Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Beginner-friendly end-to-end video creator for HyperFrames. Use when the user says "make a video", "create a video", "new video", "build a video", "video from scratch", "I want to make a video", "help me create a video", or when someone who's never used HyperFrames before arrives with a concept, script, or rough idea and wants a finished MP4. Interviews the user in one pass, then builds the full video with mandatory preview and visual-verification gates.
Use when designing or generating Make platform DSL YAML — defining apps, entities, fields, relations, views, or record schemas. Also triggered by requests like "建模", "建表", "加字段", "定义关联", or "生成 DSL". Does not deploy resources (use makecli), build frontend UI (makeui), implement Service/API code (make-app-service), handle auth (make-app-auth), runtime packaging (make-app-runtime), OCR integration (make-integration), or canvas-table behavior (use canvas-table-integration).
Market structure analysis with Wyckoff, SMC/ICT, Al Brooks, and classical price action — outputs structured trade scripts with levels, entry, stop, R:R. Use when the user wants real technical analysis on a ticker (e.g. "market structure analysis on NVDA", "Wyckoff phase for BTC", "where's the order block on SOL", "SMC analysis").
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
Guide to advanced Next.js App Router patterns, including Route Handlers, Parallel Routes, Intercepting Routes, Server Actions, error boundaries, draft mode, and streaming with Suspense. CRITICAL for server actions (action.ts, actions.ts files, 'use server' directive), setting cookies from client components, and form handling. Use when requirements involve server actions, form submissions, cookies, mutations, API routes, `route.ts`, parallel routes, intercepting routes, or streaming. Essential for separating server actions from client components.
Expert guidance on ParadeDB text and vector search, hybrid search (BM25 + semantic), filters, facets, joins, and aggregations in Postgres. Use when writing ParadeDB queries, creating ParadeDB indexes, indexing vectors, configuring tokenizers, or implementing Elasticsearch-quality search in Postgres.
Strategic regression testing with test selection, impact analysis, and continuous regression management. Use when verifying fixes don't break existing functionality, planning regression suites, or optimizing test execution for faster feedback.
Use when building or fixing Roblox game UI or input: HUD (health bar, currency, ability cooldowns), main menu, shop with a scrolling grid, settings screen, inventory, "UI scales wrong on phone", buttons hidden behind the jump button, UI too small on a tablet or TV, portrait and landscape, top bar and safe area, Scale vs Offset, UIListLayout, UIGridLayout, UIFlexItem, StyleSheets and themes, gamepad or console menu navigation, the Input Action System (InputContext, InputAction, InputBinding), ContextActionService migration, PreferredInput, reduced motion and accessibility, localization and AutoLocalize, React, Fusion or Vide, the Device Simulator, and testing UI without a phone.
Full Sentry SDK setup for Apple platforms (iOS, macOS, tvOS, watchOS, visionOS). Use when asked to “add Sentry to iOS,” “add Sentry to Swift,” “install sentry-cocoa,” or configure error monitoring, tracing, profiling, session replay, or logging for Apple applications. Supports SwiftUI and UIKit.
MUST be used when migrating an existing React app to Dune, or when no Dune auth is wired up. Detects classic vs Apps API flow from `app.json` `infra` field, installs the right packages, and wires up the entry file. No-op when a valid auth setup is already in place. Triggers: migrate to Dune, add Dune auth, DuneAuthProvider, AppSdkAuthProvider, connectToHostApp, useDune, Dune setup, setup auth, missing auth provider, CDF authentication, Fusion iframe auth.
Creates new Claude Code skills following repository conventions with proper structure, frontmatter, workflows, code examples, and reference files. Use when users request "create a skill", "new skill", "generate skill", or "add skill to collection".
Create PostHog error tracking suppression rules to drop high-volume, low-value errors at ingestion. Use when the user asks "stop capturing this error", "drop browser extension errors", "ignore ResizeObserver loops", "suppress bot-driven errors", or wants to reduce ingestion cost from noisy unactionable errors. Identifies suppression candidates, scopes the filter tightly, decides between full suppression and sampling, and confirms the rule before creating it. Suppressed errors are dropped permanently — this skill defaults to caution.
The Taishang Laojun alchemy furnace control center. Helps creators use Liu Ye's approach to self-media to turn others' viral hits and their own experiences into their own videos: understand the user's current situation and what they need to deliver this time, then call on interviews, finding benchmarks and breaking down viral hits, topic selection, series planning, opening structure, drafting, titles, review, and monetization as needed. Use when users want to make videos but don't know what to make, have references but don't know how to use them, have a topic but no script, need a title or opening revised, get poor results after posting, or manage an account for a boss or client.
Diagnose Claude Code usage limits—find out where tokens actually went and why a 5-hour or weekly limit was hit. Use whenever the user mentions hitting a usage limit, being rate limited, burning through their quota, running out of Claude Code usage, unexpected or suspicious token consumption, "why am I hitting limits", phantom usage, or asks to audit, analyze, or track their Claude Code token usage. Also use when the user asks how full their 5-hour window is, whether it is safe to start a big task now, which tool, model, project, file, MCP server, skill or subagent is eating their quota, what their usage would cost on the API, whether a habit or update changed their consumption, whether something is using Claude Code in the background or while they were away, or wants a usage report, a week-over-week comparison, a spreadsheet export, or a shareable redacted summary. Questions about the user's OWN tokens, usage, quota or limits—"where did my tokens actually go this week?"—mean this skill and the local Claude Code logs, NOT product analytics, LLM-cost or billing tools (PostHog, Stripe, cloud dashboards), even when such tools are connected. Trigger even if they don't use the word "tare" or "audit"—a complaint about limits is enough.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
A four-dimensional quantitative assessment tool for diagnosing any WeChat Official Account. It scores content health, user activity, core content metrics, and operational compliance against industry averages, then provides actionable operational improvement suggestions.
Fetch and parse WeChat Official Account articles. Extract the title, author, account name, body, images, and metadata from WeChat article links. Use when the user provides a WeChat article link (mp.weixin.qq.com/s/...) and wants to read, extract, download, or convert the article content. Use cases include fetching or downloading WeChat articles, extracting article text or metadata, converting articles to Markdown, and saving articles with images locally. Keywords: WeChat Official Account, article fetching, article scraping, article download
React performance optimization and best practices. ALWAYS use this skill when working with any React code—writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, and state management; reviewing performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, or animations restarting; preventing remounting; implementing transitions, lazy initialization, or effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers: useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
Use this skill when the user asks to “create an agent,” “add an agent,” “write a subagent,” “agent frontmatter,” “when to use description,” “agent examples,” “agent tools,” “agent colors,” or “autonomous agent,” or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Edit images with Alibaba Cloud Model Studio Qwen Image Edit models (qwen-image-edit, qwen-image-edit-plus, qwen-image-edit-max, qwen-image-2.0 series and snapshots). Use when modifying existing images (inpaint, replace, style transfer, local edits), preserving subject consistency, or documenting image edit request/response mappings.
Understand images with Alibaba Cloud Model Studio Qwen VL models (qwen3-vl-plus/qwen3-vl-flash and latest aliases). Use when building image Q&A, visual analysis, OCR-like extraction, chart/table reading, or screenshot understanding workflows.
Angular 20+ performance optimization guidelines with Signals, httpResource, signal inputs/outputs, @defer, and native control flow (@if, @for). Use when writing, reviewing, or refactoring modern Angular code. Triggers on tasks involving Angular components, services, data fetching, bundle optimization, or performance improvements.
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized, or asks "does this follow clean architecture?" or "why does everything depend on everything?". Also triggers for onboarding requests: "explain this codebase to a new developer" or "give me a codebase tour" (use onboarding mode). Do NOT trigger for: PR-level code review (use brooks-review) or line-level refactoring questions — this skill analyzes structural/module-level concerns, not individual functions.
Create reproducible development environments with Dev Containers, Nix flakes, and Devbox for consistent toolchains across teams. Use when onboarding developers, standardizing build environments, or eliminating "works on my machine" problems
Trigger when: (1) User wants to extract text, tables, formulas, or structured data from images/PDFs/scanned documents, (2) User mentions "OCR", "文字识别", "文档解析", (3) User has a document (screenshot, scanned page, invoice, paper, whiteboard photo) and needs its content in structured form, (4) User asks to parse, digitize, or extract content from a visual document. Invokes the GLM-OCR SDK (pip install glmocr) to parse documents via Zhipu's cloud API. No GPU required. Returns structured JSON (regions with labels + bounding boxes) and Markdown. Agent can operate entirely via CLI — no YAML files needed. NOT for: real-time camera feeds, audio transcription, or non-document images (photos, illustrations).
Triggers when a user asks to create, change, run, test, schedule, deploy, upgrade, open, inspect, group, or delete a saved GTM workflow, or its table, runs, diagram, or group, with phrasings like "build a workflow that scores our inbound companies", "run Score inbound accounts", "put it on a weekly schedule, hosted", "enrich my network, connections, or followers", "upgrade the workflow runtime", "take our workflows live on Vercel", "connect the workflow project", "set up keys", "move Cal.com enrichment into Inbound", or "share this workflow's data". Owns the workflows folder (workflow code, groups, tables, runs, schedules, diagrams, keys, share links) and the Vercel project it deploys to, including connecting a GTM agent to it. Not for the workspace, ICPs, or personas themselves (gtm-workspace, gtm-icp, gtm-persona), or one-off fit checks that are not saved (gtm-qualify-prospects)
Triggers when a user asks to create, set up, import, open, check, repair, or share a GTM workspace for an organization, or to add, change, or remove its members or company facts, with phrasings like “set up a GTM workspace for Acme”, “add Priya to the team”, “check the workspace”, or “share the Acme workspace”. Owns the workspace repository, the organization record, members, and workspace health, and hosts the standards every other gtm skill links to. Not for ICPs, personas, prospect fit checks, or saved workflows, which belong to gtm-icp, gtm-persona, gtm-qualify-prospects, and gtm-workflow
Use when the user asks to “create a hook,” “add a PreToolUse/PostToolUse/Stop hook,” “validate tool use,” “implement prompt-based hooks,” “use ${CLAUDE_PLUGIN_ROOT},” “set up event-driven automation,” “block dangerous commands,” or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks, focusing on the advanced prompt-based hooks API
Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, credit the author (people page only when they pass the notability gate), and cross-link. Use when the user shares a link or says "read this", "save this", "think about this"
Use this skill when the user asks to “add MCP server”, “integrate MCP”, “configure MCP in plugin”, “use .mcp.json”, “set up Model Context Protocol”, “connect external service”, mentions “${CLAUDE_PLUGIN_ROOT} with MCP”, or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.
Use when handling files, images, attachments, or binary data in n8n, or when an AI agent needs to take a user-uploaded file as tool input or return a generated file. For Data Tables (schemas, dedup, persistent state), see the separate n8n-data-tables skill. Triggers on "file", "image", "PDF", "attachment", "binary", "upload", "download", chat trigger with files, agent tool that needs a file, vision/multimodal, or any handling of non-JSON file data.
Ni Haixia (1954–2012), a Taiwanese Chinese medicine practitioner, representative of the classical formula school, and founder of Hantang Chinese Medicine. Core mental models: six-channel pattern differentiation, yang qi theory, primacy of the classics, and emphasis on classical formulas. Decision heuristics: identify the six channels before choosing a formula; support yang first when yang qi is deficient; original classical formulas are most reliable. Triggers: Ni Haixia, Haixia perspective, Chinese medicine Ni Haixia, classical formula thinking, what would Ni Haixia think, Master Ni. Knowledge base covers: completed Shanghan Lun passages (Taiyang lower section + Yangming section, modules/13) + all 129 Shanghan Lun passages (modules/01) + 23 chapters of Jin Gui Yao Lue + 72 chapters of Huangdi Neijing + acupuncture tutorial + 374 entries from Shennong Bencao Jing + Tian Ji + 1,257 fully structured case records + 243 categorized narrative case records + Liang Dong dialogues + oral expression DNA + six-channel pattern differentiation diagnostic formulas (8 formulas + quick diagnosis flowchart + pulse and tongue reference + combined and concurrent disease reference + distinguishing true cold from false heat + seven-step thinking model). Based on primary sources: Liang Dong dialogue transcripts, closed-course records from the Ren Ji classes, case collections, and Shennong Bencao Jing video lecture notes.
Diagnose and guide revisions in non-fiction books. Use for non-fiction book revision, when arguments feel weak, evidence is outdated, readers report confusion, thesis is unclear, or book structure has problems. Keywords: non-fiction, revision, thesis, argument, evidence, structure
Build and publish npm packages using Bun as the primary toolchain with npm-compatible output. Use when the user wants to create a new npm library, set up a TypeScript package for publishing, configure build/test/lint tooling for a package, fix CJS/ESM interop issues, or publish to npm. Covers scaffolding, strict TypeScript, Biome + ESLint linting, Vitest testing, Bunup bundling, and publishing workflows. Keywords: npm, package, library, publish, bun, bunup, esm, cjs, exports, typescript, biome, vitest, changesets.
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.