Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Website replication/cloning methodology. USE WHEN the user says to replicate or clone a website, clone website, copy a site, imitate a site, make one based on this site, reproduce a site, recreate a webpage effect, download this site and adapt it, or replicate an interaction/WebGL/Canvas/Three.js effect. Provides a portable decision tree for “get the actual source first → determine the path → reverse-engineer and break it down → set up the project → replace the content,” covering three branches: static sites, React/Vue/Next content sites, and WebGL-Canvas-heavy frontend sites. Requires checking any executable code in secondhand AI analysis.
Use when you need Azure DevOps CLI guidance to verify installation, configure organization and project context, discover work item IDs by optional WIQL filters, and execute safe work-item create/update operations. Uses an interactive install gate - if `az` or the Azure DevOps extension is missing, ask whether to show installation guidance before any work item commands. This should trigger for requests such as Azure DevOps work item list; List Azure Boards work item IDs; Azure DevOps WIQL query; Azure DevOps CLI planning workflow. Part of Plinth Toolkit
Diátaxis-driven documentation for AI coding agents: write, improve, or audit tutorials, how-tos, reference, explanation, and developer docs (README, CONTRIBUTING, ADRs). Detects the docs stack; gates on the outline before writing prose; verifies every claim against the code before it ships. Triggers on "absolute docs", "write docs", "write a tutorial", "write a README", "document this", "improve this doc", "audit our docs".
Create or update a living ARCHITECTURE.md for a codebase. Use when the user wants to write, refresh, restructure, or maintain an architecture document; document how the system is organized across tech stack, deployment model, services, components, and data stores; or turn codebase findings into durable architecture docs for engineers or agents. Trigger on requests such as write an architecture doc, document this system, create or update ARCHITECTURE.md, give me a technical overview of this repo, or map out how this app is put together, even when the file is not named. Prefer this skill for file-producing architecture documentation, not for generic architecture advice, implementation planning, or diagram-only brainstorming unless that work is clearly part of updating the document.
Use this skill to run an end-to-end Jetpack Compose performance audit when the symptom is broad ("the app feels sluggish", "scroll is rough everywhere", "we're starting a perf sprint", "what should we fix first?"). Orchestrates the four-phase Measure → Diagnose → Fix → Verify loop by sequencing the 25 focused skills (release-mode setup, R8, Baseline Profiles, Compose Compiler reports, stability inference, Layout Inspector, `@TraceRecomposition`, stabilization, strong skipping, phase-deferral, derivedStateOf, lazy layouts, lazy prefetch, Modifier.Node, modifier ordering, flow collection, effects, CI gates, hot-reload) and produces a written audit report with Before/After Macrobenchmark numbers. Use when the developer wants a perf sprint kickoff, a pre-release perf gate, onboarding to a perf-troubled codebase, or a written deliverable. Use when the user mentions "audit", "perf review", "perf sprint", "where do I start", or has no specific symptom yet.
Query one or more CawPlan tickets and show their current details in the conversation. Use when: the user gives or mentions CawPlan issue URLs, display IDs, or ticket unique IDs and wants ticket context. Automatically run when a CawPlan issue URL appears with no other workflow intent, even if the user did not explicitly ask to query ticket context. NOT for: creating tickets, updating tickets, downloading or adding attachments (use cawplan-ticket-attachments), product status reporting, codebase exploration, implementation, file edits, or SQA requirement analysis
Create one or more CawPlan tickets: from an explicit request, or by extracting action items/work items out of pasted long-form text such as a PRD, a Slack discussion, or a meeting transcript (version-scoped by default, or backlog only after user confirmation). Also routes a PRD's platforms (FE/BE/iOS/Android/QA) to different products under one Team, and splits work into sub-tickets under a parent ticket. Use when: the user asks to create or file a ticket, issue, bug, or task in CawPlan; asks to split a ticket into sub-tickets; or pastes a PRD/requirement doc, Slack conversation, or meeting transcript/notes and asks to turn them into tickets, extract action items, or split work into FE/BE/iOS/Android/QA tickets — including when those platforms belong to different products under the same Team. NOT for: updating existing tickets, searching tickets, critical issues, release planning, or SQA requirement analysis and archiving (use `cawplan-requirement-analyze`)
An advanced development guide to Claude Code—a comprehensive Chinese-language tutorial covering tool usage, the REPL environment, development workflows, MCP integration, advanced patterns, and best practices. For learning Claude Code's advanced features and development techniques.
Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` / `_task_decrypt`, querying `doca_aes_gcm_cap_*` for per-key-type (only `DOCA_AES_GCM_KEY_128` / `_256` — AES-192 not supported) and per-task support, sizing plaintext against the max-buf cap, setting source / destination mmap permissions, validating with a NIST GCMVS or RFC 5288 vector, or debugging DOCA_ERROR_* including the security-critical tag-verification-failed outcome on decrypt. Trigger even when the user does not explicitly mention "DOCA AES-GCM" or "AEAD" — typical implicit phrasings: "decrypt completion IO_FAILED", "auth tag isn't verifying", "NOT_PERMITTED on my encrypt buffer", "is AES-192-GCM on this BlueField" (no), or "encrypted record came back tampered". Refuse and route elsewhere for non-GCM AES modes (CBC / CTR / XTS — CPU OpenSSL), key management (KMS / HSM / rotation), SHA (doca-sha), or general AEAD background.
Entry point for Drupal Canvas Code Components (React/JSX). Points to the officially maintained drupal-canvas/skills suite (component definition, metadata, push, styling, data fetching, regions, page definition, content templates) and to this repo's complements for Twig SDCs and upstream contribution. Use when creating, modifying, or pushing Canvas Code Components, or when deciding which Canvas skill applies.
Expo / React Native iOS interface conforming to Apple Human Interface Guidelines (iOS 26) — native navigation (Expo Router native stack and tabs), platform controls (Alert, ActionSheetIOS, SF Symbols via expo-symbols), safe areas, dark mode, Dynamic Type, haptics, Liquid Glass, accessibility, and 60fps motion. Covers architecture and styling decisions made in React Native/TypeScript; for the @expo/ui SwiftUI component API use the expo-ui skill, and for native Swift use ios-hig. Trigger when building, reviewing, or refactoring such an app — even when the user does not say "HIG" or "native feel" but is writing TSX screens, navigation, lists, forms, or styling for iOS in Expo.
Fix Library.init() apiVersion issues and modernize enums to DataType.registerEnum. Use this skill when linter outputs: - `no-deprecated-api` with message "Deprecated call to ... Use the {apiVersion: 2} parameter instead" Trigger on library.js files with errors about: "Deprecated call to", "Lib.init", "Library.init", "{apiVersion: 2} parameter" Adds apiVersion: 2 to Library.init() calls and modernizes enum definitions to use DataType.registerEnum, which is required for type validation when using apiVersion: 2.
Execute a comprehensive Flutter Project Health Audit. Analyzes tech stack, architecture, state management, testing, code quality, CI/CD, and documentation. Produces a shareable Markdown report with section scores and weighted overall score. Use when the user asks to audit a Flutter project, run a health check, evaluate project quality, or assess technical debt. Triggers on: 'flutter audit', 'health audit', 'project audit', 'flutter health', 'tech debt assessment', 'project quality check'.
UI interaction design patterns for skeleton loading, infinite scroll with accessibility, progressive disclosure, modal/drawer/inline selection, drag-and-drop with keyboard alternatives, tab overflow handling, and toast notification positioning. Use when implementing loading states, content pagination, disclosure patterns, overlay components, reorderable lists, or notification systems.
Comprehensive guide for writing modern Neo4j Cypher read queries. Essential for text2cypher MCP tools and LLMs generating Cypher queries. Covers removed/deprecated syntax, modern replacements, CALL subqueries for reads, COLLECT patterns, sorting best practices, and Quantified Path Patterns (QPP) for efficient graph traversal
(NS) Execute a GitLab issue end-to-end — status gates, worktree isolation, atomic delivery, MR, mandatory code then judge loop. Use for external ISSUE_URL or SDD delivery unit (unit + issue_iid). External Phase 2: single-unit → coder-agent in worktree; multi-unit → ns-autonomous Engine. SDD unit mode uses ns-coder run-implementation. Needs mcp-gitlab-usage + ns-reviewer + ns-judge.
Usage guidelines for the PIE design system by Just Eat Takeaway. Use when building, modifying, or debugging any user-facing web UI; referencing @justeattakeaway/pie-* packages; implementing or generating code from a Figma file; or when the user asks for a UI that should follow JET/PIE design standards.
Azure DevOps Sprint 254-262 new features and enhancements (2025). Proactively activate for: (1) checking what is new in recent Azure DevOps sprints, (2) using new pipeline tasks introduced in Sprint 254+, (3) Azure Boards updates (delivery plans, query enhancements), (4) Azure Repos updates (branch policies, advanced security), (5) Azure Pipelines updates (1ES hosted pools, agent retirement), (6) Azure Artifacts updates (upstream sources, retention), (7) deprecation notices (TFVC, classic pipelines), (8) GitHub Advanced Security for ADO. Provides: sprint-by-sprint changelog, new feature reference, deprecation timeline, and migration notes.
Integrate the Synthesia Interactive Avatar into a LiveKit Agent end-to-end — detects the user's existing LiveKit setup and attaches the avatar with the three-line pattern, or scaffolds a complete boilerplate voice agent if none exists. Use when: (1) adding a real-time, interactive, conversational, or lip-sync avatar to a LiveKit agent, app, or site, or switching/swapping avatars mid-session, (2) the user mentions the Synthesia avatar plugin, livekit-plugins-synthesia, synthesia.AvatarSession, or the Interactive Avatar, (3) migrating from another avatar provider (HeyGen LiveAvatar, Tavus, Beyond Presence, Hedra) to Synthesia, (4) debugging Synthesia avatar issues — SynthesiaError (type AUTH, UNKNOWN_AVATAR, TIMEOUT, ...), avatar never joins, avatar joins but no lip-sync, (5) building any voice agent where the user wants a human face on it, even if they don't name Synthesia explicitly.
Use when using the Three.js WebGPU renderer, node-based materials, TSL (Three Shading Language), or compute shaders. Prevents the common mistake of not checking browser support, missing async init, or using GLSL with WebGPU. Covers WebGPURenderer, node materials, TSL, compute shaders, WebGL fallback, migration guide. Keywords: WebGPU, WebGPURenderer, TSL, Three Shading Language, node material, compute shader, WGSL, MeshStandardNodeMaterial, next-gen rendering, modern GPU, WebGPU setup.
Advanced TypeScript — type-level programming, library/DSL APIs, declaration merging, modern language features at depth (decorators, using, const T, NoInfer, variance), and feature implementation patterns built on advanced types. Trigger on tasks involving recursive conditional types, infer patterns, mapped-type key remapping, variadic tuples, fluent builders with phantom state, schema-first inference (Zod/Valibot), end-to-end-typed API clients, finite state machines, module augmentation, and library-publishing concerns. Trigger even when the user does not say "advanced" — if the work involves type-level algorithms, library-author API design, or going beyond surface-level uses of TS 5.x features, this is the skill. Assumes the reader has absorbed the `typescript-refactor` skill — this one extends those patterns at depth, never restates them.
Master TypeScript's advanced type system, including generics, conditional types, mapped types, and React TypeScript patterns. Use when: (1) implementing complex type logic, (2) creating reusable type utilities, (3) typing React components, hooks, and events, (4) ensuring compile-time type safety.
Advanced bash array patterns including indexed and associative arrays, mapfile/readarray, slicing, and array manipulation (2025). PROACTIVELY activate for: (1) using bash arrays effectively, (2) reading file contents into an array via mapfile/readarray, (3) authoring associative arrays (declare -A), (4) iterating arrays safely under set -u, (5) deleting/inserting array elements, (6) joining and splitting arrays, (7) passing arrays to functions via nameref (declare -n), (8) array slicing and parameter expansion, (9) sorting and deduplicating arrays in pure bash. Provides: indexed and associative array reference, mapfile and readarray recipes, nameref-based pass-by-reference, slicing/expansion patterns, and gotchas for unset variables and word splitting.
Создаёт однозначную спецификацию результата без шагов реализации. Используй, когда пользователь хочет зафиксировать задачу и контекст, целевой результат, рамки и критерии приемки, оставив технический путь исполняющему агенту. Не используй для выбора решения, составления плана реализации, непосредственной реализации или ревью изменений кода.
Track CawPlan release progress for a version: ticket completion, risk level, open items, target release dates, unresolved Critical-priority bugs, features not yet at QA Testing, what's Ready for QA/QA Testing, descope suggestions, what's blocking QA testing, assignee overload, per-QA pending counts, and tickets stale for more than N days. Use when: the user asks to track a release, check release progress, review open tickets for a version, assess release/delay risk, ask what to descope, ask what's Ready for QA / in QA Testing for a version, ask what's blocking QA testing, ask if any assignee has too many high-priority issues piled up, ask how many tickets each QA still has to verify, or ask which tickets haven't been fixed in over N days. NOT for: creating versions or tickets, product-wide metrics dashboards not scoped to a version, user activity summaries, or open-ended critical-issue search across products (use `cawplan critical search` directly for that).
Reviews Spec Kit code changes for consistency with applicable design documents, positive and negative test coverage, regression evidence for bug fixes, and consistent repository terminology. Use when reviewing a diff or pull request. Do not use for implementing changes or posting GitHub review actions.
Decision frameworks for DatoCMS content modeling — schema shape, field choice, content reuse, taxonomies, content vs presentation, admin UI organization. Use for modeling *decisions*, not implementation: model vs block; single_block vs Modular Content vs Structured Text; references vs embedded blocks; taxonomy shape (flat/tree/faceted); refactoring page-shaped schemas to reusable content; fitting 300 KB / 500-block / 5-level record limits; model behaviour (singleton, draft mode, all_locales_required, sortable/tree/ordering_field, presentation_title_field, collection_appearance, inverse_relationships_enabled); field config (validator + appearance — enum + string_select, slug auto-fill, required_alt_title, structured_text allowlists, framed vs frameless single_block). Also schema review (reuse, editor ergonomics, omnichannel). *Creating* schema → `datocms-cli` or `datocms-cma`. Query/render → `datocms-cda` + `datocms-frontend-integrations`
MVVM for .NET desktop apps (WPF, Avalonia, WinForms, MAUI) with CommunityToolkit.Mvvm 8.4+ source generators: [ObservableProperty] partial properties, [RelayCommand] async commands, Generic Host + DI, UI-thread dispatching, navigation, messaging, and testable view models. Load when the user mentions "MVVM", "ViewModel", "WPF", "desktop app", "ObservableProperty", "RelayCommand", "ICommand", "INotifyPropertyChanged", "Dispatcher", or "UI thread"
Best practices for Docker-based ROS2 development including multi-stage Dockerfiles, docker-compose for multi-container robotic systems, DDS discovery across containers, GPU passthrough for perception, and dev-vs-deploy container patterns. Use this skill when containerizing ROS2 workspaces, setting up docker-compose for robot software stacks, debugging DDS communication between containers, configuring NVIDIA Container Toolkit for GPU workloads, forwarding X11/Wayland for rviz2 and GUI tools, or managing USB device passthrough for cameras and serial devices. Trigger whenever the user mentions Docker with ROS2, docker-compose for robots, Dockerfile for colcon workspaces, container networking for DDS, devcontainer for ROS2, multi-stage builds for ROS2, or deploying ROS2 in containers. Also trigger for CI/CD with Docker-based ROS2 builds, CycloneDDS or FastDDS configuration in containers, or shared memory in Docker. Covers Humble, Jazzy, and Rolling distributions across Ubuntu 22.04 and 24.04 base images.
Build, debug, and review Eleventy v3 sites and Nunjucks templates. Use when `package.json` includes `@11ty/eleventy` or `@awesome.me/buildawesome`; when paths include `.eleventy.js`, `eleventy.config.*`, `.njk`, `.11tydata.js`, or `.11ty.js`; when asked to "create an 11ty page", "add a Nunjucks filter", "fix my layout chain", "review my .njk template", "set up Eleventy", or "migrate to Build Awesome" (v4 prerelease); or when debugging Eleventy data cascades, shortcodes, autoescape, or `| safe` output. Standalone Nunjucks work is in scope; generic static-site, SSG, or CSP tasks need confirmed Eleventy or Nunjucks context.
Subscribe to Feishu events in real time (WebSocket). Use event list to view supported EventKeys; event schema to view event payload/scope; event consume to start a persistent subscription, writing the event stream as NDJSON to stdout (blocking; one EventKey per process); event status to view active local consume processes; and event stop to stop consume by PID / EventKey / --all. Supports 22+ EventKeys (im message received/read/recalled/reaction, group member changes, contact employee changes, calendar changes, cloud drive title/collaborator changes, approval instances and tasks, VC meeting start/end). Supports reconnection and parallel subscriptions to multiple EventKeys. Use when the user requests “listen for Feishu events,” “receive message events in real time,” “subscribe to approval callbacks,” “event stream,” “persistent WebSocket listener,” “event consume,” “event list / schema / status / stop,” or “AI Agent bot real-time response.” Note: This skill only handles subscriptions; for event webhook business logic (pushing to Feishu messages/writing to Bitable), use feishu-cli-msg / feishu-cli-bitable.
Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says “start training”, “fine-tune my model”, “I'm ready to train”, or when the plan reaches the fine-tuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom prompt creation.
Fix deprecated `sap.ui.table.Table` row properties that UI5 linter reports but cannot auto-fix. Use this skill when linter outputs: - `no-deprecated-api` with messages about `visibleRowCountMode`, `visibleRowCount`, `rowHeight`, `fixedRowCount`, `fixedBottomRowCount`, or `minAutoRowCount` Trigger on: deprecated row-related properties on sap.ui.table.Table in JS or XML, modernization to rowMode aggregation. Converts deprecated flat properties to a structured `rowMode` aggregation using `sap.ui.table.rowmodes.Fixed`, `Interactive`, or `Auto`.
Fix native HTML and SVG usage in XML views/fragments that UI5 linter reports but cannot auto-fix. Use this skill when linter outputs: - `no-deprecated-api` with message "Usage of native HTML in XML Views/Fragments is deprecated" - `no-deprecated-api` with message "Deprecated use of SVG in XML View or Fragment" Trigger on: HTML elements in XML views (html:div, html:span, html:a), SVG elements in XML views, xmlns:html namespace usage. Provides guidance on replacing native HTML with UI5 controls and SVG with UI5 icons or custom controls.
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
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.