Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Test for regulatory compliance: GDPR/CMP consent verification, Google Consent Mode v2, Global Privacy Control (GPC), CCPA/US state opt-out, EU AI Act Article 50 transparency, Better Ads Standards, and cookie-inventory auditing. Covers automated consent-flow testing, policy-based script blocking before consent, and cookie drift detection. Use when: "GDPR test," "compliance," "CMP test," "cookie consent," "consent mode," "CCPA," "GPC," "AI Act," "Better Ads," "privacy banner." Not for: WCAG/axe-core test authoring — use accessibility-testing. Not for: OWASP/vuln scanning — use security-testing. Not for: evaluating your LLM feature's quality or safety — use ai-system-testing. Related: accessibility-testing, security-testing, ai-system-testing, ci-cd-integration.
When the user wants to plan a product launch, execute launch channels, or create a launch checklist. Also use when the user mentions "product launch," "launch strategy," "product announcement," "launch channels," or "market launch." For GTM motion and positioning, use gtm-strategy. For cold start and first users, use cold-start-strategy. For Product Hunt day-of, use product-hunt-launch.
End-to-end autopilot orchestrator for setting up Microsoft Teams integration in Salesforce Service Cloud ITSM — runs the whole flow (enable the Teams for Employee Service Go feature, register the Microsoft Entra app, populate Named Credentials, configure the IT Desk and IT Service checklists, turn on Swarming, and optionally embed the Agentforce agent) in one continuous pass, stopping only at the points a human must act. Use when the user asks to set up Microsoft Teams for ITSM end to end, “set up teams for it service,” “do the whole teams itsm setup,” “configure microsoft teams for employee service,” or wants a guided Teams ITSM walkthrough. Delegates each stage to a specialized child skill while driving the sequence itself. DO NOT TRIGGER when the user asks to enable Teams alone, configure just the IT Desk or IT Service checklist alone, or enable Swarming alone — delegate directly to the specific child skill in those cases.
One page, automated tier — run the web accessibility (a11y) rule engine against a live page and locate every violation it can mechanically detect. Pass a URL, a config target name (e.g. `accesslint:accessibility-scan dev`), or nothing to use the default target from `accesslint.config.json`. Ensures a debuggable Chrome, runs the @accesslint/core engine over CDP, and returns a worklist of live-DOM WCAG 2.2 violations, each grounded to its DOM selector and source `file:line`. Locates; doesn't edit. Use it for 'is this page accessible', 'check a11y on this URL', 'find contrast and alt-text issues', or to verify a UI change. For hands-on keyboard and screen-reader checks use `accessibility-inspect`; for a whole site or product use `accessibility-audit`; to diff against uncommitted changes or a branch use `accessibility-diff`.
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Apply when designing or implementing asynchronous processing in VTEX IO services through events, workers, and background handlers. Covers event handler structure, idempotency, retry-safe processing, and moving expensive work out of request-response routes. Use for event-driven integrations, delayed processing, or background jobs in VTEX IO apps
S2 multi-dimensional cross-analysis table development assistant (Expert Skill). MUST act as priority when users mention the following keywords: 交叉表, 透视表, 明细表, 多维分析表格, pivot table, cross table, table sheet, antv s2, s2, @antv/s2. Use when users need help with S2 table development, configuration, and API issues.
Validate system resilience through controlled fault injection. Covers hypothesis-driven chaos experiments, failure injection types (network, service, infrastructure, dependency), LitmusChaos/Chaos Mesh/AWS FIS/Gremlin/toxiproxy tooling, automated abort gating, game day planning, and progressive chaos adoption. Use when: “chaos engineering,” “fault injection,” “resilience test,” “game day,” “failure recovery,” “system reliability,” “blast radius.” Not for: safe rollout flags/canary/dark launch during a release — use testing-in-production; designing new tests from production telemetry — use observability-driven-testing. Related: testing-in-production, observability-driven-testing, performance-testing, release-readiness, test-environments.
The normative Design Guides for GPUI Kit desktop applications. Read in full before designing or changing any screen, layout, spacing, visual hierarchy, color, density, component choice, interaction state, overlay, motion, data-heavy view, or interface copy in a GPUI Kit (gpui-kit / gpui-component) application, and before reviewing UI work for design quality. Also use when asked what the design rules are, or whether a UI decision follows them.
When the user wants to set up, optimize, or manage LinkedIn Ads. Also use when the user mentions "LinkedIn Ads," "LinkedIn Campaign Manager," "Sponsored Content," "Lead Gen Forms," "Sponsored Messaging," "Message Ads," "Conversation Ads," "Accelerate," "Classic ad set," "Audience Network," "objective-based pricing," "Insight Tag," "job title targeting," "company targeting," "Matched Audiences," or "B2B paid ads." For organic posts, use linkedin-posts
Monetize any user project/service with the x402 payment protocol on platform networks (Base + Monad + Robinhood + X Layer + Solana; Starchild platform billing: pay_per_use / lifetime / weekly / monthly / quarterly / yearly / prepaid, plus multi-plan services), limited-time free promotions (amount-0 verify, no settle/debit), and pay other agents' x402 services. Use when the user wants to charge for an API/service, run a free promo on a paid listing, accept USDC from other agents, or call a paid x402 endpoint.
Amazon FBA and FBM shipping cost calculator and fulfillment optimization. Dimensional weight analysis, storage fee calculation, removal cost estimation, and fulfillment method comparison. Use when the user asks about Amazon shipping costs, FBA fees, fulfillment costs, storage fees, or shipping calculations.
Merges, appends, joins, and deduplicates multiple CSV, TSV, and Excel files (including multi-sheet workbooks) with pandas—mapping mismatched column names to one schema, normalizing keys, resolving conflicting values, tracking which file each row came from, and verifying the row math. Use when the user wants to combine spreadsheets or exports, stack monthly files, consolidate contact or lead lists, VLOOKUP-style join two sheets on an ID or email, or dedupe records across sources, even if they only say “put these together” or “clean up these lists into one.”
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
Fetches raw IAM recommendations and associated security insights from Google Cloud for a specified target scope (Organization, Folder, or Project). Use when you need to retrieve security recommendations before analyzing or applying them. Don't use for applying/acting on recommendations (use the recommendation applier skill) or for general allow policy querying (use the allow policy viewer skill).
Configures ESLint v9 flat config and neostandard for JavaScript and TypeScript projects, including migrating from legacy `.eslintrc*` files or the `standard` package. Use when you need to set up or fix linting with `eslint.config.js` or `eslint.config.mjs`, troubleshoot lint errors, configure neostandard rules, migrate from `.eslintrc` to flat config, or integrate linting into CI pipelines and pre-commit hooks.
Triage GitHub issues, review contributor pull requests, diagnose CI, and prepare explicitly requested releases for VoiceStudio's Electron desktop app and Python backend. Use for repository maintenance work, not ordinary VoiceStudio audio generation.
Apply when designing VTEX IO configuration apps with the configuration builder or when a service app must receive structured configuration through runtime context. Covers the separation between service apps and configuration apps, schema.json and configuration.json, settingsType, and reading injected configuration through ctx.vtex.settings. Use for shared service configuration, decoupled configuration lifecycle, or reviewing whether app settings should be replaced by a configuration app.
Create professional investment proposals for prospective clients. Covers the firm's approach, proposed allocation, expected outcomes, and fee structure. Use when pitching new clients or presenting a new investment strategy. Triggers on "investment proposal", "prospect presentation", "pitch new client", "proposal for [client]", or "new client presentation".
Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart tutorials and initial integration. If an experiment ID is available, it should be supplied as input to help determine the use case. Use when the user asks to get started with MLflow, set up tracking, add observability, or integrate MLflow into their project. Triggers on "get started with MLflow", "set up MLflow", "onboard to MLflow", "add MLflow to my project", "how do I use MLflow"
Notify Streak after creating a Gmail draft with the gws CLI. Run this immediately after every successful `gws gmail ... --draft` (send, reply, or reply-all) so Streak records the draft against the box. It POSTs the draftId, threadId, forUserEmail, and whether the draft was a reply to the box's draftCreated endpoint.
Absorb the knowledge in YouTube videos — find them, transcribe them with ElevenLabs Scribe v2, inspect their visuals, and digest what they actually teach. Use this whenever someone wants a video's content as text or knowledge rather than just a link — "transcribe this YouTube video", "what does this video say", "summarize/explain this talk", "pull the transcript", "get subtitles", "turn this lecture into notes", or research-style asks like "find 10-20 videos about <topic> and tell me everything", "research <topic> on YouTube", "what are people saying about <X>". Also use it when a question needs what is shown on screen (slides, charts, code, UI, product) and not only what is said — it extracts frames and, as a last resort, asks Google Gemini to describe the video. Works on any yt-dlp-supported URL. Trigger it even when the words "transcribe" or "skill" never appear but the goal is to learn from video
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
Migrate a test suite from one framework to another, incrementally and without losing coverage. Covers Selenium→Playwright, Cypress→Playwright, Jest→Vitest, Mocha→Vitest, and Protractor→Playwright, with parallel CI running, locator/assertion translation, and a coverage-parity track. Use when: "migrate tests," "switch framework," "Selenium to Playwright," "Jest to Vitest," "framework migration." Not for: bulk selector regeneration after a UI refactor on the SAME framework — use selector-drift-recovery. Not for: healing one flaky test at runtime — use test-reliability. Not for: modernizing patterns without changing framework — use ai-qa-review. Related: playwright-automation, cypress-automation, unit-testing, ci-cd-integration, test-reliability.
The precise design and UI vocabulary used on index.how/to/articulate — covering typography, color, iconography, layout, interaction, motion, accessibility, information architecture, copywriting, tools, analysis, and components. Use when reaching for the exact word for a design concept ("what's the term for the space between two specific letters?"), when a UI idea is described loosely and needs its proper name, when choosing between confusable near-synonyms (badge vs tag, tooltip vs popover, opacity vs visibility, kerning vs tracking), or when writing or reviewing copy, specs, or commits and you want exact terminology instead of vague language.
Configures and debugs launch splash screens in Capacitor apps with @capacitor/splash-screen and @capacitor/assets - `launchAutoHide`, `SplashScreen.hide()`, `launchFadeOutDuration` (Android default changed 200 -> 0 in Capacitor 9), Android 12+ SplashScreen API theme (`Theme.SplashScreen`, `windowSplashScreenAnimatedIcon`), iOS `LaunchScreen.storyboard` + `Splash.imageset`, and Capacitor 8.5 UIScene/SceneDelegate effects (window created in code, Main.storyboard no longer supplies the root view controller). Use for white/black flash at launch, splash never hiding, cropped/tiny Android 12 icon, dark-mode splash, or regenerating icons and splash assets. Do not use for status/navigation bar color and insets (safe-area-handling), the UIScene migration itself (capacitor-uiscene-migration), or startup performance profiling (capacitor-performance).
Query Funda AI financial data via two surfaces: the MCP server at https://funda.ai/api/mcp for analyst-grade research synthesis (DCF, comps, earnings previews/recaps, sector deep-dives, SEC filings, transcripts, supply-chain mapping, ownership flow, macro framing) via the agent_chat tool — OR the REST API at https://api.funda.ai/v1 with FUNDA_API_KEY for raw data (real-time quotes, intraday candles, EOD prices, financial statements, options chains/greeks/GEX, supply-chain KG, social sentiment, news, calendars, FRED, ESG, congressional trades, AI hiring signals). Triggers: "funda", "funda.ai", real-time quote, stock price, intraday, balance sheet, income statement, options chain, DCF, comps, earnings preview/recap, analyst estimates, 10-K/10-Q/8-K, transcript, ownership flow, gamma exposure, supply chain, sector deep-dive, congressional trades, FRED. Prefer MCP for synthesis/analysis questions; use REST for raw structured data the MCP declines.
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
Use when the user wants to optimize internal linking, fix orphan pages, or improve link structure. Also use when the user mentions "internal links," "internal linking," "anchor text," "link equity," "internal linking strategy," or "orphan pages." For IA, use website-structure.
Use the knowledge perspective of 《学习观》 to examine the user's text, extract concepts, criteria for distinguishing them, and conditional connections, then map them in an accessible formal knowledge map that reflects the text's own relationships. Each node has a plain-language definition, a short formula, and specific semantics; the diagram assumes no hierarchy. USE WHEN the user invokes /ljg-map or asks to turn an article, notes, or a talk into a formal map, thought landscape, or concept distinction and relationship diagram. NOT FOR ordinary summaries, paragraph-by-paragraph rewrites, geographic maps, or standalone formula proofs.
Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI)
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.
Playwright testing best practices for Next.js applications (formerly test-playwright). This skill should be used when writing, reviewing, or debugging E2E tests with Playwright. Triggers on tasks involving test selectors, flaky tests, authentication state, API mocking, hydration testing, parallel execution, CI configuration, or debugging test failures.
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.