The catalog
610,045 rows, by stacks then stars
FrozenMoon/ui-design-workflow Skill
3★MUST use when implementing UI components or frontend pages in this project. Triggers: designing UI, implement page, develop UI, write component, frontend development, create component, build interface, style page, button, form, modal, toast, card, input, styling, interface, shadcn, ant design, antd, element plus, component library, UI library, 设计UI, 实现页面, 开发UI, 写组件, 前端开发, 创建组件, 构建界面, 页面样式, 按钮, 表单, 弹窗, 提示, 卡片, 输入框, 样式, 界面, 组件库, UI组件, 设计规范, 生成规范, 实现功能, 检查代码, 迭代规范, 切换组件库. Before writing any UI code, load this skill to read the project's design spec.
aawp-ai/aawp Skill
no license3★AAWP (AI Agent Wallet Protocol) — the only crypto wallet protocol built exclusively for AI Agents on EVM-compatible blockchains and Solana. Not for humans. The signer is the AI Agent itself, cryptographically bound at wallet creation. Supports wallet lifecycle management, token transfers, DEX swaps, cross-chain bridging, Solana native trading (Pump.fun SDK + Jupiter), token launches, DCA automation, and price alerts.
Ow1onp/hermes-agent-skills/agents/devops-sre Skill
3★ repoUse when the user needs DevOps or SRE help including CI/CD pipelines, Docker optimization, Kubernetes manifests, infrastructure safety, or production log analysis.
Gary06868/remote-agent-collaboration-skills/plugins/remote-agent-collaboration-lite/skills/team-lead-collaboration Skill
3★ repoMarkdown collaboration Lead. Use only when the user explicitly selects $team-lead-collaboration to organize lightweight project collaboration.
bhaumikmaan/claude-code-master-skills/skills/architectural-planning Skill
3★ repoRead-only codebase analysis and implementation planning. Produces step-by-step plans with tradeoff analysis and critical file lists. Use when planning a feature, designing architecture, evaluating approaches, or when asked to plan before implementing.
Ethics03/kgskill Skill
3★Universal Knowledge Graph for accumulating and organizing knowledge from any source. Use when ingesting documents, answering questions, maintaining wiki pages, or working with project-specific knowledge bases.
devctllabs/mockapi/skills/mockapi Skill
3★ repoCreate stateful TypeScript/Hono mock API servers from OpenAPI 3.0/3.1 contracts. Use for building OpenAPI-based mock APIs, creating or repairing .mockapi sidecars, validating mock profiles, generating admin state endpoints, or freeform requests such as "mockapi build a mock server for api/openapi.yaml".
CercaTrovato/agent-rongchi Skill
3★General discipline rules for coding agents. Use when any agent performs coding, debugging, refactoring, architecture changes, repository edits, test writing or running, tool-driven implementation, or code review. Enforces query-before-guessing, ask-before-ambiguous-execution, human confirmation for business assumptions, reuse before new interfaces, active validation, architecture compliance, honest uncertainty, and cautious refactoring. Chinese triggers: 认知纪律, 八荣八耻, 荣耻, 编码纪律, 主动测试, 遵循规范.
schalkneethling/claude-toolkit/skills/code-review Skill
3★ repoReview code changes for correctness, security, performance, accessibility, maintainability, tests, dependencies, design-system adherence, and localization. Use when the user asks for a code review, PR review, review of local changes, risk assessment, code quality feedback, or actionable findings before merge.
timseriakov/sem-inspect-weave-skill/sem-inspect-weave Skill
3★ repoSemantic version control workflow: sem (structural truth) -> inspect (review prioritization) -> weave (coordination + merge semantics).
momentmaker/kaijutsu/skills/community/code-simplification Skill
3★ repoReduce code without changing behavior. Apply Chesterton's Fence (don't remove what you don't understand) and the Rule of 500 (files over 500 lines usually need splitting). Use when the user says "simplify this", "clean up", "remove dead code", "tighten", or invokes /simplify. Composes polish (review-fix loop) and blunder-hunt (regression risk).
arthjean/skills/skills/baseline-ui Skill
no license3★ repoQuickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast cleanup or polish pass.
The same file is in 2 other repositories
WhizZest/Everything-Search/skills/everything-search Skill
3★ repoProvides comprehensive guidance for using ES (Everything Search) command-line tool. Invoke when user asks about file searching, needs help with es commands, or wants to search files efficiently using Everything.
QinghongLin/paperdoctor/skills/prepare-paper Skill
no license3★ repoOrganize a paper PDF and its codebase into clean reading artifacts. Use this before any other read-* skills.
grusin-db/framework-skill-authoring/framework-skill-authoring Skill
no license3★ repoGenerate a complete, self-contained Agent Skills family for any code framework or library, so that a coding agent which only has the installed package (no source) can use the framework at full capacity. Use when asked to create skills for a framework, document a library for AI agents, build a skill pack / skill family, reverse-engineer a codebase into Agent Skills, turn a framework into something a notebook or IDE assistant can drive from just the installed wheel/jar, or author an entry-router skill plus granular capability skills. Walks an agent that HAS the source through four phases -- analyze, map to a universal capability taxonomy, generate, validate -- and emits an entry router, an always-injected workspace-instructions file, and one capability skill per domain.
roebi/agent-skills/skills/apply-tdd-loop-en Skill
no license3★ repoApplies the Test-Driven Development (TDD) cycle as an agentic loop of RED -> GREEN -> REFACTOR iterations until all requirements are covered or all existing code paths are tested. Use when a user or agent wants to write code strictly test-first, add missing tests to existing code, or drive a full TDD session for a module, class, or function. Activate for trigger phrases like: "apply TDD", "write this test-first", "do a TDD loop", "TDD cycle for", "drive TDD on", "red green refactor", or "add tests then implement".
stdin/buy-vs-build/.openclaw/skills/buy-vs-build Skill
3★ repoUse when coding, designing implementations, choosing dependencies, or reviewing whether a task should use built-ins, platform features, installed packages, open source, commercial services, or in-house code.
zenstackhq/skills/skills/zenstack-access-control Skill
3★ repoAdd access control to a ZenStack V3 schema. Use when writing access policies (@@allow / @@deny), the auth() function, field-level rules, post-update rules, or setting up the policy plugin and $setAuth runtime. (For data validation — @email/@length/@@validate — see zenstack-querying.)
The same file is in 4 other repositories
leek/agent-skills/skills/architecture-satisfaction Skill
3★ repoRun a bounded architectural refactor loop toward a stated design.
wp-a/gpt-5.6-prompt-engine/skills/gpt-5-6-prompt-engine Skill
3★ repoUse when creating, auditing, rewriting, debugging, migrating, or evaluating GPT-5.6 Sol, Terra, or Luna prompt layers, tool descriptions, agent briefs, or prompt stacks; choosing runtime configuration; or comparing controlled prompt candidates.
uzysjung/uzys-agent-harness/.claude/skills/agent-introspection-debugging Skill
3★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 5 other repositories
Doist/twist-cli/.agents/skills/add-command Skill
no license3★ repoGuide for adding new CLI commands or subcommands to twist-cli. Use when implementing new SDK endpoints, adding subcommands to existing command groups, or extending CLI functionality.
emilianoeloi/ios-WK-UI-WebView/.github/skills/concise-output Skill
3★ repoUse when: you want maximum token compression in responses. Removes all filler prose while keeping 100% technical accuracy. Inspired by the Caveman communication pattern.
Cooper-X-Oak/goal-to-do/skills/goal-todo Skill
3★ repoDefine and refine a long-running Codex goal before using `/goal`. Use when the user has a vague multi-step task, wants Codex to work autonomously toward a persistent objective, asks for a final `/goal` prompt, or needs structured interactive alignment on scope, success criteria, constraints, and decision checkpoints before launching a long-running task.
joacod/skills/skills/business-idea-validator Skill
3★ repoEvaluate and pressure-test business, product, SaaS, service, and startup ideas using current evidence, competitive research, decision gates, repair pivots, and a small paid validation test. Use when deciding whether to pursue, test, pivot, park, or drop an idea; comparing ideas; exploring a problem space; assessing customer pain, buyer and workflow clarity, market crowding, founder fit, economics, or defensibility; or updating a verdict after customer evidence. Return a compact decision card, not generic encouragement or a full business plan.
herehere14/Cascade-An-AI-Agent-World-Simulator/extensions/prompt-forest/skills/prompt-forest Skill
no license3★ repoAdaptive prompt routing for planning, verification, critique, code review, and confidence-qualified responses via the Prompt Forest plugin tools.
tjmaynes/skills/skills/agent-context-generator Skill
3★ repoGenerate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks. Use when a repository needs clear agent onboarding covering structure, tooling, testing, task flow, README expectations, and conventional commit summaries.
The same file is in 5 other repositories
callback-io/git-integration-branch-guard/skills/git-integration-branch-guard Skill
3★ repoEnforce a role-based, one-way Git integration branch workflow. Use when a user asks to create, sync, merge, rebase, pull, cherry-pick, push, open a PR, review branch history, or prepare a release in a repository with local work branches, shared dev/test/uat/staging branches, or production branches.
taohaowei/soul-guardian/skills/soul-guardian Skill
3★ repoA persistent AI counselor — it remembers you, speaks Chinese, and keeps everything local. 一位住在终端里的心理咨询师,越聊越懂你。
The same file is in 9 other repositories
robzolkos/zolkos-agent-skills/skills/catchup Skill
no license3★ repoCatch up on codebase changes by reviewing the diff from master and reading relevant spec files.
The same file is in 2 other repositories
retlehs/gitmoji-skill Skill
no license3★Prefixes commit messages and PR titles with an appropriate Gitmoji. Activate when writing or amending commit messages, drafting PR titles, or choosing a Gitmoji for a change.
gerodp/hermes-productivity-skills/analytics/umami-report Skill
3★ repoPer-site visitor & pageview reports from a private (self-hosted) Umami instance.
JayRHa/AgentSkills/0-template Skill
3★ repoTemplate for creating a new Agent Skill. Copy this folder, rename it to your skill's kebab-case name, and fill in every section. Use this as the starting point whenever you author a new skill for the AgentSkills library.
control-decks/think-it-through/plugins/think-it-through/skills/discuss Skill
3★ repoExplore and deepen the thought currently being expressed as an active, neutral thinking partner without forcing a conclusion or changing effects. Use only when the user invokes discuss or asks to reason through something together; never redirect silently.
hcaiano/skills/_deprecated/cmux-pair Skill
3★ repoLegacy cmux-based pair programming bootstrap for Claude and Codex talking through cmux surfaces with an XML protocol. Keep this for historical reference and migration only. Prefer herdr-pair for current Claude/Codex collaboration; use this skill only when the user explicitly asks for the old cmux workflow.
leo-cheung-itlger/api-key-leak-checker-leop/skills/api-key-leak-checker-leop Skill
3★ repoCheck GitHub repositories, local Git projects, AI coding projects, and Vibe Coding apps for possible API key, token, secret, .env, and config leaks. Use when the user asks to scan for leaked keys, exposed credentials, GitHub secret scanning, Gitleaks, TruffleHog, .gitignore hardening, push protection, API key rotation, or remediation after accidentally committing secrets.
arsudsandesh97/Revoact/skills/architecture-doc Skill
3★ repoGenerate a complete ARCHITECTURE.md file for any software system. Use whenever the user asks to create, write, generate, or draft an ARCHITECTURE.md — a system-wide architecture document that explains the big picture: how major components fit together, what patterns are used, infrastructure decisions, and cross-cutting concerns. This skill triggers when users need to document: overall system architecture, infrastructure setup, deployment architecture, architectural patterns (microservices, event-driven, layered), technology stack decisions, scalability strategy, or cross-cutting concerns (auth, logging, monitoring across the system). Do NOT trigger for single-feature technical designs (use Design.md skill), UI/visual design, or code-level implementation details.
GerardoRdz96/rlsgate/skill Skill
3★ repoRun the rlsgate pre-deploy security gate on a Supabase-backed project. Use when about to deploy a vibe-coded / Supabase / Lovable / Bolt / Cursor app, or when the user asks to check for RLS holes, exposed secrets, anon-readable tables, public buckets, or unverified webhooks before shipping.
Ahoo-Wang/skills/plugins/ahoo-agent-skills/skills/agent-system-prompt Skill
3★ repoUse this skill when the user needs to write the actual instructional text that defines how an AI agent behaves. This is the skill for crafting the core "brain instructions" — the system prompt, persona, or behavioral rules that go into making an AI assistant, chatbot, or agent act in a specific way. Trigger for requests to: - Create or design a system prompt, instruction set, or persona for any AI agent - Write the "instructions" field for a custom GPT, Claude project, or similar platform - Define what an AI should or shouldn't do, how it should talk, or what tasks it handles - Help someone make their AI follow specific rules or adopt a particular personality - Improve, refactor, or debug an existing system prompt Also trigger for Chinese queries mentioning: 系统提示词, system prompt, AI 助手, 智能体, 机器人, 人设, or similar terms about defining agent behavior. If the user's goal is to produce written text that controls AI behavior, use this skill. If they need to write code, set up APIs, build infrastructure, or handle technical implementation, they need a different skill. This skill guides you through a structured interview-and-draft process to produce clear, effective system prompts grounded in prompt engineering best practices.
DonkeyKing01/nev-product-search-kit/nev-product-research Skill
3★ repo面向新能源乘用车产品研究的结构化 Skill。用于把市场资料、车型参数、竞品信息、用户评论、车主反馈和访谈材料,转化为可追溯的产品研究交付物。适用于用户要求做产品研究、竞品分析、用户洞察、机会诊断、PRD 前置研究、研究报告、机会卡片或证据驱动的产品判断时。尤其适合“研究某个细分市场”“比较几款车”“从用户声音里提炼产品机会”“输出 final report / pdf 报告”这类请求;不适用于泛泛行业摘要、单纯参数查询、纯营销文案或无证据支撑的观点输出。
mindbox-cloud/agent-skills/plugins/skill-review/skills/skill-review Skill
3★ repoQuick and accessible AI reviewer for Agent Skills — for non-specialists. Checks structure, workflow, references, and links. Produces a clear report without technical jargon. Summary from Exhausted Vitaly. Use when user says "quick review", "basic skill check", "review my skill", "review for product owner", "light review", "quick check", "check my skill", "evaluate skill quality", "what's wrong with my skill", "review this skill". Don't use when: user asks for a deep/nightmare review (use skill-review-nightmare), user asks to create a new skill, to review code, user asks to review a prompt that is not a skill.
resnicdan/skills/skills/knowing-what-you-know-now Skill
3★ repoDecide whether something already built and working is worth rebuilding the elegant way, knowing everything you now know. Run it when a build works as intended and you want an educated keep / refactor / rebuild call before moving on, not a reflexive rewrite.
SwiftyJourney/requirements-engineering-skill/requirements-engineering Skill
3★ repoUse this skill to turn vague, ambiguous, or "lousy" requirements into precise, testable specifications BEFORE any code is written -- even when the user never says "BDD", "use case", or "acceptance criteria". Trigger when someone has a half-baked feature idea, an under-specified ticket, or a business brief that's "open to interpretation" and needs it pinned down: clarifying questions, As-a/I-want/So-that narratives, Given/When/Then acceptance criteria, use cases (data inputs, happy path, error and cancel courses), model-spec tables, request/response payload contracts, flowcharts, and module-dependency diagrams. This is the SPECIFICATION altitude -- WHAT to build and the contracts to honor. Hand off the implementation to the iOS architecture skill (composition root, layers, packages, concurrency), SwiftUI view code, and Swift Testing syntax -- do NOT use this skill to write or refactor that code, only to define what it must satisfy.
Js ts business crud transforms
icyJoseph/agent-skills/skills/js-ts-business-crud-transforms Skill
no license3★ repoWrite JavaScript/TypeScript for business applications (frontend and backend) with CRUD, API integration, and data transforms that are correct, readable, and easy to trust. Use when building or reviewing features involving forms, API responses, list/detail views, aggregations, or request/response shaping so outputs need minimal inspection.
The same file is in 4 other repositories
kinhluan/rules-quarkus-skills/.agent-skills/bazel-expert Skill
3★ repoExpert knowledge for writing idiomatic Bazel rules, Starlark best practices, and build performance optimization. Use for Bazel build system questions.
liutao773680119-cmyk/relay-dev-skills/.relay/skills/relay-dev Skill
3★ repo使用于接力开发总入口。用户如果说“接手这个项目,按接力开发规则来”“给这个项目初始化接力开发”“重新同步当前任务”“做一次标准交接”“按接力开发流程处理这个项目”,优先使用本 skill 统筹分流到对应接力步骤。
SamTerces/claude-sync/skills/claude-sync Skill
3★ repoSync the user's entire Claude brain — memory files, skills, agents, CLAUDE.md rules, and settings — across machines and teammates using a shared Git repository. Trigger this skill when the user wants to: push their Claude context to a remote, pull a teammate's context, see what's different between their local brain and the remote, merge a specific teammate's learnings into their own, onboard Claude on a new machine, or set up auto-sync. Also trigger on: /sync, "sync my claude", "push my memory", "pull team context", "share my brain", "sync to GitHub", "onboard new machine", "what's different from the team", "merge alice's context".
fengshiyangrouguan/Actio_agent/backend/mainsystem/skills/main Skill
3★ repoActio Agent 是一个面向物理交互场景的智能体编排框架。它通过大语言模型进行任务规划与推理,调度VLA模型执行具体的机器人操作,实现从自然语言指令到物理世界动作的完整闭环。
feifeiqiu11-2025/slidewright Skill
3★Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
ADAvault/cardano-skill Skill
3★Write, test, and debug Aiken smart contracts for Cardano. Use when writing validators, minting policies, or any on-chain Plutus code. Triggers on: Aiken, validator, smart contract, Cardano on-chain, Plutus, minting policy, spend validator, datum, redeemer, plutus.json, blueprint. Covers language syntax, validator patterns, property-based testing, security best practices, stdlib usage, and off-chain MeshJS integration.
Orfi/trackbed/claude/skills/trackbed-adr Skill
3★ repoInternal + shared ADR intake/create for Trackbed. Resolve the ADR location, scan and read existing Architecture Decision Records so planning respects them, and gap-fill a new ADR only when there is a genuine uncovered decision. Invoked inside trackbed-init (step 2, for an epic or project) and usable standalone — by a story flow, OR directly on an epic or project when you only need ADRs surfaced or created and do NOT want a roadmap. No manifest, roadmap, or caller is required to run it standalone. Reading existing ADRs is the common case; creating one is the rare exception. Trigger whenever an epic, project, or story needs its recorded architecture decisions surfaced — with or without a roadmap.
aikdna/kdna-skills/kdna-loader Skill
3★ repoUse the official KDNA MCP or CLI for one explicit .kdna file or the current workspace's user-approved attachments. Do not discover, attach, mutate, auto-select outside the approved set, or hide adoption.
Financial astrology pattern search
wauputr4/financial-astrology-skills/skills/financial-astrology-pattern-search Skill
3★ repoUse when researching whether astrological aspect cycles correlate with returns across crypto, equities, ETFs, commodities, FX, or other investment assets using hermetic-alpha-library. Provides a reproducible event-study workflow with train/test validation, anti-overfitting rules, cross-asset checks, and clear publishable reporting.
hec-ovi/agentickit/.pilot/skills/choose-provider Skill
3★ repoPick a model provider for a consumer's app. Covers auto-detection, the six allow-listed prefixes (openai, anthropic, groq, openrouter, google, mistral), the Vercel AI Gateway fallback, and the escape hatch for non-registered providers (Ollama, Azure, Bedrock). Use when the question is "which model string / which env var / which adapter".
Nembie/claude-code-skills/agents/bug-fixer Skill
3★ repoDiagnose bugs through iterative investigation, apply a type-safe fix, and generate a regression test. Use when asked to fix a bug, debug an error, diagnose a crash, investigate a failing test, or resolve an exception.
myksyut/pev-harness/skills/empirical-prompt-tuning Skill
3★ repoagent 向けテキスト指示(skill / slash command / task プロンプト / CLAUDE.md 節 / コード生成プロンプト)を、バイアスを排した実行者に動かしてもらい、両面(実行者の自己申告 + 指示側メトリクス)で評価して反復改善する手法。改善が頭打ちになるまで回す。プロンプトや skill を新規作成・大幅改訂した直後、またはエージェントの挙動が期待通りにならない原因を指示側の曖昧さに求めたいときに使う。
madflojo/learn-this-project/skills/learn-this-project Skill
3★ repoProvides fast, evidence-backed repository triage for unfamiliar codebases and produces a summary of purpose, architecture, tech stack, workflows, conventions, and key files without overstating certainty. Use when the task involves a repo overview, architecture summary, onboarding context, or quick identification of a repository's main components and capabilities.
ivanzwb/agent-skills/skills/stock-analysis Skill
3★ repoA股股票数据分析工具,提供股票搜索、K线数据、基本面数据、板块信息、新闻等。当用户要求分析某只股票、查询股票行情、了解个股基本面、查看K线走势、获取板块信息或相关新闻时,必须使用本技能。
TeXmeijin/claude-case/skills/case Skill
3★ repoOpens a browser UI for the user to answer multiple-choice design/policy decisions with recommended defaults, per-question free-text override, and shared notes; returns structured JSON. TRIGGER when about to enumerate '1. X? 2. Y? 3. Z?' style questions in chat, or when presenting 2+ decisions at once, or when a single decision has a clear recommendation worth an explicit ack. トリガー: 「いくつか方針を決めて」「選択肢を整理して」「推奨つきで意思決定したい」「〜にするか〜にするか」。SKIP: a single yes/no confirmation, or a question whose answer is derivable from code/conversation.
ChrisLamDev/cua-desktop-automation-skills/skills/auto-gui-debug-loop Skill
3★ repoGeneral-purpose GUI debugging loop — use Cua Driver + Vision AI to automate any desktop GUI app with screenshot analysis and automated click/verify flow