inserting them into Feishu Docs as selected by the user; and explaining and validating Chart Assistant configurations. Use whenever the user explicitly mentions Chart Assistant, editable charts or configurations, built-in Chart Assistant templates or cards, data-source syncing, turning Fengshen or Feishu Sheet/Base links into editable charts, or requests MBB/consulting-style charts or recreation from a reference image—even if they do not mention the skill name. Do not take over ordinary requests like “make a chart” or “draw a trend chart” unless they require the product capabilities above; do not trigger the chart-creation workflow when only a textual explanation is requested and no chart is to be created
PERSONAL APP ARCHITECT - Strategic development orchestrator for personal productivity applications. Analyzes project context, makes architectural decisions for single-developer projects, delegates to specialized skills, and ensures alignment between user experience goals and technical implementation. Optimized for personal apps targeting 10-100 users.
Vision-driven browser automation using Midscene Bridge mode. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. This mode connects to the user's desktop Chrome browser via the Midscene Chrome Extension, preserving cookies, sessions, and login state. Use this skill when the user wants to: - Browse, navigate, or open web pages in the user's own Chrome browser - Interact with pages that require login sessions, cookies, or existing browser state - Scrape, extract, or collect data from websites using the user's real browser - Fill out forms, click buttons, or interact with web elements - Verify, validate, or test frontend UI behavior - Take screenshots of web pages - Automate multi-step web workflows - Check website content or appearance Powered by Midscene.js (https://midscenejs.com)
End-to-end Chrome security backport for an Electron release branch. Given a Chrome Releases blog URL and a branch (e.g. 41-x-y), determines which CVE fixes are missing from the *actual synced source*, writes the cherry-pick patches locally, validates them with `e sync --3` + `lint --patches`, then pushes a single PR. Use when asked to backport a Chrome security release to N-x-y, "is CVE-X already in N-x-y?", or to produce/validate the cherry-pick set for a release branch.
Enable CircleCI Smarter Testing features (test impact analysis, dynamic test splitting, auto-rerun failed tests) on top of an existing testsuite, driven by `circleci testsuite doctor`. Use for test impact analysis, dynamic test splitting, auto-rerun, or "smarter testing". Requires `.circleci/test-suites.yml` to already exist — if it doesn't, use the circleci-testsuite skill first.
Comprehensive knowledge for using the Bash tool in Claude Code effectively. This skill should be used when orchestrating CLI tools, configuring hooks, setting up automation workflows, managing git operations, handling multi-command patterns, or encountering Bash tool errors. Covers: PreToolUse hooks, command chaining patterns, git workflow automation, CLI tool integration, custom commands (.claude/commands/), security configurations, allowlisting, session persistence, output handling, error prevention, and troubleshooting common issues. Use when: setting up Claude Code hooks, configuring bash permissions, creating custom commands, automating git workflows, orchestrating multiple CLI tools, debugging bash command failures, implementing security guards, logging command execution, or preventing dangerous operations.
Rewrite UX, product, research, handoff, ticket, or engineering-facing content so it reads like a capable human practitioner wrote it. Use when generated or existing content is bloated, robotic, unclear, over-structured, audience-blind, or sounds like AI while preserving meaning, evidence strength, and uncertainty.
Clerk auth with API version 2025-11-10 breaking changes (billing endpoints, payment_source→payment_method), Next.js v6 async auth(), PKCE for custom OAuth, credential stuffing defense. Use when: troubleshooting "Missing Clerk Secret Key", JWKS errors, authorizedParties CSRF, JWT size limits (1.2KB), 431 header errors (Vite dev mode), or testing with 424242 OTP.
Build stateful Durable Objects for real-time apps, WebSocket servers, coordination, and persistent state. Use when: implementing chat rooms, multiplayer games, rate limiting, session management, WebSocket hibernation, or troubleshooting class export, migration, WebSocket state loss, or binding errors.
Production-tested patterns for wiring a React frontend to a Cloudflare Workers + Hono backend with Clerk authentication and D1, including an API client that attaches auth tokens automatically, a ProtectedRoute auth gate with loading states, CORS middleware for dev and production, Clerk JWT verification middleware, wrangler.jsonc bindings, .dev.vars environment variables, and @cloudflare/vite-plugin config (the Worker and frontend share one dev port, so relative /api URLs are correct). Use when connecting frontend to backend, implementing an auth flow, or troubleshooting CORS errors, 401 Unauthorized responses, auth tokens not passing, race conditions while auth is still loading, environment variable confusion, or D1 connection issues.
Use when researching markets, analyzing competitors, planning customer acquisition, creating marketing content, evaluating channels, building brand positioning, or understanding customer sentiment. Dispatched by CEO or invoked directly for marketing questions.
Generate standardized CNC setup sheets for MNMUK machine shop. Covers DMG MORI mills/lathes, CITIZEN Swiss, MITSUBISHI EDM, and Haas machines. USE WHEN user says 'setup sheet', 'create setup', 'job setup', 'machine setup', 'tooling list', 'fixture setup', or 'new job' for any CNC operation.
Development assistant for the cross-platform 2D/3D game engines Cocos Creator 3.8.x and COCOS 4. Use for writing and debugging TypeScript components, node and component systems, event systems, Tween/Animation, physics and collisions, UI (Label/Sprite/Button/Widget/Layout), asset loading and AssetBundle, scene management, performance and DrawCall optimization, and publishing to platforms such as WeChat Mini Games, Douyin Mini Games, H5, iOS, Android, and HarmonyOS Next. Use when the user mentions Cocos, Cocos Creator, Creator 3.8, COCOS 4, cocos-cli, cc modules, .scene/.prefab/.meta files, @ccclass/@property decorators, mini-game publishing, Spine animation, or game engine performance.
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a module diagram from source code.
Python coding standards and best practices covering error handling, performance optimization, async patterns, SOLID design principles, documentation, data validation, and object-oriented programming. Use when writing, reviewing, or refactoring Python code, or when the user asks about Python style, design, or best practices
Search and enrich people and companies with Lima Data through the ColdIQ marketplace API. Use when finding work or personal emails, finding phone numbers, enriching a person or company, prospecting contacts by title/seniority/location, Sales-Navigator-style filtering, batch enrichment, LinkedIn-URL lookups, or monitoring people/companies for changes. Triggers on "find email", "work email", "personal email", "find phone", "enrich person", "enrich company", "prospect people", "prospect companies", "search people", "search companies", "batch enrich", "find people at company", "LinkedIn lookup", "Sales Navigator list". Do NOT use for sending campaigns (see instantly-api / emailbison), Apollo-specific filter semantics (see apollo-search), pure list dedup (see list-dedup), or buying-signal discovery (see signal-detection).
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.