Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Complete video editing toolkit - silence removal, auto-captions, vertical crop, YouTube clipping, 3D transitions, and social media compression. Use when user asks to edit video, remove silences, add captions/subtitles, crop to vertical/shorts, download YouTube clips, compress video, or create video teasers.
Use this skill to create complete videos with voiceover and music. Triggers: "create video", "product video", "explainer video", "promo video", "demo video", "training video", "ad video", "commercial", "marketing video", "video with voiceover", "video with music", "brand video", "testimonial video" Orchestrates: script, voiceover, background music, video clips/images, and final assembly.
Circle high above the issue board, spotting what's dead (implemented but not closed), what's decaying (stale/outdated), and what needs consolidation. The vulture descends, cleans up the carcass, and leaves the backlog healthy. Use when your issue board needs hygiene—closing completed work, consolidating fragments, and removing decay.
Web automation, debugging, and E2E testing with Playwright. Handles interactive (login, forms, reproduce bugs) and passive modes (network/console capture). Triggers on "e2e test", "browser test", "playwright", "screenshot", "debug UI", "debug frontend", "reproduce bug", "network trace", "console output", "verify fix", "test that", "verify change", "test the flow", "http://localhost", "open browser", "click button", "fill form", "submit form", "check page", "web scraping", "automation script", "headless browser", "browser automation", "selenium alternative", "puppeteer alternative", "page object", "web testing", "UI testing", "frontend testing", "visual regression", "capture network", "intercept requests", "mock API responses". PROACTIVE: Invoke for security verification, UI fix verification, testing forms/dropdowns, or multi-step UI flows. ON SESSION RESUME - check for pending UI verifications.
L2 AI-driven web UI testing for a React/Vite dashboard app. Originally authored against the Onsager Dashboard (the body's route table + file paths are Onsager-shaped); other React dashboards fork the procedure and substitute their own routes / test paths. Use when testing UI on PRs, triaging L1 test failures, or verifying UI behavior at desktop + mobile viewports. Triggers include "test the UI", "check the dashboard", "triage L1 failure", "run L2 tests", "validate this PR", "exploratory test the web app".
WebAuthn/FIDO2 passwordless authentication. Passkeys, registration and authentication ceremonies, SimpleWebAuthn library, resident credentials, and platform/cross-platform authenticators. USE WHEN: user mentions "WebAuthn", "FIDO2", "passkey", "passwordless", "biometric login", "security key", "fingerprint login", "SimpleWebAuthn" DO NOT USE FOR: password-based auth - use `jwt` or `oauth2`; magic links - different flow; OAuth social login - use `oauth2`
A dedicated skill for a bathroom renovation pitfalls guide. Covers the full process — wet/dry separation, moving the vanity outside, three-way separation, waterproofing, floor drains, tile grouting, tiles, borrowing light for windowless bathrooms, shower heads and faucets, bathroom vanities, toilet rough-in distance, shower enclosures, heater ventilation, basin selection — compiling the highlights of the 西安装修课堂 knowledge base in reverse order, to help users get it right the first time and avoid rework after moving in.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
This skill should be used when the user asks about TUI widgets, forms, dialogs, tables, trees, charts, command palettes, split panes, scrollbars, validation, state management, Elm/MVU architecture, async message passing, configuration, packaging, distribution, terminal security, escape-sequence injection, paste sanitization, or production hardening. PROACTIVELY activate for: widget design, validation, virtual scrolling, config/keybinding files, XDG paths, packaging, secure terminal output, and release readiness. Provides: widget contracts, state patterns, config, security, and distribution checklists.
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
Personal solo-dev coding workflow, run only on an explicit "workflow COMMAND" or "/workflow COMMAND" message; never on casual mentions of brainstorm, plan, execute, review or learn elsewhere in a message. Commands: brainstorm, improve, plan, execute, review, park, wrap, status, next, learn, log, todo, bootstrap, realign; bare "workflow" = next.
Look up complete source-pinned WoW event declarations, ordered typed payloads, nilability, secrecy and callback-versus-frame dispatch across Retail, Forever and Classic progression. Verify addon-facing registration and runtime delivery separately.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Retrieve YouTube data using the YouTube Data API. Use when you need to search videos, get video or channel details, fetch transcripts, read comments, find trending or related content, or when the user mentions 'YouTube data', 'video stats', 'transcript', or 'channel info'.
Yunxiao development delivery and code implementation. Even if the user does not write $yunxiao-development-delivery or the standard command words, as long as natural language clearly expresses viewing, claiming, assigning, starting, implementing, submitting or completing development tasks, fixing one's own or a specified Bug, or handling release backflow or cleaning up release branches, proactively recognise it as development intent; first use the official aliyun devops CLI to uniquely locate the [delivery], [development] or Bug item, then normalise it into internal actions. When there is no unique formal item but development intent is clear, create a traceable TEMPDEV branch before the first business code write, without blocking coding and test verification; claiming and freezing must be completed before formal production push. On multiple candidates or conflicting evidence, only block the affected repository, do not guess IDs from titles, and do not silently write to Yunxiao. General local code testing, formal QA testing tasks, product requirements and production releases should not trigger this Skill. All platform writes continue to use snapshots, hash pre-checks, drift checks, single writes, targeted read-back and idempotent receipts; browser, DOM, Cookie and web internal interface fallbacks are prohibited.
ZenTao execution (sprint) management — list executions, get execution details, create executions. Triggers when the user says: 'query executions', 'execution list', 'list executions', 'view execution', 'execution details', 'create execution', 'new execution', 'sprint', 'Sprint', 'milestone', 'ZenTao execution'.
ZenTao product management — list products, get product details, create products, update products, and close products. Triggers when the user says: '查询产品', '产品列表', '有哪些产品', 'product 列表', '查看产品', 'product 详情', '创建产品', '新建 product', '产品信息', '产品线', '禅道产品'.
ZenTao project management — list projects, get project details, create projects, update projects, delete projects. Triggers when the user says: 'query projects', 'project list', 'what projects are there', 'project list', 'view project', 'project details', 'create project', 'new project', 'project info', 'project members', 'ZenTao project'.
ZenTao release management — list releases, get release details, create releases. Triggers when the user says: 'query releases', 'release list', 'list releases', 'view release', 'release details', 'create release', 'new release', 'version release', 'release info', 'ZenTao release'.
ZenTao story management — list, view, create and update stories. Triggers when the user says: 'query stories', 'story list', 'what stories are there', 'story list', 'view story', 'story details', 'create story', 'new story', 'story change', 'close story', 'story status', 'story review', 'ZenTao story'.
ZenTao task management — create tasks, view task lists, update task status, assign owners, start tasks, pause tasks, complete tasks, close tasks. Triggers when the user says: 'query tasks', 'task list', 'what tasks are there', 'task list', 'view task', 'task details', 'create task', 'new task', 'assign task', 'start task', 'complete task', 'task status', 'to-do tasks', 'my tasks', 'ZenTao task'.
ZenTao user management — list users, view user details, query users by department/role. Triggers when the user says: 'query users', 'user list', 'list users', 'view user', 'user details', 'team members', 'member list', 'who is responsible', 'developer', 'tester', 'ZenTao user'.
Zhang Xuefeng’s thinking framework and style of expression. Based on in-depth research into 5 books, 15+ authoritative media interviews, 30+ first-hand quotes, 11 key decision records, and a complete life timeline, it distills 5 core mental models, 8 decision heuristics, and a complete expression DNA. Use as a thinking advisor to analyze education choices, career planning, social mobility, and related topics from Zhang Xuefeng’s perspective. Trigger when the user mentions “from Zhang Xuefeng’s perspective,” “what would Zhang Xuefeng think,” “Zhang Xuefeng mode,” or “Xuefeng perspective.” Also trigger for requests such as “help me think about this from Zhang Xuefeng’s point of view,” “what would Zhang Xuefeng say,” or “switch to Zhang Xuefeng.”
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.
