Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Type-safe routing guidance for navigation, URL state, data loading, authentication, SSR, and framework adapters. Use when a project uses TanStack Router or when the task needs its setup, implementation, debugging, testing, migration, or integration guidance.
Reactive store guidance for state, atoms, selectors, batching, async state, and framework adapters. Use when a project uses TanStack Store or when the task needs its setup, implementation, debugging, testing, migration, or integration guidance.
Virtualization guidance for large lists, grids, dynamic measurement, reverse feeds, and framework adapters. Use when a project uses TanStack Virtual or when the task needs its setup, implementation, debugging, testing, migration, or integration guidance.
Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where Claude is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers during post-task feedback discussions and when the user explicitly mentions skill observations, improvements, the observation log, skill taxonomy, or asks Claude to watch for skill opportunities. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: this skill should be invoked at the start of every task-oriented session — if you are about to use tools to produce deliverables, invoke this skill first.
Use when a task needs several agents that must coordinate with each other while they work, such as negotiating an interface across layers, debating competing hypotheses, or redirecting each other's research, and the harness supports agent teams
Compare and analyze valuation bubbles and fundamentals of A-share tech companies, and identify overvalued and undervalued tech stocks. Use this skill when users ask about tech stock valuations, the A-share tech bubble, whether STAR Market valuations are reasonable, valuation analysis of hot tech sectors such as AI/chips/new energy, or comparisons of tech company growth and valuation.
Logs and views ML training data in TensorBoard using PyTorch SummaryWriter and TensorFlow/Keras callbacks: scalars, images, text, histograms, model graphs, embedding projector, hyperparameter tables, PR curves, and TensorFlow or PyTorch profiler traces. Use when plotting loss and accuracy curves during training, comparing multiple runs in one dashboard, inspecting weight and gradient distributions, projecting embeddings with PCA or t-SNE, tracking hyperparameter experiments, or finding performance bottlenecks in a training loop. Not for hosted experiment tracking with team collaboration; use a dedicated tracking service for that.
Push GPS routes to users' fitness devices with Terra API Routes (pre-release). Use when creating GPS courses or navigation routes, defining waypoints and course points, pushing a route to Garmin, COROS, or Wahoo devices, handling GPX or FIT route formats, or building turn-by-turn navigation onto wearables. Covers the create-then-push workflow, the RouteTemplate and Waypoint data model, per-provider wire formats and feature gaps, cascade re-pushes, and route deletion.
Write, review, and adapt SQL for TiDB with correct handling of TiDB-vs-MySQL differences (VECTOR type + vector indexes/functions, full-text search, AUTO_RANDOM, optimistic/pessimistic transactions, foreign keys, views, DDL limitations, and unsupported MySQL features like procedures/triggers/events/GEOMETRY/SPATIAL). Use when generating SQL that must run on TiDB, migrating MySQL SQL to TiDB, or debugging TiDB SQL compatibility errors.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker). Use when asked to break work into tickets, or when a thinking session reaches its tickets step.
Expert third-party risk management (TPRM) advisor — a vendor risk analyst for the full lifecycle: risk-based vendor tiering, tailored due-diligence questionnaires (SIG-style or mapped to ISO 27001, SOC 2, DORA, NIS2, HIPAA), SOC 2 Type II report review (exceptions, carve-outs, CUECs, bridge letters), DPA and sub-processor review under GDPR Art. 28, contract security addenda (DORA Art. 30 provisions), ongoing monitoring programmes, and vendor offboarding. Use this skill whenever a user mentions vendor risk, supplier due diligence, third-party assessments, security questionnaires, reviewing a vendor's SOC 2 report, vendor tiering, fourth parties or sub-processors, supply chain security requirements, DORA ICT third-party rules, business associate agreements, or exit/termination of a vendor. Also trigger for 'a customer sent us a questionnaire' and 'how do I assess this vendor' style requests.
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
Use when creating, editing, or reviewing TYPO3 extension documentation (Documentation/*.rst, guides.xml, README.md, XLF translations), rendering docs with Docker, using TYPO3 RST directives, adding screenshots, deploying to docs.typo3.org, improve docs, fix documentation, or XLIFF 2-space indentation (TYPO3 v14+).
Packages uni-app projects as native Android APK/AAB and iOS IPA via offline packaging, covering manifest configuration, signing certificates, native plugin integration, and build distribution. Use when the user needs to package a uni-app as a native app, configure Android keystore or iOS provisioning, or set up offline build for distribution.
Unity 6 ECS/DOTS development guide. Use when working with Entity Component System, data-oriented design, Jobs system, or Burst Compiler. Covers Entities, IComponentData, ISystem, EntityManager, baking, Jobs, and Burst. Based on Unity 6.3 LTS documentation.
Unity NPC behavior design-to-code translation. Perception system architecture, decision layer patterns, action execution pipeline, faction & relationship systems, NPC memory & forgetting, crowd & squad coordination. DESIGN INTENT format: INTENT/WRONG/RIGHT/SCAFFOLD/DESIGN HOOK. Based on Unity 6.3 LTS.
Unity 6 physics development guide. Use when working with Rigidbody, colliders, raycasting, triggers, collisions, joints, or physics simulation. Covers PhysX 5 (3D) and Box2D (2D) physics, FixedUpdate timing, layer masks, and contact data. Based on Unity 6.3 LTS documentation.
Unity 6 platform targeting and build guide. Use when building for specific platforms, configuring build profiles, using platform scripting defines (#if UNITY_IOS, #if UNITY_ANDROID), optimizing for mobile, WebGL, or consoles, working with Addressables/asset bundles, or choosing between IL2CPP and Mono. Based on Unity 6.3 LTS documentation.
Manages guarded accounts receivable in Qonto for French businesses. Audits client readiness, verifies French and EU business identity, prepares compliant invoices and quotes, creates invoice-linked payment pages, drafts and sends invoice emails after confirmation, checks payments, and prepares overdue reminders. Use when the user asks to invoice or bill a client, create a quote, collect payment, check whether an invoice was paid, follow up on an overdue invoice, audit clients, or verify French invoice compliance.
Edit, inspect, transcribe, cut, master, or package video and audio media with the headless `video-edit-cli` CLI. Use when the user asks to edit a recording, cut a video, inspect unfamiliar media, extract audio, preview a range, synchronize cameras, make a vertical clip, or produce podcast/episode deliverables.
A complete AI Agent workflow for automatically editing travel vlogs. From raw footage to finished video, only ffmpeg is needed at the system level; everything else runs inside a Python venv. by nyx研究所 (GitHub @znyupup · Bilibili/Xiaohongshu @nyx研究所)
Help users draft and, when authorized, submit feedback to volcengine/volcengine-agent-toolkit: skill problems, missing capabilities, cloud scenarios, and successful Agent workflows. Use for explicit feedback or sharing requests, or an optional invitation at a natural summary after Volcengine CLI errors or an incompletely solved task. Feedback never blocks the main task.
Use when the user asks to analyze, consult, setup, manage, configure, or design a Volcengine Landing Zone, including organization, accounts, finance, identity, cloudtrail, or network infrastructure, or to deploy a solution/blueprint.
Build, review, refactor, configure, or debug Voltra code using Voltra JSX, Voltra JS APIs, the Expo config plugin, and the Voltra CLI. Use when the user asks about charts, Live Activities, Dynamic Island UI, iOS widgets, scheduled widgets, Android widgets, ongoing notifications, image handling, app.json plugin config, React Native CLI setup, or Voltra push update flows.
Provides comprehensive guidance for Vue Router including route configuration, navigation, dynamic routes, nested routes, route guards, programmatic navigation, and route meta. Use when the user asks about Vue Router, needs to set up routing, implement navigation guards, handle route parameters, or manage route transitions.
Web accessibility and interface standards guide. Covers WCAG compliance, semantic HTML, keyboard navigation, screen readers, forms, touch targets, and internationalization. Use when building, reviewing, or auditing web interfaces for accessibility and UX quality.
Author and maintain versioned Selenium WebDriver tests with Java and JUnit 5. Use for creating, debugging, or running Selenium specs, implementing Page Objects, handling explicit waits, capturing screenshots, or setting up Maven test projects. Supports Chrome, Firefox, and Edge. Keywords: Selenium WebDriver, Java, JUnit 5, Page Object Model, explicit waits, Maven, screenshots.
Create, format, and publish WeChat Official Account (微信公众号) articles to draft box with stable quality gates (config bootstrap, metadata validation, cover style×palette presets, and publish preflight). Use when user asks to write/format/publish a WeChat article, generate cover image, or push content to 公众号草稿箱.
Transform generated wiki Markdown files into a polished VitePress static site with dark theme and interactive Mermaid diagrams. Use when user asks to "build a site" or "package as VitePress", user runs the /deep-wiki, or user wants a browsable HTML output from generated wiki pages.
Use when the user wants to capture a writer's voice from a few sample articles and rewrite text to sound like that author — "蒸馏文风", "提炼XX的风格", "把这篇改成XX的味儿", "学某某笔法改写", "mimic this writer", "match this author's style", "style transfer". Works for any author, 王建硕 included.
Write user stories, and acceptance criteria (which represent requirements) from a feature idea, ticket, notes, or existing behavior. Use when the user asks to write, draft, or rewrite/edit/improve requirements, a spec, BRD, user stories, use cases, or acceptance criteria.
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.