Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
State-first design pass — inventories and implements all non-happy states (loading, empty, error, partial, conflict, offline) before the happy path, and refactors impossible boolean state to proper state machines. Use when starting a new screen, reviewing an existing one for edge-case gaps, or when the user says “handle the error state” / “add loading states” / “what happens when data is missing”. Invoke when the user asks for unhappy on their UI, or mentions 'unhappy' alongside design / UI / frontend work.
Adapt designs for narrow, medium, wide, embedded, or print web contexts without losing usability, hierarchy, or target sizing. Use when the user mentions responsive design, breakpoints, narrow layouts, viewport changes, touch-capable browsers, or cross-context adaptation.
Use when designing or costing an Azure architecture (AKS, App Service, Functions, Cosmos DB, Bicep or ARM, Azure DevOps, migration to Azure). Designs it with architecture_designer.py, generates Bicep with bicep_generator.py and finds savings with cost_optimizer.py.
Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger keywords - debug inference, managed inference endpoint, local inference, ollama, lm studio, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, credential_endpoint_mismatch, host.openshell.internal.
Check open leaves for deadline alerts and required decisions. Surfaces only the leaves that require an action and explains why — not a status board. Use weekly, or whenever the attorney needs to know which leaves have upcoming designation, certification, or exhaustion deadlines.
Draft a DMCA takedown notice, triage one you received, or draft a §512(g) counter-notice. Use when asserting copyright through a §512(c)(3) takedown with the fair-use and perjury gates, when an incoming takedown needs triage into comply / counter / engage / ignore options, or when drafting a §512(g)(3) counter-notice with the consent-to-federal-jurisdiction gate.
Generates Bruno collection files (.bru) from Express, Next.js, Fastify, or other API routes. Creates organized collections with environments, authentication, and folder structure for the open-source Bruno API client. Use when users request "generate bruno collection", "bruno api testing", "create bru files", or "bruno import".
DingTalk AI Table (multi-dimensional table) operation skill. Use the mcporter CLI to connect to DingTalk's official new AI Table MCP server, and perform queries as well as create, update and delete operations on Base, Table, Field and Record based on the baseId / tableId / fieldId / recordId system. Suitable for creating AI tables, searching tables, reading table structures, batch adding, updating or deleting records, batch creating fields, updating field configurations, creating tables from templates, and similar scenarios. Requires configuring DINGTALK_MCP_URL or using a Streamable HTTP URL directly.
Add translator comments to Lingui messages so translations are accurate. Use when adding or modifying translatable messages, when strings are short or ambiguous ("Back", "Delete", "Post"), when placeholders are unclear ({count}, {name}), when deciding between comment and context, or when auditing extracted .po catalogs for missing translator context.
Retrieves ClinGen gene-disease validity assertions for a public gene or disease, and reviews source-linked public evidence and literature for one supported GRCh38 germline nuclear SNV or simple indel through Folklore Clinical Variant Interpretation MCP. Used when a scientific agent must branch deterministically on resolved, ambiguous, not-found, invalid, unsupported, or unavailable variant outcomes; chain a resolved public variant into related literature or publication details; or preserve evidence provenance without accepting patient, phenotype, family, segregation, or private case data
Close a matter — capture outcome, final exposure, and lessons, then archive it out of the active portfolio without deleting the record. Use when the user wants to close a matter, says "[matter] is done", or needs to record a settlement, dismissal, judgment, withdrawal, or consolidation outcome.
Generates 3D models, textures, format conversions, reference images, rigging, animation and motion clips with the Meshy CLI, and prepares them for physical 3D printing: white or multicolor prints, printability repair, Creative Lab products, sizing and slicer handoff (Bambu Studio, OrcaSlicer, PrusaSlicer, Cura). Use when the user asks to make, texture, rig, animate or convert a 3D model, or wants something 3D-printed. Signs in through the browser; no API key required.
Query OpenSea marketplace data — listings, offers, sales / events, floor prices, collection stats, drops, traits — and execute Seaport trades via the official `@opensea/cli` and OpenSea REST API across Ethereum, Base, Arbitrum, Optimism, Polygon, and more. Includes search across collections / NFTs / tokens / accounts. NOT for general NFT metadata reads (name, image, traits, ownership), token metadata, current wallet balances, transaction history, or live RPC reads — for those use `alchemy-cli` (live), `alchemy-mcp`, `alchemy-api` (app code), or `agentic-gateway` (no API key). For pure cross-chain token swaps (no marketplace context), prefer the `lifi` ecosystem skill. Requires `OPENSEA_API_KEY` (instant via API).
Produce a proposed marked-up policy redraft that closes a gap found by /regulatory-legal:gaps or /regulatory-legal:policy-diff. A first draft for internal review — not for direct application to approved policy documents. Use when the user says "redraft the policy", "draft the policy fix", "mark up the policy", or when gap-surfacer hands off a gap for drafting.
Transcribes Chinese/English audio with StepFun's stepaudio-3-asr-max via its SSE endpoint (not /v1/audio/transcriptions) — one call handles long-form audio with no chunking. Use when migrating from step-asr/stepaudio-2.5-asr, or when hitting the misleading "model not supported" error (actually the wrong endpoint). Triggers on 阶跃 ASR, 语音识别. Not for TTS with the sibling model (use stepfun-tts).
Use for Chinese-language or China-family-context family-doctor-style parenting and child health management: 育儿, 宝宝护理, 科学养育, 生长发育, 喂养, 母乳, 配方奶, 辅食, 睡眠, 湿疹, 过敏观察, 疫苗沟通, 居家观察, 宝宝档案, parenting.md tracking, 看病问诊, 病例归档, 父母焦虑, 家庭协作, visual parenting plans, or dad-focused caregiving. Also use as a safety bridge when a caregiver raises acute child symptoms in a parenting context. Do not use for diagnosis, prescriptions, medication dosing, lab reports, or adult-only health questions.
Quickly determine whether a processing activity needs a PIA, a mandatory GDPR DPIA, or can proceed — surfaces privacy policy conflicts and routes to the right next step. Use when the user asks "does this need a PIA", "triage this feature", "privacy check on X", "is this okay from a privacy perspective", or describes a new data processing activity, product feature, or vendor relationship.
Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says "what's wrong with my app", "why is my eval failing", "analyze errors", "root cause analysis", "diagnose failures", or wants to understand production failure patterns.
Remove signs of AI-generated writing from text to make it sound more natural and human-written. Use when editing or reviewing any form of document including: markdown, technical docs, emails, blog posts, PRDs, or any dedicated writing content. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Manage matter workspaces — new, list, switch, close, or detach (practice-level). Use when a multi-client practitioner needs to create a matter, switch the active matter, list matters, archive a matter, or detach to practice-level context, or when another skill needs to know which matter it's working in.
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.
Guide AI agents through TypeScript coding best practices including type safety, error handling, code organization, and architecture patterns. This skill should be used when generating TypeScript code, reviewing TypeScript files, creating new TypeScript modules, refactoring JavaScript to TypeScript, or when the user asks about TypeScript patterns, types, or coding standards. Keywords: typescript, types, coding standards, best practices, type safety, generics, architecture, refactoring.
Guides day-to-day work in Tuist-generated Xcode workspaces, including generation, build and test commands, and buildable folders. Use when working in a Tuist-generated project or when users mention `tuist generate`, `xcodebuild test`, or generated workspaces.
macOS platform guide for the agent-desktop CLI. Use for desktop automation on macOS: granting Accessibility and Screen Recording permissions (TCC), what headed mode does on macOS (physical-first click, type and scroll), surfaces (menu, menubar, sheet, popover, alert, dock, menu-bar extras), menu bar apps and system panels with no window, Notification Center, Chromium and Electron apps including launch --cdp, and fixing PERM_DENIED, empty accessibility trees, ACTION_FAILED and APP_UNRESPONSIVE
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when the user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to set up Claude Code for a project for the first time, or wants to know which Claude Code features they should use.
Douyin video batch download tool — based on the F2 framework to deliver efficient, incremental video downloading. Supports downloading from a single or multiple creators, automatic Cookie management, and a differential update mechanism. Use this skill when the user needs to batch download a specific creator's videos, deploy automated downloading on a server, or periodically update a video library.
Build type-safe APIs with Hono for Cloudflare Workers, Deno, Bun, Node.js. Routing, middleware, validation (Zod/Valibot), RPC, streaming (SSE), WebSocket, security (CSRF, secureHeaders). Use when: building Hono APIs, streaming SSE, WebSocket, validation, RPC. Troubleshoot: validation hooks, RPC types, middleware chains, JWT verify algorithm required (v4.11.4+), body consumed errors.
Write a noun or concept into a usable understanding: first explain in plain language what it is and how it differs from neighboring concepts, then describe how it works and what judgments it changes, and finally give concrete handles for acting on it. Use when the user asks what X is, how to understand it, what it means, why it matters, or how to judge or use it later; especially suited to technical concepts, institutions, products, roles, methods, standards, and practices. Not for: simply looking up facts, proving formulas, step-by-step tutorials, deep vertical causal digging (use ljg-think), or motif structure (use ljg-structure).
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.