Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when a user is installing DaVinci Resolve for the first time, switching machines, configuring a media drive for video editing, or asking about backup/proxy settings. Triggering symptoms include phrases like "just installed Resolve", "set up DaVinci Resolve", "drop frames during playback", "where should my media live", "how do I configure backups", or any DaVinci Resolve installation/preferences question.
Use when someone asks what is true, false, misleading, unsupported, unknown, or genuinely complicated in a persuasive message, article, pitch, advertisement, policy claim, or viral post. Analyze propaganda, spin, selective framing, urgency, social proof, deceptive marketing, and AI-generated persuasion by tracing claims to evidence and separating literal truth from implied conclusions. Do not use to read deception from demeanor, adjudicate intent, or replace broad domain research.
Instrument an AI application with DeepEval's native tracing so its behavior is visible in Confident AI. TRIGGER when the user wants to add DeepEval tracing or @observe to an LLM app, agent, RAG pipeline, or chatbot; wire a framework, model-provider, or vector-database integration (LangGraph, LangChain, OpenAI Agents, LlamaIndex, Pydantic AI, CrewAI, and others); choose between a native integration and manual instrumentation; set span types, tags, or metadata; or send DeepEval-SDK traces to Confident AI's Observatory. DO NOT TRIGGER for building DeepEval pytest eval suites, datasets, goldens, metrics, or deepeval test run (use the `deepeval` skill), or for raw OpenTelemetry / OTLP export without the deepeval package (use the `deepeval-otel` skill). This skill is purely DeepEval-SDK instrumentation — producing well-formed traces, not running evals.
Design movements from Arts and Crafts through Bauhaus, Swiss Style, Memphis, and grunge to flat design and current styles, with context, visual markers, and UI tokens for each. Use when choosing an aesthetic direction, explaining why a style reads the way it does, or applying a period style without misusing it.
Blocks dangerous commands before execution via a Rust-based Claude Code hook. Use when configuring agent safety guards, setting up destructive command blocking, or auditing CLI protection rules. Use for git reset protection, rm -rf interception, force-push blocking, pack-based command filtering, and PreToolUse hook safety.
Developer experience (DX) engineering, SDK design patterns, API ergonomics, CLI tooling design, documentation-driven development, and developer onboarding. Use when designing SDKs, improving API ergonomics, building developer tools, or creating developer documentation.
Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for 数字人、数字分身、虚拟人、照片开口说话、人像口播、改稿不重拍, AI avatar, AI avatar video, avatar video, talking avatar, talking photo, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, digital human, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and output quality. Do not use for a static profile-picture avatar, game or 3D character creation, an industrial digital twin, ordinary B-roll, generic image-to-video, video translation, talking-head editing, lip-sync dubbing alone, or TTS-only requests.
This skill triggers when a user submits contract text, a transaction arrangement, a business agreement or a description of a legal relationship and needs to assess possible legal disputes or breach-of-contract risks. Typical trigger scenarios include but are not limited to: - The user asks for a contract review and identification of potential risks - The user asks whether a transaction arrangement has any obstacles to performance - The user describes difficulties in contract performance and needs to determine whether they constitute a breach - The user asks for a risk rating of contract clauses - The user provides an agreement between two or more parties and asks to identify possible points of dispute - The user describes a performance deviation that has already occurred and needs to assess the legal consequences - Forward-looking risk identification is needed in scenarios such as contract review, due diligence and transaction negotiation This skill focuses on the two core questions of "whether legal disputes will arise" and "whether breach-of-contract risks exist", and outputs a structured risk list with recommended responses.
Extract scanned documents or images with Mistral OCR and export page Markdown, tables, figures, and structured annotations. Use when Mistral OCR is requested or approved; do not send ordinary PDFs to a paid external OCR service when their embedded text is sufficient.
Scan the codebase and classify every fact by lifecycle stage — tag @draft, @spec, or @implemented based on what the code actually shows. Add missing facts, fix inaccurate ones, remove obsolete ones. Use when asked to discover facts, bootstrap or update a fact sheet, scan the codebase for truths, sync facts to match the code, or audit the fact sheet for accuracy.
Building or editing forms with @falcondev-oss/form — the type-safe, reactive, schema-driven form library (packages form-core, form-react, form-vue) built on @vue/reactivity. Use when working with useForm / useFormCore, form.fields accessors, $use(), field.value / field.handleChange / field.model, form.data, or a Standard Schema (zod v4 / arktype) form in a React or Vue codebase.
Feynman's thinking framework and approach to learning. Based on in-depth research of 30+ sources including "Surely You're Joking, Mr. Feynman!", "What Do You Care What Other People Think?", "The Feynman Lectures on Physics", the Challenger accident investigation report, his Nobel lecture, and James Gleick's "Genius", it distills 5 core mental models, 7 life heuristics, and a complete expression DNA. Use: as a thinking advisor, analyze learning methods, simplification of complex problems, scientific thinking, creativity and other issues from Feynman's perspective. Use when the user mentions "Feynman's perspective", "what would Feynman think", "Feynman mode", "feynman perspective". Also applies to: optimizing learning methods, simplifying complex concepts, breaking superstition about authority, cultivating curiosity, scientific honesty. It can also trigger even if the user only says "how to learn better", "this concept is too complex", "explain it in simple words", "Feynman technique". Do not trigger when the user is only asking purely practical questions such as "help me write code" or "how do I adjust this format" -- activate only when Feynman's core methodology is involved, such as learning thinking, simplifying the complex, scientific spirit, first-principles thinking.
Use this skill whenever building interfaces that should feel physically responsive, alive, and polished. Trigger for spring animations, gesture-driven UI, interruptible animations, physics-based motion, drag interactions, momentum scrolling, layout animations, shared element transitions, spatial UI, micro-interactions, haptic feel, or any request to make an interface feel alive, snappy, smooth, natural, polished, or less static. Also trigger when building interactive components (drawers, sheets, carousels, modals, accordions, reorderable lists) without specified animation, or any interactive prototype, component library, or design system.
Implement, repair, or review Flutter user authentication and session lifecycle, including OAuth or OIDC redirects, PKCE, token refresh, logout, account switching, passkeys, and device re-authentication. Use when sign-in identity or session behavior is the task; route broad threat audits to flutter-security and request transport to flutter-networking.
Deploy HTML/CSS websites to ERPNext/Frappe (v15/v16) as Web Pages via the REST API. Use this skill whenever a user wants to host a website on ERPNext, deploy HTML mockups to Frappe, create Web Pages programmatically, configure Website Settings, or integrate Frappe's Discussion system as a forum. Also use when the user mentions "website on ERPNext", "Web Page API", "Page Builder", "Web Template", or wants to serve custom HTML from Frappe. Covers: Web Pages with Page Builder, custom Web Templates, Website Settings (navbar, footer), CSS management, Frappe Discussion integration, and deployment scripting.
Invoke when the user asks about creative vision, game pillars, core fantasy, design direction, art style decisions, scope arbitration, or creative conflicts. Triggers on: "vision", "pillars", "creative direction", "core fantasy", "tone", "aesthetic", "creative conflict". Do NOT invoke for mechanics design (use game-designer) or technical architecture (use game-technical-director). Part of the AlterLab GameForge collection.
Invoke when the user asks about game UI, onboarding, HUD design, controller navigation, player feedback, usability testing, colorblind modes, or game-specific UX patterns. Triggers on: "UI", "UX", "onboarding", "HUD", "controller nav", "usability", "colorblind", "player feedback", "menu design". Do NOT invoke for deep accessibility audits (use game-accessibility-specialist) or art style (use game-art-director). Part of the AlterLab GameForge collection.
Use when the user explicitly asks to "extract a review topic from a file/image/web page/description" or to "generate structured output of topic + keywords + core questions". Supports many input sources such as files (PDF/Word/Markdown/Tex), folders, images, natural language descriptions, and web page URLs; automatically identifies the input type and extracts content, producing structured output that can be used directly with systematic-literature-review and other literature review skills.
Git workflow management with atomic commit principles. Capabilities: commit organization, branching strategies, merge/rebase workflows, PR management, history cleanup, staged change analysis, single-responsibility commits. Actions: commit, push, pull, merge, rebase, branch, stage, stash git operations. Keywords: git commit, git push, git pull, git merge, git rebase, git branch, git stash, atomic commit, commit message, conventional commits, branching strategy, GitFlow, trunk-based, PR, pull request, code review, git history, cherry-pick, squash, amend, interactive rebase, staged changes. Use when: organizing commits, creating branches, merging code, rebasing, writing commit messages, managing PRs, cleaning git history, analyzing staged changes.
Deploy, manage, and troubleshoot self-hosted GitHub Actions runners. Covers systemd service, Docker containers, Kubernetes (Actions Runner Controller), and the Scale Set Client. Use when setting up a CI runner, debugging registration failures, designing autoscaling, or hardening runner security. Do not use this skill for unrelated requests; route to the nearest named specialist.
Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any explicit ask to generate or edit with this model.
This skill should be used when the user asks to "send a payment", "check balance", "list transactions", "create a quote", "manage customers", "create external account", "what currencies does Grid support", "how do I use the Grid API", "send money to [country]", "pay [UMA address]", "send to CLABE", "send to PIX", "send to IBAN", "send to UPI", "fund sandbox account", "test a payment", "on-ramp", "off-ramp", "convert crypto to fiat", "convert fiat to crypto", "look up UMA", "real-time quote", "JIT funding", "check exchange rate", "FX rate", "payment corridor", "what rate will I get", "estimate withdrawal fee", "crypto withdrawal fee", "USDB", "USDB offramp", "embedded wallet", "embedded wallet sign", "Grid-Wallet-Signature", "Turnkey stamp", "payloadToSign", "EMAIL_OTP credential", "HPKE bundle", "decrypt credential bundle", or any payment operations using the Grid API CLI.
Use when the task involves Halo CLI, Halo CMS terminal operations, or any command-line interaction with Halo. This includes login, profiles, posts, single pages, search, plugins, themes, attachments, backups, moments, comments, notifications, shop operations, or shell completion. Trigger this skill whenever the user mentions 'halo', 'Halo CLI', or wants to manage Halo from the terminal, even if the exact command area is unclear.
Install, configure, repair, and verify Hammerspoon on macOS for keyboard-driven multi-monitor window placement, Spaces controls, Chrome search scopes, and Claude desktop controls. Use when reproducing this setup, fixing silent Hammerspoon hotkeys, or testing window movement without relying on AeroSpace.
Use when a session is running out of context and the work needs to continue in a fresh one, or when starting a session meant to pick up where an earlier one stopped. Not for compacting in place — that is /compact — and not for specifying work that has not started, which is a plan.
Product design partner for @taste-penpot. Use on design, UI, look, polish, or handoff AFTER taste locks identity (identity gate: designer thinking in .heyeddi/, then 3–5 What/Why/How options when unset) and the look. Records personas, route job, and tokens into .heyeddi/design.md, then hands off to @heyeddi-handoff or @design-handoff-flutter. Does not invent a second palette, type system, or multi-step aesthetic. Blocks handoff unless taste layout hard gates pass (no text-wall, hifi.html when MCP cannot Flex, visual QA). Screenshot gate still applies before done.
Convert html-ppt presentations to PPTX in one click. Triggers: export PPTX, convert to PPT, HTML to PPTX, convert to pptx, export for colleagues, PPTX export. Use when the user has an HTML presentation generated by html-ppt (index.html) and wants to convert it to .pptx format. Also applies when the user says "send this HTML to a colleague" or "they only accept PPT".
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.