Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Docling document parser for PDF, DOCX, PPTX, HTML, images, and 15+ formats. Use when parsing documents, extracting text, converting to Markdown/HTML/JSON, chunking for RAG pipelines, or batch processing files. Triggers on DocumentConverter, convert, convert_all, export_to_markdown, HierarchicalChunker, HybridChunker, ConversionResult.
Integrate the Dynatrace React Native Plugin into a React Native or Expo project — dependency setup, dynatrace.config.js, Babel registration, npx instrumentation, navigation tracking, user privacy options, and verification. Handles both bare React Native and Expo (babel-preset-expo) Babel configuration automatically. Trigger: "add Dynatrace to React Native", "React Native plugin setup", "instrument React Native app", "integrate Dynatrace RN", "mobile observability React Native", "react-native-plugin", "dynatrace react native", "add Dynatrace to Expo", "instrument Expo app", "Dynatrace Expo setup". Do NOT use for: querying RN RUM data (use dt-obs-frontends), non-React Native mobile setups, or Dynatrace server-side configuration.
Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query individual results, and set up scheduled reports on an evaluation. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, inspect sentiment classifications, or manage the evaluation lifecycle.
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.
Huawei Cloud Ascend model deployment and testing skill for large language models on Ascend DevServer (910B series). Supports single-machine and dual-machine deployment for LLM, VL (vision-language), Embedding, and Rerank models. Provides model inference testing, deployment log viewing, and status monitoring with automated model matching and deployment script generation. Use this skill when the user wants to: (1) deploy a model on Ascend DevServer, (2) test model inference, (3) view deployment logs or status, (4) list supported models, (5) check deployment prerequisites. Trigger: deploy, test, model list, deployment log, Ascend, DevServer, 910B, ModelArts, LLM, VL, Embedding, Rerank, multimodal, inference, model catalog, 昇腾, 部署模型, 测试模型, 模型列表, 部署日志, 模型部署, 推理测试
When the user wants to build or improve a sales bot's ability to calm frustrated prospects. Also use when the user mentions "de-escalation," "angry prospect," "frustrated customer," "complaint handling," or "calming techniques."
This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see reference.md. If you need to fill out a PDF form, read forms.md and follow its instructions.
When the user wants to build or improve a sales bot's ability to track conversion rates, drop-off points, and response patterns. Also use when the user mentions "bot analytics," "conversation metrics," "tracking performance," "measuring bot effectiveness," or "conversion tracking."
Offline-searchable X/Twitter CLI and MCP surface for archiving posts, resolving links, monitoring mentions, composing threads, publishing Articles, and searching synced bookmarks. Trigger phrases: `search X for`, `archive tweets about`, `show me the X thread for`, `monitor my X mentions`, `post a thread to X`, `use x-twitter`, `run x-twitter-pp-cli`.
Use when asked to review, critique, audit, or improve an existing user interface — "review this UI", "why does this look generic", "make this more polished", "design feedback", "does this look AI-generated", "audit this page". Also use as the final gate before shipping any frontend work, and when a UI renders correctly but feels unfinished, cheap, or inconsistent without an obvious cause.
Integrating TanStack Router with TanStack Query: queryClient in router context, static queries and fire-and-forget queries in loaders, useSuspenseQuery in components, defaultPreloadStaleTime: 0, setupRouterSsrQueryIntegration for SSR dehydration/hydration and streaming, per-request QueryClient isolation.
Use when the user wants to create, improve, or deploy sales enablement tools and resources. Also use when the user mentions "ROI calculator," "value calculator," "business case builder," "sales tools," "deal support materials," "proposal generator," "pricing calculator," or "value selling tools." This skill covers building tools that help sales teams demonstrate value and close deals.
This skill should be used when the user asks "monolith vs microservices", how to "split into services", set "service boundaries", find the right "service granularity", design an "API gateway / BFF", do "service discovery" or add a "service mesh", or worries that services are "too chatty" / "too fine-grained" — including when a team is pushed to adopt microservices or Kafka between services "to be ready to scale" and the right answer may be a modular monolith. It gives the recipe for carving a system into services (or deciding not to) and wiring how they find and call each other. Use it whenever a design has more than one service — or someone is tempted to add more — even if the user doesn't say "microservices".
Debug and visualization helpers in three.js Core Helpers (AxesHelper, GridHelper, CameraHelper, light helpers, SkeletonHelper, bounding box helpers, PlaneHelper, PolarGridHelper, ArrowHelper) and Addons Helpers (VertexNormalsHelper, VertexTangentsHelper, RectAreaLightHelper, LightProbeHelper, ViewHelper, OctreeHelper, TextureHelper, PositionalAudioHelper, AnimationPathHelper, RapierHelper). Use only for development and editor overlays—not for shipping art; for gizmo-style manipulation use threejs-controls
Tiger Brokers OpenAPI Python SDK—complete skills for AI coding tools. Covers SDK setup, market data queries, stock/futures/options trading, real-time push subscriptions, CLI command-line tool, and MCP server integration. Use when building trading applications, querying market data, placing orders, using the tigeropen CLI, or integrating the Tiger Brokers API with AI editors. 老虎证券 OpenAPI Python SDK 完整技能集。涵盖 SDK 配置、行情查询、股票/期货/期权交易、实时推送订阅、CLI 命令行工具、MCP Server 集成。适用于构建交易应用、查询行情数据、下单交易、使用 tigeropen CLI、或将老虎 API 集成到 AI 编辑器。用户提到以下关键词时自动使用 / Auto-activate on these keywords: 行情、报价、价格、K线、快照、买卖盘、深度、买入、卖出、下单、撤单、改单、交易、持仓、资金、账户、订单、委托、期权、期权链、到期日、期货、推送、订阅、选股、筛选、tigeropen、tiger API、quote、price、K-line、order、buy、sell、trade、position、asset、account、option、future、push、scanner
When the user wants to build or improve a sales bot's ability to recognize external events that create opportunity. Also use when the user mentions "trigger events," "buying triggers," "event detection," "intent signals," or "sales triggers."
Use when the user wants to build or improve a sales bot's ability to introduce scarcity or time-sensitivity without being pushy. Also use when the user mentions "creating urgency," "scarcity," "time-sensitive offers," "limited availability," or "driving action."
Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize software structure, create C4 diagrams, or generate context/container/component/deployment diagrams. Triggers include “architecture diagram”, “C4 diagram”, “system context”, “container diagram”, “component diagram”, “deployment diagram”, “document architecture”, “visualize architecture”.
Use when the user wants to build or improve a sales bot's ability to pull in firmographic or contact data mid-conversation. Also use when the user mentions "data enrichment," "lead enrichment," "pulling company data," "contact data lookup," or "real-time data."
Develop professional plans for vertical short dramas, including emotional value analysis, golden three-second hook design, and three-act structure planning. Suitable for early-stage short drama project planning, commercialization strategy design, and creative guidance
Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
Expert blueprint for scene loading, transitions, async (background) loading, instance management, and caching. Covers fade transitions, loading screens, dynamic spawning, and scene persistence. Use when implementing level changes OR dynamic content loading. Keywords scene, loading, transition, async, ResourceLoader, change_scene, preload, PackedScene, fade
Russian text editor that removes signs of AI generation, bureaucratic language, and filler while preserving facts and adding voice. Includes 38 AI-slop patterns with strict prohibitions (negative parallelisms, em dashes, mathematical signs, tech jargon), a deterministic linter, and detection of chatbot copy-paste artifacts. Use when users ask to “edit,” “remove the fluff,” “make it sound natural,” “humanize,” “remove AI traces,” or “rewrite it to sound more human”; say the text “sounds AI-generated”; prepare an AI draft for publication; or ask “Was this written by AI?”, “check for AI,” or “is it detectable?” (detect mode audits without editing). Do NOT use for writing from scratch, translation, spelling or punctuation checks, non-Russian text, code and configs, or legal and academic texts (bureaucratic language and passive voice are part of the genre).
Integrate Mem0 into an existing repository using a goal-driven, TDD pipeline. Automatically detects the repo's language and asks the user to choose between Mem0 Platform (managed) and Mem0 Open Source (self-hosted). Writes failing tests before implementation. Produces a local feature branch plus `.mem0-integration/` artifacts consumed by the paired verification skill. TRIGGER when: the user says "integrate mem0", "add mem0 to this repo", "wire mem0 into <repo>", or asks how to add memory to an existing project. DO NOT TRIGGER when: the user wants general SDK usage (use skill:mem0), CLI usage (use skill:mem0-cli), or Vercel AI SDK (use skill:mem0-vercel-ai-sdk). After success, invoke skill:mem0-test-integration to verify in the same workspace (loose coupling).
Converts architecture descriptions, module specifications, or workflow documents into Mermaid diagrams. Use to visualize brick module relationships, workflows (DDD, investigation), or system architecture. Supports flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams, and Gantt charts. Generates valid Mermaid syntax for embedding in Markdown documents.
Use when the user wants to build or improve a sales bot's ability to identify emerging objections across campaigns. Also use when the user mentions "objection patterns," "objection learning," "new objection detection," "objection analysis," or "objection flagging."
Calculate risk-based position sizes for long stock trades. Use when user asks about position sizing, how many shares to buy, risk per trade, Kelly criterion, ATR-based sizing, or portfolio risk allocation. Supports stop-loss distance calculation, volatility scaling, and sector concentration checks
Use when the user wants to build or improve a sales bot's ability to know when to quote pricing, when to deflect, and when to escalate to a human. Also use when the user mentions “pricing logic,” “when to quote,” “price handling,” “discount authority,” or “pricing conversations.”
Create SEO-optimized pages at scale using programmatic/template-based approaches. Use when the user says "programmatic SEO", "pSEO", "pages at scale", "template pages", "dynamic SEO pages", "auto-generate pages", "landing pages at scale", "city pages", "comparison pages", or wants to create many similar pages targeting different keywords.
Use when the user wants to build or improve a sales bot’s ability to enrich prospect data from multiple sources. Also use when the user mentions “prospect research,” “data enrichment,” “lead enrichment,” “prospect intelligence,” or “contact enrichment.”
Use when lighting or rendering in Unreal Engine 5.8: physical light units and exposure (EV100, lux, lumens), Lumen GI and reflections, MegaLights, virtual shadow maps, sky, fog and clouds, post process and color grading, the path tracer, or Movie Render Graph stills. Triggers: "Lumen is noisy", "MegaLights noise", "the interior is too dark", "light leaks", neon signs, a night or dusk scene, "fireflies", "path tracer vs Lumen", "render a still", EXR settings.
Use this skill when the user wants to turn a recurring browser workflow into a reusable, parameterized agent skill, especially when the task has concrete inputs and a clear output such as scheduled scrapes, form submissions, data extraction, monitoring flows, price probes, or login-gated reports. Do not use for one-off web tasks; use steel-browser.
WebXR integration for three.js: WebXRManager and XRManager on the renderer, session initialization patterns, VRButton and ARButton helpers, XRControllerModelFactory and hand model families, XREstimatedLight, XRPlanes, and related addon Webxr utilities. Use for immersive sessions and controller/hand tracking—not for standard desktop camera projection (threejs-camera) or composer post effects (threejs-postprocessing).
Use when you need to reduce token usage, lower API costs, fit work within a context window, or speed up an expensive or slow agent loop. Triggers on phrases like “optimize tokens,” “reduce token usage,” “save on cost,” “fit in context,” “context too long,” “running out of tokens,” “prompt caching,” “compact the context,” “agent is too expensive,” “shrink the prompt,” “cheaper model,” and “tokens-per-task.” Provides a layered tactic catalog: measurement (heuristic counting and budget allocation), prompt-side levers (caching, system prompt trimming, tool-definition pruning), context management (compression, observation masking, file-system offload), agent-loop patterns (parallel tool calls, batch operations, model routing by complexity), and output-side controls (depth tiers, stop sequences, structured output). Project- and provider-agnostic; works across Claude Code, Codex CLI, Cursor, Gemini CLI, and Copilot
Use when a GitHub issue needs triage — typically one carrying status/needs-triage label, a freshly opened issue without type/priority labels, or when the user says "triage #N" / "triage this issue". One issue per invocation; for backlog walkthroughs, the caller loops.
Build, debug, and modernize UI with Vue 3.6. Use when editing *.vue files, writing components or composables, or working with code that imports “vue”. Covers script setup, reactivity, Vapor Mode, SSR, and version-specific API changes from 3.4 through 3.6.0-beta.17.
Use when the user wants to build or improve a sales bot's ability to automatically categorize why deals closed or died. Also use when the user mentions "win/loss analysis," "deal outcome," "loss reason," "closed reason," or "deal categorization."
When the user wants to build or improve a sales bot's ability to automatically test message variations to optimize conversion. Also use when the user mentions "message testing," "A/B testing bots," "optimizing bot messages," "testing variations," or "message optimization."
Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done. Use when the user types /advisor, asks to turn the advisor on or off, picks an advisor model, or explicitly asks for a second opinion from a stronger or different model. Never enable it on your own.
Assess the health and consistency of an existing brand — identity, messaging, voice, positioning, and market perception. Use when the user says "brand audit", "brand review", "assess our brand", "is our brand consistent", "brand health check", "brand analysis", "something's off with our brand", "our brand feels outdated", "brand diagnosis", "review our brand", "brand gap analysis", or wants to understand where their brand is strong and where it needs work before investing in brand development.
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.