Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 437 files from 1 744 authors, of which 61 785 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Expert guidance on Swift Concurrency best practices, patterns, and implementation. Use when developers mention: (1) Swift Concurrency, async/await, actors, or tasks, (2) modern concurrency patterns or structured concurrency, (3) migrating to Swift 6 or strict concurrency checking, (4) data races or thread safety issues, (5) refactoring closures to async/await, (6) @MainActor, Sendable, or actor isolation, (7) concurrent code architecture or performance, (8) concurrency-related linter warnings, (9) AsyncSequence, AsyncStream, or task groups, (10) nonisolated, @preconcurrency, or @unchecked Sendable.
Linear CLI for issue tracking and project management. Use when developers mention: (1) Linear issues or tickets, (2) issue tracking or task management, (3) WDY team issues, (4) closing, updating, or triaging tickets, (5) linking PRs to issues, (6) issue states (triage, backlog, started, completed).
Expert guidance on Hummingbird 2 web framework. Use when developers mention: (1) Hummingbird, HB, or Hummingbird 2, (2) Swift web server or HTTP server, (3) server-side Swift routing or middleware, (4) building REST APIs in Swift, (5) RequestContext or ChildRequestContext, (6) HummingbirdAuth or authentication middleware, (7) HummingbirdWebSocket, (8) HummingbirdFluent or database integration, (9) ResponseGenerator or EditedResponse.
Expert guidance on building Swift database client libraries. Use when developers mention: (1) building a database driver, (2) wire protocol implementation, (3) connection pooling design, (4) state machines for protocol handling, (5) NIO channel handlers for databases, (6) backpressure in result streaming, (7) actor executor alignment with NIO.
Expert guidance on SwiftNIO best practices, patterns, and implementation. Use when developers mention: (1) SwiftNIO, NIO, ByteBuffer, Channel, ChannelPipeline, ChannelHandler, EventLoop, NIOAsyncChannel, or NIOFileSystem, (2) EventLoopFuture, ServerBootstrap, or DatagramBootstrap, (3) TCP/UDP server or client implementation, (4) ByteToMessageDecoder or wire protocol codecs, (5) binary protocol parsing or serialization, (6) blocking the event loop issues.
Expert guidance on Swift best practices, patterns, and implementation. Use when developers mention: (1) Swift configuration or environment variables, (2) swift-log or logging patterns, (3) OpenTelemetry or swift-otel, (4) Swift Testing framework or @Test macro, (5) Foundation avoidance or cross-platform Swift, (6) platform-specific code organization, (7) Span or memory safety patterns, (8) non-copyable types (~Copyable), (9) API design patterns or access modifiers.
Wendy Cloud testing skill — supplies test commands, stack setup, and failure-mode knowledge for the cloud monorepo. Use when: (1) running Swift broker or Go services integration tests, (2) checking whether the local dev stack is healthy, (3) diagnosing enrollment or certificate errors, (4) verifying device reachability. Pair with /wendy-iterating to drive a continuous fix loop.
Expert guidance on using Valkey and Redis with Swift. Use when developers mention: (1) Valkey or Redis in Swift, (2) valkey-swift library, (3) RESP protocol or RESP3, (4) Redis cluster routing or hash slots, (5) pub/sub or subscriptions, (6) Redis transactions or MULTI/EXEC, (7) caching with Redis.
Expert guidance on contributing to WendyOS: Yocto builds, agent internals, E2E testing, and system architecture. Use when developers mention: (1) building WendyOS images, (2) meta-wendyos layers or bitbake, (3) wendy-agent development or internals, (4) containerd or nerdctl on WendyOS, (5) E2E tests for wendy-agent, (6) Yocto recipes or bbappend files, (7) mDNS/Avahi service configuration, (8) device identity or UUID generation.
General-purpose iterate-fix-and-ship loop for any codebase. Use when: (1) running a continuous bug-fixing loop, (2) iterating on a feature until all tests pass, (3) driving worktree-per-fix PR workflows autonomously. Pair with a project-specific testing skill (e.g. /wendy-cloud-testing) that supplies test commands and failure-mode knowledge.
Expert guidance on deploying Wendy applications and infrastructure to Google Cloud. Use when: (1) deploying anything to GCP, (2) writing or changing Pulumi programs, (3) creating GCP service accounts, IAM roles, or custom roles, (4) touching wendy.sh / wendy.dev DNS records, (5) choosing GCP compute or databases, (6) setting up CI/CD deployment to GCP, (7) provisioning Cloud Run, Cloud SQL, or Artifact Registry.
Expert guidance on building WASM apps for Wendy Lite MCU firmware on ESP32-C6. Use when developers mention: (1) Wendy Lite or wendy-lite, (2) WASM apps on ESP32 or microcontrollers, (3) WendyLite Swift package or import WendyLite, (4) building C/Rust/Swift/Zig apps for ESP32, (5) WAMR runtime on embedded devices, (6) GPIO/I2C/SPI/UART/NeoPixel from WASM, (7) Embedded Swift on WASM or wasm32-none-none-wasm, (8) BLE provisioning on ESP32-C6, (9) uploading WASM binaries to MCU, (10) TLS/networking on ESP32 from Swift.
Curated Swift package ecosystem for WendyOS and Linux. Use when developers mention: (1) Swift packages for Linux or ARM64/AMD64, (2) choosing a Swift library, (3) Swift Package Index, (4) swiftpackageindex.com, (5) what Swift library to use, (6) Swift on WendyOS dependencies, (7) edge computing Swift libraries.
Expert guidance on building and deploying apps to WendyOS edge devices. Use when developers mention: (1) Wendy or WendyOS, (2) wendy CLI commands, (3) wendy.json or entitlements, (4) deploying apps to edge devices, (5) remote debugging Swift on ARM64, (6) NVIDIA Jetson or Raspberry Pi apps, (7) cross-compiling Swift for ARM64.
| 雅思数据诊断 + 个人化备考计划生成。读历史数据，输出诊断报告和每日训练计划。 触发方式：/ielts-diagnosis、「诊断」「备考计划」「帮我分析」「我的弱项在哪」
| 雅思写作批改教练。四维评分 + 句子级标注 + 改写对比 + 审题检查 + 历史追踪。 触发方式：/ielts-writing、「批改作文」「帮我看看这篇」「审题」「写作练习」
| 雅思口语素材工厂。话题分组 + 万能故事生成 + Part 3 追问预测 + 高分表达 + 练习追踪。 触发方式：/ielts-speaking、「口语素材」「话题分组」「万能故事」「Part 2 准备」
| 雅思备考 AI 教练系统入口。路由到写作 / 阅读 / 口语 / 听力 / 词汇 / 诊断 / Dashboard 训练。 触发方式：/ielts、「我要备考雅思」「雅思怎么准备」「IELTS」
| 雅思阅读精读教练。同义替换提取 + T/F/NG 逻辑拆解 + 段落结构分析 + 错题诊断 + 同义替换库累积。 触发方式：/ielts-reading、「分析阅读」「这道为什么错」「同义替换」「阅读训练」
| 雅思听力错题分析 + 精听训练 + 题型追踪。逐题拆解错因，Section 得分分析，推荐精听任务。 触发方式：/ielts-listening、「听力」「错题」「精听」「听力怎么练」
| 雅思词汇训练。间隔重复复习 + 同义替换专项 + 场景词汇积累 + 拼写检查。 触发方式：/ielts-vocab、「背单词」「词汇」「复习」「同义替换」「拼写」
| IELTS 学习数据可视化 Dashboard。生成本地 HTML 网页，展示写作趋势图、四科雷达图、错题热力图、同义替换统计、考试倒计时。 触发方式：/ielts-dashboard、「Dashboard」「看数据」「打开数据面板」
Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the recommended path: LiveKit Cloud + LiveKit Inference. REQUIRES writing tests for all implementations.
Generate targeted test scenarios for a LiveKit voice or chat agent and run them as simulations — locally, from the agent''s own code plus what the user wants stress-tested. Use whenever the user wants to "test my agent", "what should I test", "create/generate simulation scenarios", "make a sim test suite", "use lk agent simulate", "stress-test the X flow", "set up scenarios for my agent", or wants to probe edge cases / refusals / regressions before shipping. Generates scenarios on the user''s machine (their code is never uploaded) and lets the user deeply steer what gets tested. Trigger even without the word "simulation" when the user clearly wants to decide what to test and verify how their agent behaves across realistic conversations. Not for building a new agent from scratch (use the livekit-agents skill), load-testing, or ordinary unit tests.
Create, audit, compact, or update repository instruction files such as AGENTS.md, nested AGENTS.md, AGENTS.override.md, and optional CLAUDE.md compatibility files. Use when an agent should deterministically scan instruction sources, project manifests, declared commands, CI, documentation, and tool-specific precedence before producing concise project guidance instead of a large generic repository manual.
Generate or update a project-specific DESIGN_SYSTEM.md that enforces consistent UI/UX across SPAs, traditional server-rendered sites, and hybrid systems. Use for design tokens, reusable component rules, UI source-of-truth conventions, animation/transition/custom class rules, accessibility gates, visual QA, Playwright screenshot guidance, and production asset/manifest requirements.
Guidelines and workflow for working on Laravel 11 or Laravel 12 applications across common stacks (API-only or full-stack), including optional Docker Compose/Sail, Inertia + React, Livewire, Vue, Blade, Tailwind v4, Fortify, Wayfinder, PHPUnit, Pint, and Laravel Boost MCP tools. Use when implementing features, fixing bugs, or making UI/backend changes while following project-specific instructions (AGENTS.md, docs/).
Create, reorganize, audit, clean up, or update proportionate documentation for monorepos and single-project repositories. Use for documentation architecture, source-of-truth ownership, minimal routing indexes, module or feature docs, API contracts, workflows, runbooks, optional roadmaps and delivery records, documentation-churn reduction, and removing obsolete plans, notes, archives, or stale references that pollute agent context.
Diagnose and improve performance with measurements and source-of-truth constraints. Use when the user reports slowness, latency, high CPU, high memory, slow queries, N+1 issues, large payloads, slow builds, slow tests, rendering lag, bundle size, Core Web Vitals, caching, pagination, image/font loading, queues, background jobs, or asks to profile, optimize, speed up, or reduce resource usage.
Generate Docker Compose and Dockerfile configurations for local development through interactive Q&A. Supports single-app and monorepo PHP/Laravel, WordPress, Drupal, Joomla, Node.js, and Python stacks with live reload, dependency installer jobs, Nginx/reverse proxy routing, databases, Redis, queues, schedulers, and email testing. Use when designing local dev stacks that differ from optimized production images.
Design, verify, and refactor admin dashboard, internal dashboard, customer/user management dashboard, back-office console, and reporting UI. Use only for dashboard-style management systems with operational workflows such as metrics, stat cards, filters, data tables, CRUD/list/detail pages, forms, side panels, admin shells, Playwright/browser UI verification, screenshot-based dashboard fixes, or visual QA for operational interfaces. Do not use for general UI/UX design, marketing pages, landing pages, portfolios, product sites, games, or consumer app screens unless the task is specifically an admin or management dashboard.
Reproduce, isolate, and fix software bugs without guessing. Use when the user reports errors, stack traces, crashes, regressions, logs, broken behavior with unknown cause, flaky behavior, incorrect business logic, UI bugs, integration failures, failing tests or CI failures with unclear root cause, or asks to debug, investigate, diagnose, or find the root cause of a problem.
Implement frontend UI/UX from user-approved concepts, mockups, screenshots, visual references, or a website the user wants to emulate or clone. Use when Codex must generate and compare UI concepts, recommend a concept as a technical leader, predict the user's likely preference, persist the chosen concept outside commits, recreate a reference site's look and interactions in an existing project, or verify before/after UI with Playwright, Playwright MCP, Chrome DevTools MCP, screenshots, and responsive checks.
Universal project development workflow for safe, maintainable, proportionate software changes. Use when creating or modifying code, documentation, UI/UX, tests, architecture, design systems, debugging workflows, performance work, deployment preparation, or multi-repository features. Enforces source-of-truth-first discovery, reuse before creation, smallest-reliable-solution decisions, dependency judgment, scoped verification, and visual QA for UI tasks.
Plan, add, repair, and run tests and verification for software changes. Use when the user asks for tests, coverage, QA, acceptance criteria, regression checks, CI test failures, Playwright or browser verification, UI screenshot comparison, visual regression, or when a code change needs a focused test strategy across frontend, backend, API, or full-stack workflows.
Deliver a large implementation plan, architecture migration, refactor, or feature roadmap as right-sized, coherent subtasks that are meaningful to code, review, test, and recover independently. Use only when the user explicitly requests this skill or workflow, or explicitly accepts it after an optional proposal during a user-initiated brainstorming or planning session before coding. Do not use for ordinary coding requests with clear requirements and no prior user-requested brainstorming or discussion. This skill does not authorize subagents; before any spawn, explain the usage impact and obtain explicit user approval for the proposed agent count and scope.
Plan and implement secure production deployments of Docker Compose applications on self-hosted VPS or cloud servers using Docker Engine, Docker Compose, Traefik, private registries, SSH tunnels, least-privilege users, persistent volumes, backups, DNS, and storage growth planning. Use when an AI agent needs to design, review, document, or execute a real deploy for websites, APIs, websockets, workers, databases, and object storage integrations on Ubuntu or Debian style Linux hosts.
Comprehensive Tailwind CSS v4 documentation snapshot and workflow guidance. Use when answering Tailwind v4 questions, selecting utilities/variants, configuring Tailwind v4, or migrating projects from v3 to v4 with official docs and gotcha checks.
Search the internet with Google or DuckDuckGo, inspect results, and extract selected pages as readable Markdown. Use when answers require current web sources, JavaScript-rendered pages, or browser access that can handle bot protection. Prefer dedicated tools such as GitHub CLI for GitHub data and curl for direct files or simple URLs.
Use fresh-context specialists to challenge regression risk before implementation, then verify the smallest correct change. Use only when the user says "preflight," asks for a risk gate, or explicitly requests this workflow. Never auto-invoke it.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.
When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' or 'sharpen the messaging.' Use this when the user already has copy and wants it improved rather than rewritten from scratch. For writing new copy, see copywriting.
Use this skill when reviewing, designing, or improving a workshop, lesson, training session, facilitation plan, talk, or educational explanation. Use it when the user provides a topic, concept, or explanation and wants better framing questions, curiosity hooks, opening prompts, discussion questions, learner reflection prompts, or ways to make participants think before being taught.
Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.
Administer the backlog tooling ecosystem when a capability gap is discovered. Invoke when backlog.py, backlog skills, or backlog agents lack a needed operation and a workaround was used or is about to be used. Classifies gaps as script (delegates to @python-cli-architect), process (loads improve-processes), or documentation (delegates to @contextual-ai-documentation-optimizer). Scope — backlog.py, create/work/groom-backlog-item skills, backlog-item-groomer agent, hooks, templates, references, rules, and tests.
Activates Standard of Excellence enforcement for the current session. Load before starting any task to apply completion standards: finish the whole thing, fix the root cause, ship the complete working result. Blocks partial solutions, workarounds, deferred threads, and invented content limits when the permanent solve is within reach. Triggers: 'do the whole thing', 'boil the ocean', 'standard of excellence', 'finish it completely', before starting any implementation, refactoring, or multi-step task where partial output is a risk. Does NOT apply to: read-only queries, one-line typo fixes, pure knowledge questions, or single-output summarize requests.
Generates and commits conventional-commits messages by analyzing staged git diffs — fast and fork-context safe. Use when the user asks to commit staged changes, needs a type-scope-description message generated from the current diff, or wants scope selection guidance and pre-commit hook handling.
Close a completed GitHub milestone and generate a completion summary. Use when a sprint or release is finished and needs to be officially closed. Audits open and closed issues, offers to carry forward open items to a new or existing milestone, closes the milestone, updates Project V2 Status to Done for closed issues, and produces a completion report.
Explains Chain of Verification (CoVe) prompt design — a 4-step pattern separating generation from independent factual verification. Use when designing prompts that require factual accuracy, reducing hallucinations, checking technical standards or APIs, or producing step-by-step procedures where subtle errors are costly.
Analyze git branches and generate structured MR/PR descriptions with domain-based change categorization — bug fixes, enhancements, technical debt, documentation, testing, build/CI, and non-functional changes. Use when preparing merge request descriptions, pull request bodies, writing changelogs from git diffs, documenting branch changes, or generating release notes. Works with GitHub and GitLab without requiring JIRA or issue tracker integration.
Creates a GitHub milestone on the current repository and returns its number for downstream use. Use when starting a new sprint, release, or theme grouping of backlog items. No args triggers guided intake (title, due date, description); 'quick {title}' skips to description only. Checks for duplicates before creating. Returns milestone number for /group-items-to-milestone.
Create GitHub Releases with AI-analyzed changelogs for every calendar day with commits on origin/main. Use when creating daily release notes, backfilling releases, or generating AI-categorized changelogs per day. Uses collect → bucket → analyze → synthesize → publish pipeline via Haiku subagents. Idempotent — skips up-to-date days, updates releases where new commits were added. Accepts optional --start-date, --end-date, --branch, and --dry-run arguments.
Delegation prompt template enforcing WHERE-WHAT-WHY structure for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Agent tool, preparing prompts for specialized agents, or needing the OBSERVATIONS-SUCCESS-CONTEXT format with authoring rules and pre-send checklist. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.
Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents generic AI aesthetic — soft gradients, glassmorphism, hero sections in dashboards, oversized rounded corners, and decorative copy. Applies constraints from Linear/Raycast/Stripe/GitHub design philosophy for functional, honest, human-designed interfaces. Triggers on UI generation, dashboard building, component creation, CSS styling, landing page design, or any task producing visual interface code.
Validate and iterate on the SDLC Layer Separation Architecture implementation across 6 check categories — cross-references, doc completeness, knowledge-explorer layer filters, research entry metadata, integration points, and plan consistency. Produces a structured findings report and optionally applies safe fixes. Use when validating a first-pass implementation, before claiming layer work complete, auditing layer docs or schema, or running --dry-run to preview findings without changes.
Test harness for Claude Code skill argument substitution — demonstrates capture-block pre-declaration, XML tag referencing, unintentional variable corruption in code blocks, and correct placement of shell examples in reference files. Use when verifying substitution behavior before applying a pattern to other skills, testing how arguments flow from skill invocations, or understanding the pre-declaration and reference file pattern with greet/farewell/inspect actions.
Integrates patterns from external sources (URLs or local files) into local skills, agents, and plugins. Use when comparing external agent definitions against local equivalents, extracting best practices from frameworks like GSD or BMAD-METHOD, enhancing local skills with external workflow patterns, or adding interoperability with external tool ecosystems. Runs a 3-phase workflow — parallel candidate mapping, contextual enhancement, and validation — with source attribution and backlog tracking for deferred enhancements.
Verifies claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that must use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Use when items are marked UNVERIFIED or when verifying tool API claims, CLI flags, or documented software behavior.
Wraps investigation requests with evidence-chain discipline. Use when asked to find out why something happens, research a root cause, debug an issue, or investigate unexpected behavior. Transforms vague investigation requests into reproducible-proof investigations with a 5-step protocol — disambiguate, reproduce, read source, build evidence chain, present findings. Invoke with /find-cause followed by a description of what to investigate.
Claude Skills — questions
Answers built from the skills we actually parsed.