Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Operate desktop applications on macOS, Windows, and Linux through native accessibility trees, using the agent-desktop CLI. Use when an AI agent must see or act on a desktop GUI: click buttons, fill forms, read UI state, navigate menus, toggle checkboxes, scroll, drag, type text, press shortcuts, take screenshots, manage windows, use the clipboard, launch or close apps, and read notifications. Triggers on: "click button", "fill form", "open app", "read UI", "computer use", "operate desktop", "accessibility tree", "snapshot app", "type into field", "navigate menu", "toggle checkbox", "take screenshot", "desktop automation", "agent-desktop", or any desktop GUI task on macOS, Windows, or Linux.
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.
Persist project decisions in reviewable `.agent-memory/` markdown. Use when asked to "remember a project decision", "save session learnings", "initialize .agent-memory", "manage project memory", "migrate memory", "build memory from docs", "sync memory", "run memory maintenance", "check memory status", or "onboard a new developer"; when `.agent-memory/` or `AGENTS.md` memory pointers are in play; when sharing project context, conventions, or session handoffs with another developer or reviewing project memory in a pull request; or when context "forgets between sessions". Sync reconciles files already in the checkout. Not for vendor auto-memory consolidation, personal agent rulebooks, memory leaks, RAM usage, or human memory
Extract the design of a screenshot, website URL or Figma file into a design.md with tokens, components, layout and brand rules, or copy one element (navbar, card, illustration) into an element.md with a rebuild or image-generation prompt. Use when the user wants to document, replicate, audit or reverse-engineer a visual design: its design system, palette, typography or style.
Generate AscendC operator validation test cases and help users design test cases. Use when the user mentions test case design, generalized test case generation, operator benchmarks, UT cases, accuracy cases, or performance cases.
Implement secure authentication and authorization using Clerk. Use this skill when you need to authenticate users, protect routes, check permissions, implement subscription-based access control, or integrate Clerk with your application. Triggers include "authentication", "auth", "authorization", "Clerk", "protect route", "check user", "sign in", "session", "permissions", "subscription access".
Use when creating SwiftData custom schema migrations with VersionedSchema and SchemaMigrationPlan — property type changes, relationship preservation (one-to-many, many-to-many), the willMigrate/didMigrate limitation, two-stage migration patterns, and testing migrations on real devices
Expert knowledge for Azure Virtual Desktop development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring session hosts, FSLogix profiles, autoscale, MSIX App Attach, or Teams media optimization, and other Azure Virtual Desktop related development tasks. Not for Azure Virtual Machines (use azure-virtual-machines), Azure Dev Box (use azure-dev-box), Azure VMware Solution (use azure-vmware-solution).
Position an AI product when everyone claims AI and skeptics call it “just a wrapper.” Find the real wedge (data, workflow, trust, domain), make reliability the differentiator, answer “won't the big labs just build this,” and stop leading with “AI-powered.” Use when your AI or dev tool blends into a sea of similar demos, buyers doubt the accuracy, or you can't say why you win when the model is a commodity.
CamoFox CLI — 50 commands for anti-detection browser automation from the terminal. Use when the user needs CLI reference for camofox commands, terminal-based browser control, or a quick lookup of command syntax. Triggers include "camofox command", "CLI reference", "terminal browser", or any request for camofox command-line usage.
Use when modifying existing code that lacks tests and you need to document its actual current behavior before making changes -- the legacy code dilemma where you need tests to refactor safely but the code was not written for testability. Specifically for understanding and pinning down what code currently does, not what it should do. Do NOT use for test-driving new behavior (see tdd), general test writing patterns (see testing), verifying test effectiveness (see mutation-testing), or making untestable code testable (see finding-seams)
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
Multi-agent collaborative debate producing visible round-by-round transcripts with real intellectual friction — members are topic-briefed custom agents, run as a 3-round DEBATE or a 1-round QUICK check, to find the best path. USE WHEN council, debate, multiple perspectives, weigh options, deliberate, get different views, what would experts say, pros and cons. NOT FOR pure adversarial attack (use RedTeam).
Use this skill when the user wants to create, draft, author, or generate new slides / a presentation in this open-slide repo. Triggers on phrases like “make slides about X,” “make a deck about X,” “create a presentation,” “draft slides for,” “new slide,” “a deck with speaker notes / a script,” or when the user asks to add content under `slides/`. Do NOT use for editing the framework itself — only for authoring content inside `slides/<id>/`.
Generates self-contained HTML/CSS animations of app features for walkthroughs, demos, and onboarding. Researches the target app via Chrome, interviews the user, generates a structured brief and animation HTML file, then enters an iterative freeze-inspect-feedback review loop until the user approves. Use when the user says “css animation”, “animate this feature”, “create a css walkthrough”, “animation walkthrough”, or wants to create a CSS-based visual demo of an app feature
Data science and analytics expertise for statistical analysis, machine learning pipelines, data governance, business intelligence, predictive modeling, and analytics strategy. Use when building ML models, analyzing data, creating dashboards, or designing data architectures.
dontbesilent content structuring system. Turn a large local collection of drafts, posts, topics, case studies, and course materials into a content structuring project that can grow over time: first audit its size and scope, then create a project, copy materials, extract content units, and generate topic maps and topic assembly drafts. Triggers: /dbs-content-system, /内容结构化系统, “把我的内容做成结构化系统”, “把本地素材变成可重组系统”, “帮我搭内容资产工程”, “我想把旧内容变成可复用资产”. Content structuring system. Audits local content volume, then builds a reusable content knowledge project with units, topic maps, and assembly drafts. Triggers: /dbs-content-system, “build a content structuring system”, “turn my archive into reusable assets”.
Main entry point for the dontbesilent business toolkit. Dual mode: pre-task routing (which skill to use for your question) and post-task navigation (what to do next after a diagnosis). Triggers: /dbs, /商业, “帮我看看”, “下一步怎么走”. Main entry point for the dontbesilent business toolkit. Dual mode: pre-task routing + post-task navigation. Triggers: /dbs, /商业, “帮我看看”, “下一步怎么走”
A title formula tool for Xiaohongshu image-and-text posts and general content. Choose the right option from 75 proven viral formulas, use it correctly, and understand why it fits. Not for finished-video titles, rewritten video titles, two-part Douyin titles, or writing to the finished-video directory 视频标题.md; use ra-video-title for those cases. Triggers: /dbs-xhs-title, /小红书标题, “帮我起个小红书标题”, “小红书标题公式”. Xiaohongshu article/general title formula tool. Pick the right formula from 75 proven templates. For finished video titles or two-part benchmark-driven titles, use ra-video-title instead. Triggers: /dbs-xhs-title, “xiaohongshu title”, “RED title formula”.
Triggers a Power Platform Pipeline deployment run for a Power Pages solution. Selects a target stage, validates the package, optionally configures deployment settings (environment variables, connection references), then deploys and polls for completion. Use when asked to: "deploy pipeline", "run pipeline", "trigger deployment", "deploy to staging", "deploy to production", "run power platform pipeline", "deploy solution via pipeline", "promote solution", "push to staging", "push to production".
Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands, (3) check schema-pack consistency against the brain's actual shape, (4) file enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify resolvability, (7) report. Named after the Radiohead song. Nothing produced during significant work lives only in chat — knowledge becomes permanent, patterns become reusable. Also carries the always-on auto-fire gate: when >=500 words of structured analysis on a user-shared document is about to be delivered, file the brain page first, then deliver the analysis with the link in that same reply.
Ember.js performance optimization and accessibility guidelines. Use this skill when writing, reviewing, or refactoring Ember.js code to ensure optimal performance patterns and accessibility. Triggers on tasks involving Ember components, routes, data fetching, bundle optimization, or accessibility improvements.
Use when building or reviewing FaasJS backend APIs and jobs: .api.ts files, defineApi, zod params schemas, HttpError, HTTP helpers, middleware/staticHandler, .job.ts files, defineJob, typed job paths and params, enqueueJob including transaction-coupled enqueueing, cron schedulers, retries, leases, workers, discovery, and job tests.
Use when working with @faasjs/pg or PostgreSQL in FaasJS: Tables declaration merging, QueryBuilder, select aliases, parameterized sql expressions, raw SQL, numeric/decimal/bigint boundaries, transaction isolation and read-only modes, row locks, concurrency, migrations, SchemaBuilder, TableBuilder, faasjs-pg CLI, PgVitestPlugin, shared migration snapshots, per-file test database isolation, and database type tests.
Use when creating, configuring, reviewing, or onboarding a FaasJS project; working with create-faas-app, vp CLI, TypeScript or Vite config, feature folders, file and naming conventions, test placement, JSDoc/comments, or complete application slice workflow.
Use when implementing, reviewing, or verifying normative FaasJS runtime behavior and compatibility for faas.yaml, staged config discovery and merge order, zero-mapping route resolution, HTTP request/response protocol envelopes, status behavior, plugin identity, concurrent mount and failed-mount retry behavior, lifecycle execution, config layering, and config-driven plugin loading.
Use when working with @faasjs/utils or FaasJS data helpers: deepMerge, streamToString, stringToStream, objectToStream, streamToObject, parseJson, parseObjectFromJson, parseArrayFromJson, parseYaml, z validation helpers, isObjectRecord, parseSchemaValue, formatSchemaError, and isPathInsideRoot.
Framer Motion performance optimization guidelines. Use this skill when writing, reviewing, or refactoring React animations with Framer Motion to ensure optimal performance patterns. Triggers on tasks involving motion components, animations, gestures, layout transitions, scroll-linked effects, and SVG animations
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in FrameVideo HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the framevideo-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the framevideo-media skill; for Chanjing digital humans, OAuth, and website-project synthesis see the chanjing-digital-human skill.
FrameVideo CLI dev loop — `npx framevideo` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the FrameVideo build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `framevideo-media` skill instead.
Build trading strategies, automation bots, and backtesting scripts on the FYERS Trading API v3 (Indian markets — NSE/BSE/MCX). Use when the user wants to fetch market data, historical candles, quotes, market depth, or option chains; place, modify, or cancel orders (regular, GTT, smart orders); manage positions/holdings; stream live data over WebSocket; authenticate with FYERS OAuth; or backtest a strategy with FYERS historical data. Triggers: "fyers", "fyers api", "fyers bot", "fyers strategy", "fyers backtest", "place an order on fyers", "fyers option chain", "fyers historical data", "fyers websocket".
Daily SEO/GEO patrol (2026-06-24 standard). Covers SERP keyword rank tracking (DataForSEO / volume 300-1000 / KD 5-35), Google index count, llms.txt accessibility, GA4 tag deployment checks and AI-source channel configuration, PH canonical consolidation fixes, and social keyword avalanche recovery (title includes best/free/top/guide+year, inject ≤2-3 internal links per section, proactively cite competitor external links). Use when the user says “run SEO daily report,” “check rankings,” “a keyword dropped,” “fix canonical,” or “add internal links”
Hand-drawn storybook cartoon videos - wobbly inked outlines that boil, paper grain and crayon hatching, flat muted colours, simple round characters with big expressive acting - built in code (SVG + GSAP in HyperFrames) and rendered to MP4 at 9:16 or 16:9. Use for cute explainers, character stories, mascot shorts, fables and any request for a handmade, doodly, storybook or less-corporate look. Not for clean flat vector (use flat-vector-explainer), 3D characters (use 3d-toy-character) or text-only videos (use kinetic-typography).
Heihu Zhizao bill of materials management: Query, view, import, update, or bulk enable or disable BOMs. Use when users maintain product materials, yield rates, versions, statuses, or associated process routes. Not for launching a new product into production or executing real-world production.
Heihu Zhizao inventory change tracing: In one conversation, link inventory changes, quantity adjustments, attribute adjustments, and freeze records by material, batch, QR code, or related document; generate a timeline and explain the sources of changes. Use when users ask why inventory changed, who made the change, or which document it is associated with. Not for modifying inventory.
Heihu Zhizao new product production preparation: In one conversation, create and verify the finished product, production definition, BOM, work order, and pending production task. Use when users want to advance a new product to the production task stage. Does not handle material picking, material feeding, operation reporting, or completion.
Heihu Zhizao work order material readiness check: In one conversation, summarize work order material requirements, current available inventory, allocations, and in-transit evidence to determine whether the work order can start, has risks, or cannot start. Use when users ask whether a work order can begin, whether materials are ready, or which materials are missing. Does not create documents or modify inventory.
Guides an Upwork client from candidates to a signed contract by searching for freelancers, reviewing proposals, shortlisting, inviting, and preparing offers. Use when a client wants to find or vet talent, review applicants to a job, shortlist or decline proposals, invite a freelancer, or send a contract offer.
Use when generating agent enforcement hooks for a repo — doc-coverage reminders from docs/, skill-drift and markdown-lint warnings, and the session preflight and delivery-gate hooks that check a session against its outcome contract. Installs into Claude Code and Codex hook configuration.
Huawei Cloud SWR (Software Repository for Container) image lifecycle management skill using hcloud CLI. Use when the user wants to: (1) manage SWR namespaces (organizations) — create/query/delete, (2) manage image repositories — create/query/update/delete, (3) manage image tags/versions — query/create/delete, (4) obtain docker login credentials for SWR, or (5) check SWR quotas and usage limits. Trigger: user mentions “SWR image management”, “SWR 镜像管理”, “container image”, “镜像仓库”, “SWR 组织”, “SWR namespace”, “镜像版本”, “docker login”, “SWR 配额”, “SWR tag”, “容器镜像”, “镜像生命周期”, “SWR repository”, “SWR 登录”, or “SWR quota”
Enforces Intent UI component library conventions. Use when writing React components, reviewing UI code, or building pages/features that involve UI elements. Ensures semantic color tokens, correct form and overlay patterns, the `intent` variant prop, and that existing components from src/components/ui/ are used.
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.