Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.
Route `/gemini ...` requests to the Cursor headless CLI for one-shot autonomous execution. Use when the user explicitly invokes `/gemini` or asks to hand a task off to Cursor agent. Preserves the prompt verbatim, runs in headless print mode, and returns Cursor's output.
Use Google Gemini CLI to answer questions about code, analyze files, or perform codebase exploration. Invoke this skill when the user asks to use Gemini, wants a second opinion from another AI, or wants to compare Claude's answer with Gemini's response.
Analyzes the user's genetic data from a VCF file. Use when the user asks about their genetics, inherited traits, predispositions, substance metabolism (caffeine, alcohol, medications), athletic ability, disease risks, or gene-based nutrition.
NCBI GEO access via GEOparse and E-utilities. Search by keyword/organism/platform, download GSE series matrices, parse GPL annotations, extract GSM metadata, load expression matrices into pandas. For single-cell use cellxgene-census; for multi-DB access use gget-genomic-databases.
Swiss-German translator for brand/UI and legal text — trained on real translation patterns from 12+ top brands (Swisscom, UBS, On Running, Logitech, IKEA, Stripe, Notion, Slack, Apple, Shopify, BMW, Vercel). Translates and validates i18n JSON or plain text from English to Swiss-formal German (Hochdeutsch CH). Anti-translationese: restructures German thoughts fresh instead of mapping English. Two text types: brand/UI and legal. Two actions: TRANSLATE and VALIDATE. Includes 100+ brand-confirmed translation pairs, 40+ glossary terms with keep/translate decisions, DSGVO/DSG legal terminology, completeness checks, and a 4-agent pipeline for legal documents.
CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices.
Gin Go web framework. Covers routing, middleware, binding, validation, and rendering. Use for fast, minimalist Go APIs. USE WHEN: user mentions "gin", "gin-gonic", "go web framework", "go rest api", asks about "gin middleware", "gin binding", "gin validation", "gin router", "fast go api", "gin context" DO NOT USE FOR: Echo projects - use `echo` instead, Fiber projects - use `fiber` instead, Chi projects - use `chi` instead, non-Go backends
Guidance for setting up Git-based multi-branch deployment systems with SSH access, web servers, and automated deployment hooks. This skill should be used when configuring Git repositories that deploy to multiple environments (e.g., main/dev branches), setting up SSH authentication for Git, configuring web servers to serve content from different branches, or creating post-receive hooks for automated deployments.
Harden GitHub Actions and Dependabot: create or modify workflow YAML, reusable workflows, or .github/dependabot.yml; configure dependency updates, alerts, graphs, private registries, and pull-request automation; audit security, correctness, reliability, cost, or performance.
Interact with the GitHub API as the joelclawgithub[bot] app. Use when creating PRs, pushing commits, managing issues, checking CI status, listing repos, or any GitHub API operation. Triggers on "create a PR", "push to GitHub", "open an issue", "check CI", "list repos", "merge PR", "GitHub API", or any task requiring programmatic GitHub access. All actions appear as joelclawgithub[bot], not as @joelhooks.
A guided end-to-end process starting from a new machine: SSH passwordless login → install Docker → install/register GitLab Runner → get a minimal CI/CD pipeline working. Semi-automated: SKILL.md provides steps and command templates, while scripts/ offers detection, configuration, and validation scripts. The user only needs to provide the machine address and GitLab token. Trigger when the user says “configure runner,” “install gitlab runner on a new machine,” “add a runner to gitlab,” or “get CICD running.”
This skill provides comprehensive film and television industry terminology. Covers production terms, script coverage vocabulary, development jargon, and professional communication standards from A-Z. Use when: encountering unfamiliar industry terminology, writing professional correspondence, understanding script coverage or notes, or communicating with industry professionals.
Comprehensive codebase review and parallel agent-based remediation skill. Use PROACTIVELY when agent needs to perform full codebase audit, generate master findings report with quantified metrics, and execute remediation using parallel goodvibes background agents (max 6 concurrent, one task per agent with fresh context). Triggers on: codebase review, code audit, full project analysis, quality assessment, technical debt analysis, parallel remediation, bulk fixes.
MCP (Model Context Protocol) server configuration for live Google Ads API access. Activate when the user wants to connect Claude to their Google Ads account via MCP, set up the google-ads-mcp server, or configure credentials for live API queries. Provides setup instructions, server configuration, and troubleshooting.
Search Google Patents database for patent research, infringement risk checks, and competitive IP analysis. Use when user mentions: 专利, patent, 侵权, infringement, 知识产权, IP, 外观设计, design patent, 专利检索, patent search, 专利风险, patent risk, 专利分析, patent analysis, 专利布局, patent portfolio, 有没有专利, 会不会侵权, 能不能卖, FTO, freedom to operate, 规避设计, 专利壁垒, 技术壁垒, 权利要求, claims, 专利详情, 发明人, inventor, 受让人, assignee, 专利号, patent number, 说明书, description, 技术领域, 背景技术, 发明内容, 具体实施方式, PDF
Writes and executes JavaScript-based shell scripts using Google's zx library. Use when writing shell scripts, automation, build tools, file processing, CLI tools, deployment scripts, data pipelines, or batch operations. Also covers piping, streams, parallel execution, retries, cross-platform scripting, built-in fs utilities, and minimist argument parsing.
Use when building applications that programmatically interact with the Google Play Developer API using GPC's TypeScript SDK packages. Make sure to use this skill whenever the user mentions @gpc-cli/api, @gpc-cli/auth, PlayApiClient, createApiClient, resolveAuth, listReports, downloadStatsReport, downloadFinancialReport, STORAGE_READ_ONLY_SCOPE, Google Play API client, TypeScript SDK, programmatic access, API client, HTTP client, rate limiter, pagination, edit lifecycle in code, Node.js Google Play, server-side Play Store, backend integration — even if they don't explicitly say 'SDK.' Also trigger when someone wants to build a backend service, custom dashboard, automation script, or any TypeScript/JavaScript application that interacts with Google Play programmatically rather than through the CLI. For CLI usage, see other gpc-* skills. For building plugins, see gpc-plugin-development.
Use when managing Google Play developer account users, permissions, grants, or testers. Make sure to use this skill whenever the user mentions gpc users, gpc testers, gpc grants, developer account permissions, user roles, invite user, remove user, permission grants, per-app permissions, per-app grants, standalone grants, tester groups, beta testers, internal testers, alpha testers, Google Group testers, tester CSV import, team management, access control, user audit — even if they don't explicitly say 'user management.' Also trigger when someone wants to invite team members to their Play Console, update permissions for existing users, manage per-app grants independently from users, manage who can test their app, import testers from a CSV file, or audit who has access to their developer account. For authentication setup, see gpc-setup. For release track management, see gpc-release-flow.
Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls `runcomfy run openai/gpt-image-2/edit` through the local RunComfy CLI. Triggers on "gpt image edit", "gpt-image-edit", "chatgpt image edit", "edit with gpt image 2", or any explicit ask to edit with this model
Apply public choice theory to analyze political decision-making as rational self-interested behavior. Use this skill when the user needs to evaluate government policy failures, rent-seeking costs, voting outcomes, or bureaucratic incentives, especially when the assumption of benevolent government is questionable.
Write winning grant proposals for nonprofits and social impact organizations. Covers grant research and selection, proposal structure, compelling narrative writing, budget development, evaluation plans, and submission best practices. Use when applying for foundation grants, government funding, corporate sponsorships, or capacity-building grants. Trigger on "write a grant proposal", "grant writing", "apply for funding", "foundation grant", "nonprofit fundraising", "how to get grants".
World logic design tool for GraphOS. Design World/Context/Variant/System/Event/EventSystem graph models for any game or app, focusing on domain logic, lifecycle systems, bootstrap events, and event-driven context initialization. Depends on graph-management for graph read/apply APIs and graph-world-ts for TypeScript implementation work.
Q&A session that challenges your plan against the existing domain model, sharpens terminology, and updates docs inline (CONTEXT.md, ADR) as decisions are made. Use when the user wants to stress-test a plan against the project's language and recorded decisions.
Guides security assessment of embedded and cyber-physical systems on hardware-in-the-loop (HIL) test benches—bench setup, ECU/ECM or PLC targets, bus interfaces (CAN/CAN-FD, LIN, automotive Ethernet, Modbus at high level), fault injection and stimulus design, simulated plant/environment integration, attack-surface monitoring on real hardware, reproducible test cases, lab safety interlocks, and evidence capture for firmware and vehicle security teams. Use for HIL security testing, ECU security assessment, CAN bus security, PLC HIL test, fault injection lab, embedded hardware security—not web/API pentest (web-pentester), network-only pentest (network-pentester), malware/binary RE only (reverse-engineer), SOC operations (soc-analyst), AI red team (ai-redteam), classified ISSO paperwork (information-systems-security-officer-classified-specialist), or pure software CI without hardware (build-validator).
Create, list, remove, and run scheduled autonomous Claude Code agents. Agents run on a timer via macOS launchd, execute any prompt headlessly, and deliver results via Beeper messages and macOS notifications. Use for recurring research, monitoring, overnight builds, or any task you want Claude to do on autopilot.
Guidance for setting up HuggingFace model inference services with Flask APIs. This skill applies when downloading HuggingFace models, creating inference endpoints, or building ML model serving APIs. Use for tasks involving transformers library, model caching, and REST API creation for ML models.
Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents. Dispatched subagents run in isolated context and do NOT inherit the session's Honey hook, so they emit full-fat code and verbose reports. Use when you are about to dispatch implementer/reviewer/fixer/parallel subagents: it gives the exact Honey directive to paste into each dispatch prompt, with a worker variant and a reviewer variant, so the levers apply inside the subagents too — where the multiplied cost actually is.
Build HTML slide decks from materials (notes, articles, research documents, meeting minutes, URLs, verbal requests), verify diagrams, SVG and draw.io diagrams by measurement on a fixed 1600x900 canvas, and polish readability through a rejection loop with an evaluation sub-agent. Whenever someone says "make slides", "presentation material", "conference material", "proposal deck", "deck", "slides", "presentation", "turn this material into slides", or "summarize for a talk", use this skill first even if no format is specified. Also use it to improve slide quality issues such as text that is too small, too crowded, overflowing or hard to read, and to rework existing HTML decks. This skill also provides a "review mode" where the user points at elements on the generated deck and requests changes. Use it as well when asked to "let me review", "there are things I want to fix", "open the deck", "read the feedback", "fix the feedback I sent", or "fix this", if a deck already exists. Route to the pptx skill only when an editable .pptx file itself is the delivery requirement.
Use for scientific AI/ML discovery and implementation across biology, chemistry, physics, astronomy, climate, genomics, materials science, medicine, ecology, engineering, mathematics, drug discovery, protein design, weather modeling, single-cell analysis, PDE solving, and related research domains. Helps find and use curated Hugging Science and Hugging Face resources, including datasets via `datasets`, models via `transformers` or the HF Inference API, Spaces via `gradio_client`, and blog posts for methodology. Trigger when the user asks for scientific datasets/models, fine-tuning data, scientific ML benchmarks, domain ML tools, or AI tools for research.
Generates human-like git commit messages based on staged or unstaged changes. Reads git diff, analyzes what changed, and outputs 3 natural commit message options that sound like they were written by a developer — not AI. This skill should be used when the user wants a commit message, asks "what should I write for commit", "generate commit message", "human like commit", or just asks for help committing. NOT for changelogs, release notes, or PR descriptions — it writes commit subjects only.
Handle Hotwire form workflows: form submission lifecycle, inline editing, validation errors, typeahead/autocomplete, modal forms, and external form controls. Prefer this skill when the core problem is correctness and UX of form interaction. Use hwc-navigation-content for pagination/tabs/filter navigation, hwc-realtime-streaming for WebSocket/Turbo Stream broadcasting, hwc-media-content for image/video/audio behavior, hwc-ux-feedback for generic loading/transition polish, and hwc-stimulus-fundamentals for framework-level Stimulus APIs not tied to forms.
Handle media-heavy Hotwire features: image/video/audio uploads, previews, playback controls, progress tracking, and third-party media integrations (for example WaveSurfer, Swiper, Picture-in-Picture, Blurhash). Prefer this skill when the core problem is media rendering, playback state, or media library integration. Use hwc-realtime-streaming for server-pushed Turbo Stream updates, hwc-navigation-content for non-media pagination/tab/lazy-navigation flows, hwc-forms-validation for form validation and inline-edit behavior, hwc-ux-feedback for generic loading/transition patterns, and hwc-stimulus-fundamentals for Stimulus primitives not specific to media.
Build Hotwire navigation and content-discovery flows: Turbo Frame pagination, tabbed navigation, lazy loading, faceted filtering/search, cache lifecycle, scroll restoration, and visit/render control. Prefer this skill when the core problem is request/response navigation state and browser history behavior. Use hwc-forms-validation for form validation and inline edit flows, hwc-realtime-streaming for WebSocket/Turbo Stream push updates, hwc-media-content for image/video/audio features, hwc-ux-feedback for generic loading/progress/transition polish, and hwc-stimulus-fundamentals for Stimulus APIs not centered on navigation.
Plan and review localization changes across app, docs, and web surfaces. Use for string extraction, locale routing, plural/date/number formatting, RTL, pseudo-locale QA, message catalogs, and translation readiness. NOT for generic copy editing, frontend visual design, SEO, or JavaScript conventions.
Generate Chinese-language illustrations built on "Xiaohei + real objects + physical action + narrative whitespace". Default output is a 16:9 inline illustration for internet-worker relatability images, workplace anxiety in the AI era, the situation of programmers/product people/creators, and visual metaphors for article arguments; for "easter egg mode / long-scroll story image / extra-wide format / personal experience / project retrospective / product evolution / growth path", output a Xiaohei long-scroll story image. Standard mode defaults to a #FFFFFF pure white background; easter egg long-scroll mode uses a premium near-white background and one real-object life line. Samples are high-quality template masters and quality benchmarks for output; proportions, whitespace, action clarity, and narrative relationships must be aligned with them, but their object combinations, spatial topology, Xiaohei poses, or label positions must not be replicated.
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.