Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Monitor cloud infrastructure and applications using metrics, logs, and traces to provide real-time observability into performance, health, and reliability. Use when the user requests cloud monitoring or provides relevant inputs for this workflow.
Design a feature architecture by analyzing existing codebase patterns and conventions, then provide a comprehensive implementation blueprint with specific files to create or modify, component designs, data flows, and a build sequence. Use this skill when the user asks for an architecture design, an implementation plan for a non-trivial feature, or when dispatched as a sub-task during feature-dev architecture phase.
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting". NOT for deepening shallow modules or redesigning a module's interface or seam, use module-deepening.
Automated code review for Arduino/ESP32/RP2040 projects focusing on best practices, memory safety, and common pitfalls. Use when user wants code feedback, says "review my code", needs help improving code quality, or before finalizing a project. Generates actionable checklists and specific improvement suggestions.
Review code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter. Use this skill when reviewing a small set of changes locally (such as unstaged diff), when dispatched as a sub-task during feature-dev quality review, or when the user wants a critique of a specific file or function.
Guided, scripted pipeline for running JSX/TSX/React codemods safely across large legacy codebases. Use when you need to scaffold a codemod, dry-run it, validate its findings, and apply it across many files (50 to 100k+) without breaking the build. Walks the full inner/outer loop with the Codemod CLI (JSSG, ast-grep, workflows). Triggers on large-scale refactor, legacy React migration, codemod a prop/API change, migrate components across the codebase, run a codemod safely, batched/resumable codemod apply, dry-run a codemod.
Author, validate, and enforce a CODEOWNERS file: detect an existing file, gather ownership evidence from directory structure and git history, write or update rules with correct CODEOWNERS syntax, validate the file against the GitHub API, and wire the ruleset rule that requires code owner review on pull requests. Use when the user says "add CODEOWNERS", "who owns this path", "require owner review", "validate CODEOWNERS", or invokes /codeowners. Idempotent — safe to re-run; diffs before overwriting and never auto-assigns an owner without confirmation. Do NOT use for branch rulesets in general (use /gh-bootstrap) or community health files such as README, LICENSE, CODE_OF_CONDUCT, and SECURITY (use /oss-hygiene) — this skill only covers the CODEOWNERS file and the review rule it feeds.
Analyses git changed files in the workspace and makes atomic, functional, and semantic commits using conventional commits format. Use when the user asks to commit changes, create commits from staged/unstaged files, or organise working tree changes into meaningful commits.
When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' or 'competitive landing pages.' Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Emphasizes deep research, modular content architecture, and varied section types beyond feature tables.
Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition. Triggers on: "create a video", "animate this", "make an explainer", "manim animation", "motion graphic". NOT for React video, use remotion-video.
Workflow for building and modifying content management systems across WordPress, Shopify, Wix, Squarespace, Drupal, WooCommerce, Joomla, HubSpot CMS Hub, Webflow, Adobe Experience Manager, and similar platforms. Use when working on CMS themes, plugins, apps, modules, admin panels, media uploads, content models, editors, markdown pipelines, or static export workflows.
Develop and execute a content strategy that maps content to audience needs, funnel stages, and business goals through editorial planning and performance analysis. Use when the user requests content strategy or provides relevant inputs for this workflow.
Framework-driven copywriting for ads, landing pages, emails, sales pages, and CTAs. Includes AIDA, PAS, BAB, 4Ps, StoryBrand, QUEST, FAB, and more. Use when writing conversion-focused copy, ad creative, headlines, email sequences, sales pages, or when the user mentions copywriting frameworks, persuasive writing, or direct response copy.
Looker Developer Onboarding: Step 7 (Final Step). Creates a LookML dashboard in the project, imports it as a user-defined dashboard (UDD) in Looker, and iteratively refines it based on user feedback by syncing changes. Only execute this after Step 6 (Model Setup using `creating-lookml-model`).
Dark theme design and implementation for web UIs: surface elevation, desaturated brand colors, text/border tokens, color-scheme, system-preference detection, a no-flash theme toggle, and Tailwind dark variants. Use when the user asks to "add dark mode", "create a dark theme", "dark mode support", "implement dark/light toggle", "theme switcher", "prefers-color-scheme", "design for dark background", "night mode", or any dark theme work. For dark mode in HTML email use email-design; for building the full color palette use color-palette.
Comprehensive guidance for CQRS Architecture — independent CQRS skill covering L1/L2/L3 implementation levels, Event Sourcing, idempotency design, domain event lifecycle, and architecture-specific CQRS integration patterns for Layered/Onion/Hexagonal/Clean/COLA. Use when user asks about CQRS, 读写分离, Event Sourcing, 事件溯源, Command Bus, Query Model, or domain events.
Use when designing software architecture, refactoring code structure, solving recurring design problems, or when code exhibits symptoms like tight coupling, rigid hierarchies, scattered responsibilities, or difficult-to-test components. Also use when choosing between architectural approaches or reviewing code for structural improvements.
Pixel-perfect Figma-to-React conversion using coderio. Generates production-ready code (TypeScript, Vite, TailwindCSS V4) with high visual fidelity. Features robust error handling, checkpoint recovery, and streamlined execution via a helper script.
Senior DevOps Engineer with expertise in CI/CD automation, infrastructure as code, monitoring, and SRE practices. Proficient in cloud platforms, containerization, configuration management, and building scalable DevOps pipelines with focus on automation and operational excellence
Build high-performance APIs with Django-Bolt, including BoltAPI routes, typed request validation, msgspec serialization, auth guards, middleware, OpenAPI docs, pagination, streaming, SSE, WebSockets, and testing. Use when the user asks to create a new bolt endpoint, set up a Django-Bolt project, add JWT or API key auth, configure runbolt, wire guards or middleware, add pagination or streaming, generate OpenAPI docs, write TestClient tests, or migrate from FastAPI, Django REST Framework, or Django Ninja to django-bolt. Do NOT use for general Django views, Django admin customization, or standard Django REST Framework work.
Look up CE.SDK React reference docs, guides, and configuration pages. Use when the user needs CE.SDK docs for React — configuration, UI customization, export options, feature guides, or getting-started instructions. Also triggered by “IMG.LY”, “CreativeEditor”, “CE.SDK”, or “cesdk” when the user needs an existing React doc page. Not for writing code (use build) or concept explanations (use explain). <example> Context: User asks about React configuration user: “How do I configure the editor in React?” assistant: “I'll use /imgly-sdk:docs-react to look up configuration options.” </example> <example> Context: User needs React component setup user: “How do I embed CE.SDK in a React component?” assistant: “Let me use /imgly-sdk:docs-react to find the relevant documentation.” </example>
Creates comprehensive Python library documentation including Google-style docstrings, Sphinx setup, API references, tutorials, and ReadTheDocs configuration. Use when writing docstrings, setting up Sphinx documentation, or creating user guides for Python libraries.
Doubao WebSearch search tool. Calls Doubao's web search capability via the 红狐 API, automatically polling for results after submitting a query. Use when users need Doubao search, web search, or AI search for real-time information. Trigger words: 豆包搜索, 豆包websearch, 联网搜索, AI搜索, doubao搜索.
5 proven email writing frameworks for cold outreach - Do the Maths, Short-Trigger, Challenge of Similar Companies, Neutral Insight, and Leader Responsibilities. Use when writing cold emails, structuring outreach messages, or choosing the right framework for your ICP.
Use when you need to discover an API's surface — poke a base URL to find its type (REST, GraphQL, SOAP, JSON-RPC), auth scheme, available endpoints, rate limits, and CORS policy. Also probes MCP servers (HTTP and stdio) to discover tools, resources, and prompts with full input schemas. Runs a Python probe script that checks well-known discovery paths (OpenAPI/Swagger, GraphQL introspection, health, .well-known), fingerprints the server, sends OPTIONS for CORS, detects auth from 401/403 responses, and guesses common REST resources. For MCP, performs JSON-RPC initialize handshake then tools/list, resources/list, prompts/list. Feed it a base URL or MCP server URL, optionally with auth credentials.
Scaffolds Expo (React Native) iOS screens that follow Apple Human Interface Guidelines by construction — list, detail, form, modal sheet, native tabs layout, and settings screens, each wired with native navigation, FlashList, safe-area insets, semantic colors, SF Symbols, haptics, and empty/loading states. Generated code follows the expo-ios-hig rules so it passes expo-ios-hig-verify without rework. Each screen is TSX for Expo Router, not Swift. Trigger whenever the user wants to create, add, generate, or scaffold a new Expo screen, route, tab layout, or form for iOS — even if they don't mention HIG.
Feishu cloud storage: Drive uploads and downloads (chunked large files, resume support, and overwriting as a new version); binary imports such as DOCX/XLSX and asynchronous export tasks; directory mirror push/pull; link and token type parsing; renaming; version history and restoration for uploaded files; basic file/media operations; Wiki knowledge spaces and node structure (create, move, copy, delete) and members; document comments and replies (including comments on selected parts of spreadsheets/slides); collaborators, public links, sharing passwords, ownership transfer, permission requests, and classification labels. Use when the user mentions cloud storage, folders, uploads or downloads, importing Office files, knowledge base directories, comments, sharing, or permissions. Not for reading or editing document/Wiki content or native cloud-drive .md files (feishu-cli-docs), meeting recordings or meeting minutes (feishu-cli-meetings), or document search (feishu-cli-platform).
Author FigJam boards with granular control — sticky notes (single + batch), connectors between nodes, shapes-with-text, sections, tables, code blocks, and auto-arrange — plus read back board contents and the connection graph. Use when the user wants to build or edit a FigJam board element-by-element. Triggers: 'add stickies to FigJam', 'create a flowchart/diagram in FigJam', 'connect these nodes', 'make a section/table/code block in FigJam', 'auto-arrange the board', 'read what's on the FigJam board', 'map the connections'. More granular than the native generate_diagram (which produces a whole diagram in one shot). FigJam files only (figma.editorType === 'figjam'). Requires the Figma Desktop app (Plugin API).
Organize a Figma COMPONENT_SET's variants into a clean, labeled grid — rows and columns derived from the variant properties, with row labels on the left, column headers on top, and a titled white container. Use when a variant set is a messy pile and you want a presentable, documentation-ready layout — triggers: 'arrange my variants in a grid', 'organize this component set', 'lay out the variants with labels', 'make a variant matrix', 'clean up my component set layout', 'add row/column headers to my variants'. Picks the last property (usually State) as columns and the rest as rows by default. NOT something the native MCP's read-only tools do — this writes a new organized layout to the canvas.
Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev workflows, or comparing production UI against Figma designs.
Generate a human-readable markdown changelog between two Figma file versions — pages added/removed/renamed plus per-component changes, enriched with author handles and timestamps, ready to paste into release notes, PRs, or Storybook MDX. Use when the user wants prose history — triggers: 'generate a Figma changelog', 'write release notes from Figma', 'what changed between these versions in markdown', 'summarize Figma changes for the PR', 'changelog between version A and B', 'design changelog since last release'. Uses the Figma REST API + a personal access token because version history is NOT reachable via the Plugin API / use_figma / the native Figma MCP. For raw structured diff JSON use figma-version-history; to find which version introduced a specific change use figma-blame-node.
Combines Pareto prioritization (80/20), timeboxing, and deep work techniques to manage attention, eliminate context-switching, and maximize high-impact output. Use when managing time and attention, combating procrastination, prioritizing high-impact work, planning daily/weekly schedules, or when user mentions timeboxing, Pomodoro, deep work, 80/20 rule, Pareto principle, focus blocks, task batching, or energy management.
Render, inspect, test, preview, and export WebGPU video and frame grids with the framefields headless engine. Use when verifying compositions, diagnosing blank frames, running frame grids or pixel tests, showing the user a live preview, exporting MP4/WebM, reading render progress, running video QA, naming renders in framefields.json, rendering without a GPU, or splitting a render into chunks in framefields. Cloud GPU rendering is in framefields-cloud.
Use when the user wants to plan, evaluate, or build a free tool for marketing purposes—such as lead generation, SEO value, or brand awareness. Also use when the user mentions “engineering as marketing,” “free tool,” “marketing tool,” “calculator,” “generator,” “interactive tool,” “lead gen tool,” “build a tool for leads,” or “free resource.” This skill bridges engineering and marketing and is useful for founders and technical marketers
Generate an annotated blog-style write-up from a presentation's slides and video recording. Orchestrates the full pipeline: fetching slides, converting to images, extracting transcript, generating chapters, outlining slides, and producing the final annotated markdown. USE FOR: write-up, blog post, presentation summary, annotated write-up, generate writeup.
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.
