Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Synthesizes raw learnings and codebase analysis into an interlinked Markdown Knowledge Base (KB). Use at the beginning of a loop to build or update architecture.md, entities, and vulnerabilities. Don't use for generating threat models or formulating execution plans.
Use when the user asks to "check technical SEO"; audits crawlability, indexing, Core Web Vitals, robots.txt, sitemaps, canonicals, redirects, and migrations. Not for on-page tags or content—use on-page-seo-checker. 技术SEO/网站速度
Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art, inpainting, photo manipulation. Triggers: gpt image, gpt-image-2, openai image, chatgpt image, dall-e, dalle, openai image generation, gpt image edit, gpt inpainting, openai dall-e, gpt 4o image
Use when the user asks to “script this short video”, “write a TikTok / Reels / Shorts script”, “给这条抖音或视频号视频写脚本”, or “fix the hook — viewers drop off in the first seconds”; produces timestamped beat-sheet scripts on the retention-gate model (0-2s hook / 2-5s confirmation / 5-15s payoff / loop-or-CTA) with per-scene script lines, on-screen text for muted viewing, asset keywords, and 9:16 format-param rows per platform norm card for TikTok, Reels, Shorts, 抖音, and 视频号 — plus 2-3 hook options from named hook families and an AI-content disclosure line by default on realistic synthetic media. Spec-only: rendering, TTS, and publishing stay with the user’s own tools — no pipelines, no upload automation. Not for creator video briefs — use brief-generator; long-form video SEO belongs to content-writer. 短视频脚本/抖音分镜/开头钩子/竖屏9:16
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks for documentation governance, project-knowledge organization, documentation integrity, or a deterministic docs audit without naming a narrower skill.
Produce a risk matrix or heatmap that quantifies what could break by business impact × probability, runs failure mode analysis on the top items, and maps test coverage to risk zones. Includes stakeholder interview frameworks and continuous reassessment. Run this BEFORE test-strategy or test-planning. Use when: "risk assessment," "risk matrix," "risk heatmap," "what could break," "critical paths," "failure modes," "where to focus testing." Not for: multi-quarter QA direction — use test-strategy. Not for: a single sprint/release test plan — use test-planning. Not for: hands-on session-based bug hunting — use exploratory-testing. Related: test-strategy, test-planning, release-readiness, qa-metrics.
Call Exa Search directly with cURL or raw HTTP. Use when an agent needs Exa semantic web retrieval from POST /search without an SDK, including ranked results, domain or category filters, freshness-aware result content, highlights or text extraction, structured output, or streaming search responses
MyBatis and MyBatis-Spring patterns for mapper design, XML and annotation SQL, result mapping, dynamic SQL safety, transactions, batching, pagination, and query performance. Use when building or reviewing Java persistence code with MyBatis, Spring Boot, MyBatis-Spring, or MyBatis-based legacy applications.
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating against a customer-defined primary metric and optional constraints. Use only when the request identifies an AOI / automated-optical-inspection, PCB-defect, VisualChangeNet, or ChangeNet workflow. Supports air-gapped/offline runs with pre-staged assets. Never infer AOI from generic iterative-improvement language. Do not use for CLIP / SigLIP image retrieval, attribute-labelled image data, standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.
All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses sub-agents for heavy analysis to keep main context clean. Trigger with 'project health', 'check project', 'setup project', 'kickoff', 'bootstrap', 'tidy permissions', 'clean settings', 'capture learnings', 'audit context', 'add python permissions', or 'init project'.
Explore and compare multiple meaningfully different UI directions grounded in the current project's design system and 21st inspiration. Use when the user wants options, variants, concepts, a redesign direction, visual experimentation, or is unsure how a new interface should look. Trigger for requests such as “show me three directions”, “explore alternatives”, “what could this page look like”, or “generate variants”. Do not use for a straightforward implementation with an already-selected direction.
Create a dark monochrome procedural background with enlarged square pixels and visible Bayer-style ordered dithering. Use when a page needs an atmospheric near-black dither field, broad organic waves or cloud masses, and restrained gray-white highlights behind framed UI, hero content, or data overlays
Write a complete 8-part Claude Motion prompt (The bar, Format, The one rule, Look, Motion, Never, Before you finish, The scene) for one short looping motion graphic, in your own brand. Takes your brand (a website screenshot, a logo, hex codes, or nothing for the Apple-style default) and one moment you want to show, in plain words. Use when someone says "write me a Motion prompt", "turn this idea into a motion graphic", "fill in the 8 parts" or "make my motion brief". Outputs parts 1 to 7 as a reusable brief and part 8 as the scene, in one paste-ready code block.
Make AI-generated writing read as human-written, in fiction and in professional prose. Repairs the narrative architecture of fiction and stories (based on StoryScope, arXiv:2604.03136); routes professional text through domain rules for release notes, announcements, PR and issue replies, code-review comments, incident postmortems, tickets, work orders, technical articles, blog posts, and long-form journalism. Four operations - write, review (diagnose AI tells without editing), refactor (minimal in-place edits), recreate (full rewrite). Use when asked to humanize, de-AI, unslop, or strip AI flavor from any text; when writing or revising any of these document types; or whenever output must not read as machine-written.
Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. Use when the user asks to "run the AOI workflow", "fine-tune my PCB AOI model end-to-end", "improve my AOI ChangeNet model", or "AOI workflow with AutoML" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. "run JUST the DEFT loop", "skip AutoML, only DEFT"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include "run the AOI workflow", "AOI end-to-end", "AutoML + DEFT", "AutoML then DEFT", "tune hyperparameters then DEFT", "DEFT with AutoML at both ends", "warm-start DEFT", "improve my AOI model"
Convert a supplied HTML page or generated HTML reference into a screenshot-backed article containing multiple reusable interaction prompts. Use when the user provides an HTML file, exported page, generated-page.html, or local/live reference and asks to extract animation/interactions, create prompts, capture screenshots for each prompt, add them to an article, or commit the resulting article/assets.
Polish Chinese articles, reviews, and documents by removing empty phrasing, repetition, and formulaic expressions (often called removing the “AI flavor” or AI writing traces), making the text more natural while preserving facts, certainty, and the author’s voice. Use for editing or reviewing existing text; not for determining an author’s identity, and it does not guarantee passing AI detectors. If the user asks to clean invisible Unicode, text-based AI watermarks, or file provenance, use $text-watermark-cleaner-zh-tw instead; do not present tone rewriting in this skill as watermark removal.
Send DingTalk messages. Use this skill when the user mentions “DingTalk message,” “send a message,” “send a notification,” “group notification,” “group message,” “Webhook,” “bot message,” “send a bot message,” “work notification,” “direct message,” “group chat message,” “recall a message,” “message read status,” “send Markdown,” “send a card message,” “ActionCard,” “@someone,” “@employee,” “at someone,” “remind someone,” “dingtalk message,” “send message,” “robot message,” or “work notification.” Supports all messaging operations, including custom group Webhook bots (text/Markdown/ActionCard/Link/FeedCard + signing + @someone), direct and group messages from enterprise app bots, message recall, read-status checks, and work notifications.
Strict frontend design guardrails for building modern, minimal-visual-noise, airy, non-generic app UIs. Use whenever creating or changing frontend UI, React components, shadcn/ui themes, Tailwind styles, app layouts, or first-version product screens. This skill complements vertical/domain skills like CPQ, CRM, and similar app builders: follow the selected domain skill's workflow and layout requirements, then enforce this skill's shared visual rules for brand-aware theming, generous spacing, typography, contrast, roundedness, shadows, surface hierarchy, cardless defaults, no-sidebar defaults, and anti-pattern avoidance.
MUST activate when the project contains a uiBundles/*/src/ directory and the task involves creating or configuring a Custom Application for hosting a UI bundle in Lightning Experience. Use this skill when creating a CustomApplication metadata record to surface the UI bundle in the App Launcher. Activate when files matching applications/*.app-meta.xml exist and need modification, or when the user wants to expose their app via the Lightning App Launcher without a Digital Experience Site. Do NOT use generating-custom-application for this — UI bundle apps do not use tabs, action overrides, or flexipages.
Manage music releases using RELEASE.md documents stored in releases/{release-slug}/ within an artist workspace. Triggers when the user mentions an artist's album, EP, single, or project — or asks about release planning, DSP pitches, metadata, marketing, press materials, physical production, or tour coordination. First infer which artist and release the user means, then find or create the RELEASE.md. Use this skill to create, update, or pull data from release documents, and to generate deliverables like DSP pitches, press one-sheets, and production specs.
Comprehensive startup idea validation and market analysis tool. Use when users need to evaluate a startup idea, assess market fit, analyze competition, validate problem-solution fit, or determine market positioning. Triggers include requests to "validate my startup idea", "analyze market opportunity", "check if there's demand for", "research competition for", "evaluate business idea", or "see if my idea is viable". Provides data-driven analysis using web search, market frameworks, competitive research, and positioning recommendations
Generate images, videos, and audio/music via Lovart AI. Also manages Lovart projects, threads (conversation history), and user settings. Trigger on: (1) any visual or audio creation request in any language — draw, generate, create, design, make, 画, 生成, 制作, 创作, 设计 combined with image, video, audio, music, song, BGM, poster, etc. (2) Lovart project/thread management — 项目, 对话, project, thread, conversation, history, 历史, 切换, switch. You CAN generate directly - never say you cannot.
Generates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
Run the technical (code) review step of Flows app certification in a local git app. Loads flows-review-checks for the actual bar, then writes artifacts under reviews/code-review/feedback-round-<N>/. Use when the user asks for a Flows code review, technical review, pre-submit review, app certification code review, or "run flows-code-review". Re-run until 0 open Must Fix items remain before moving on to flows-design-review.
You MUST use this when executing an existing implementation plan through coordinated subagents, including resuming interrupted orchestration. Covers task delegation, review, verification, and integration. Not for inline plan execution or unrelated parallel investigations.
Wren CLI for AI agents — a semantic SQL layer over 22+ databases (Postgres, MySQL, BigQuery, Snowflake, Spark, …). The actual workflow guides live inside the `wren` CLI itself; this is just a discovery stub. Use whenever the user asks a data question (how many, show me, top N, compare, trend, breakdown, metric, revenue, customers, orders), wants to install / set up Wren Engine, connect a new database, connect SaaS data via dlt (HubSpot, Stripe, Salesforce, GitHub, Slack), generate or regenerate an MDL project from a database schema, enrich a project with business context (enum meanings, units, cubes like ARR / DAU / churn), or turn a project's context layer into a shareable GenBI web app / dashboard and deploy it to Vercel or Cloudflare. Triggers: 'install wren', 'set up wren engine', 'connect database to wren', 'connect SaaS to wren', 'load hubspot / stripe / salesforce data', 'generate mdl', 'scaffold wren project', 'enrich wren context', 'augment my project', 'add cubes', 'build a dashboard', 'make a shareable analytics app', 'deploy my context layer as a web app', 'genbi app', 'wren onboarding', 'wren usage', 'wren generate mdl', 'wren dlt connector', 'wren enrich context', 'wren genbi'.
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.