Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guide LaTeX document authoring following best practices and proper semantic markup. Use proactively when: (1) writing or editing .tex files, (2) writing or editing .nw literate programming files, (3) literate-programming skill is active and working with .nw files, (4) user mentions LaTeX, BibTeX, Mentipy in a Beamer/article/PythonTeX context, interactive slide questions in LaTeX, or document formatting, (5) reviewing LaTeX code quality. Ensures proper use of semantic environments (description vs itemize), csquotes (\enquote{} not ``...''), cleveref (\cref{} not \S\ref{}), and a caption on every table and figure (a float, never a bare tabular).
Triage the LinkedIn inbox - sort connection requests and DMs into leads, recruiters, peers and spam, and draft the replies worth sending. Use when the user says "my inbox is a mess", "triage my DMs", "should I reply to this", pastes a batch of LinkedIn messages, or is drowning in connection requests.
Input your best customers and find 100+ companies that match the profile. Uses firmographic data, tech stack, growth signals, and similarity scoring to identify ideal prospects. Use when building target account lists or expanding to new markets.
This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.
Create a NocoBase 3 project for local development with `pnpm create @nocobase/app@beta`, configure it with `pnpm nocobase config init`, `config set`, and `config check`, start it, and hand over to the application's own guidance. Use when the user asks to install, create, set up, or try NocoBase for development, and the working directory has no NocoBase application yet. Not for production deployment, which belongs to the `nocobase-app-installer` Skill. Not for NocoBase 2 or the `nb` CLI, or work inside an existing application, which has its own AGENTS.md and Skills.
OpenMP skill for shared-memory parallel programming. Use when writing parallel for loops, reductions, task parallelism, SIMD directives, GPU offloading, or profiling with Score-P/TAU. Activates on queries about OpenMP, pragma omp, schedule static dynamic, reduction, false sharing, or OMP_NUM_THREADS.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.
Manage payment methods, bind card, spending limit. TRIGGER when: user asks about payment methods, bind card, spending limit, payment status. DO NOT TRIGGER when: billing history, usage queries, subscription status (use qwencloud-usage), support tickets.
Use when asked to "radical candor", "give feedback that cares", "have a difficult conversation", "challenge directly", "manage performance issues", or "give praise that lands". Helps deliver direct feedback while showing you care. The Radical Candor framework (created by Kim Scott) teaches how to challenge directly while caring personally.
Interactive guide to creating Remotion videos, from strategic concept to rendered MP4. Use when the user wants to create a video, make a Remotion project, build a product demo video, generate a launch video, make a recurring content template, create a marketing video, or says "I need a video for...", "help me make a video", "video for my product", or "remotion video". Covers the full creative process: expert deliberation, scenario design, build, and review. Works alongside the official remotion-dev/skills for API-level guidance.
Half-hour television comedy craft (半小时情景喜剧/笑点力学/困境机器/多机位单机位格式) — merged from Evan S. Smith's Writing Television Sitcoms (premise-driven comedy in three levels, nine predicaments, six character mixes, setup/punchline mechanics, toppers, running gags, ten comedic nuances, format rules), Neil Landau's sitcom seven-step formula and comedy-room models, Richard Blum's act-length and set-count parameters, Phoebe Waller-Bridge's Fleabag scripts (direct address as a season-long device, six-episode skeleton), Pamela Douglas on dramedy, Kam Miller on complementary comic traits, and Jesse Armstrong on jokes carrying tragedy. Use when writing or fixing a sitcom episode or spec, raising joke density per page, designing a comic predicament that generates stories, choosing between multi-camera and single-camera format and page counts, structuring cold open/acts/tag, writing a half-hour pilot, running a comedy punch-up, or making a drama funny without shifting genre.
Implement Blazor Splitter layouts with pane configuration, resizing, and state management. Use when creating split pane layouts, handling user interactions, managing pane states, and applying custom styling to Syncfusion Blazor Splitter components.
Leader view—roll up a team’s pipeline by rep and stage, flag at-risk deals, and surface coaching moments. Use when the user asks “show my team’s pipeline,” “team forecast,” “prep for my team’s pipeline review,” or “where does my team need help.”
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.
37signals Rails coding principles and conventions from DHH, Jorge Manrubia, and the Fizzy/Basecamp/HEY codebase. This skill should be used when writing, reviewing, or refactoring Ruby on Rails code following the 37signals philosophy — vanilla Rails, CRUD controllers, rich domain models, concerns, no service objects, Hotwire, Turbo, Stimulus, Solid Queue, Solid Cache, Solid Cable, multi-tenancy, Minitest, custom auth, or DHH conventions.
The ads consultant that becomes an ads agent. Reads paid-ad performance natively through the TikTok Ads connector, or via a build-connector Zapier connection for other ad platforms, explains in plain English what is working and what is burning money, recommends budget, targeting, and creative changes with the dollar impact of each, drafts new ad copy in the owner's voice plus Canva creative briefs, and — only after an explicit yes — executes the approved changes in the ad account. Works from exported CSV reports when nothing is connected, the normal starting point. Use this whenever the owner talks about ads or ad spend at all, including "are my ads working," "what's my ROI on ads," "I'm spending money on Facebook and I don't know what I'm getting," "should I turn this campaign off," "my cost per lead is going up," "write me a new ad," "who should I be targeting," or "the ad guy quit"
For contributors to angular-best-practices. Reviews and audits rule files for accuracy, validity, and formatting compliance. Not for Angular application development — install angular-best-practices instead.
Migrates LLM observability from Braintrust into Arize AX — historical trace import via OTLP (BT output→output.value, span_parents, one AX trace per turn + session.id), datasets, and prompts (latest or versions). Use when migrating from Braintrust to Arize or importing Braintrust logs into AX.
ast-grep rule writing and usage best practices. This skill should be used when writing, reviewing, or debugging ast-grep rules for code search, linting, and transformation. Triggers on tasks involving YAML rules, pattern syntax, meta variables, constraints, or code rewriting.
This skill should be used when the user asks about "LLM gateway", "Bankr LLM", "LLM credits", "top up credits", "auto top-up", "llm.bankr.bot", "Claude Code gateway", "OpenClaw setup", "Cursor setup", "OpenCode setup", "LLM models", or any LLM gateway configuration or usage topic.
A complete development guide for Baidu Maps JSAPI WebGL (BMapGL), covering map initialization, overlays, layers, events, styles, and performance optimization to build high-performance 3D map applications in one place. Triggers automatically when users mention BMapGL, Baidu Maps, jsapi-gl, or related map development needs.
Comprehensive testing guide for Cloudflare Workers using Vitest and @cloudflare/vitest-pool-workers. Use for test setup, binding mocks (D1/KV/R2/DO), integration tests, or encountering test failures, mock errors, coverage issues.
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when the user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.
MUST be used whenever reviewing a Dune app for code quality, maintainability, or clean code issues — before a PR review, after a feature is complete, or when the user asks for a code review. Do NOT skip linting steps. Triggers: code quality, code review, clean code, refactor, maintainability, technical debt, any type, naming, dead code, duplication, DRY, single responsibility, component size, lint, linting, TypeScript strict, dependency injection, file structure.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.
Check customer account health and prepare for a QBR: relationship strength, engagement trends, risk signals, value delivered, and an agenda that makes the review worth their time. Use when the user asks “how healthy is [account]”, “customer health check”, “prep the [account] QBR”, “business review prep”, or “are we at risk with [customer]”.
Use when the user runs /debug-voice, says voice mode has flaws, asks to see or capture what happened in a Grok realtime voice session, or a voice integration has no debug logging yet. Proposes a plan, then installs a dev-only log pipeline (client logger → local NDJSON) in the app's own language and conventions, then runs the fix loop: match the user's report to log signatures, fix one thing, re-test.
Diagnose a Douyin account’s operational health in one click. Uses Honghu Data services to retrieve the account profile and recent post data, then evaluates six dimensions: basic account profile, content productivity, interaction health, content quality, content trends, and follower quality. Outputs an overall score out of 100, detailed scores by dimension, six types of risk alerts, and targeted optimization recommendations. Trigger phrases include “diagnose Douyin account,” “Douyin account analysis,” “Douyin account checkup,” “Douyin account assessment,” “view XX’s Douyin data,” and “analyze this Douyin account.”
Edit, transform, extend, upscale, and enhance videos using EachLabs AI models. Supports lip sync, video translation, subtitle generation, audio merging, style transfer, and video extension. Use when the user wants to edit or transform existing video content.
Builds multi-step forms with validation schemas (Zod/Yup), step components, shared state management, progress indicators, review steps, and error handling. Use when creating "multi-step forms", "wizard flows", "onboarding forms", or "checkout processes".
Hardware virtualization internals skill for Intel VT-x and AMD-V. Use when studying VMCS/VMCB, EPT/NPT page tables, VMEXIT handling, APIC virtualization, or building minimal hypervisors. Activates on queries about VMX, SVM, VMCS, EPT, NPT, VMEXIT, or type-1 hypervisor.
This skill should be used when the user needs to calculate their income tax (所得税), compute deductions, or import withholding slips. Trigger phrases include: "所得税を計算", "確定申告書を作成", "控除を計算", "源泉徴収票を取り込む", "所得税額", "納付額を計算", "還付額を計算", "第一表", "第二表", "申告書B", "所得控除", "税額控除"
Creates personalized learning paths for technologies, frameworks, or concepts. Use for user-interactive session only for onboarding new technologies, hackathon skill-building, or personal development planning. Not for use in automated development or investigation. Sequences resources (docs, tutorials, exercises) based on current skill level and learning goals. Adapts to learning style: hands-on, theory-first, project-based.
Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.
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.