The catalog
608,253 rows, by stacks then stars
KKenny0/loom-skills/debate Skill
no license0★ repo辩证推理 — 通过扬弃达到更高层次理解,不是罗列正反方。输入主张、争议、Source Brief Disputes 或 Synthesis Pack Conflicts,输出结构化辩证记录(钢铁侠建构 → 反题 → 扬弃)。当用户想要辩证分析争议、钢铁侠论证、压力测试主张、"把问题辩一辩"、或理解对立观点各抓住了什么时使用。
Improving feature completeness
pacho-h/ssep/skills/improving-feature-completeness Skill
0★ repoAudits a working feature for the gap between "happy path passes" and "production-ready" — edge cases, error handling, loading/empty/error states, a11y, responsive, i18n, observability, ops hooks. Use when a feature works but needs polish, for "완성도 높여줘", "production ready로", "edge case 검토", "polish this feature", "is this ready to ship?", "엣지 케이스 다 챙겼나", "PR 전 점검", "빠진 상태 없나", or before shipping any non-trivial feature. Also triggers proactively right before PR creation on a non-trivial branch. Triggers even when the diff is small or the happy path was verified manually; gaps emerge from state interactions (empty/loading/error/disabled, role and locale variants), not line count, and "I already clicked through it in Playwright" does not substitute for the audit. Distinct from brainstorming (designs), test-driven-development (implements), and requesting-code-review (evaluates structure); raises the bar of a working impl via production-readiness audit.
prilk-consulting/frappe-agent-kit/skills/add-custom-field Skill
0★ repoStep-by-step workflow to add a custom field to another app's DocType (e.g. Customer, Sales Invoice) from your own app, idempotently via install.py. Use when the user asks to add a field to a standard/ERPNext doctype, extend Customer with X, or store extra data on an existing DocType.
sirzzang/claude-code-weekly-review Skill
no license0★Claude Code 사용 습관의 주간 변화를 추적하고 개선 여부를 확인하는 스킬. "주간 회고", "weekly review", "습관 추적", "지난주 대비", "프롬프트 개선됐어?", "사용 패턴 변화", "트렌드" 등의 요청 시 트리거한다. 단발성 프롬프트 품질 분석이 아니라 시계열 변화 추적이 목적이므로, "이번 주 어땠어", "나아지고 있어?", "개선 포인트 확인" 같은 맥락에서도 트리거한다.
kaixin1seu/retrospective-system/.claude/skills/retro-coding Skill
no license0★ repo代码复盘——从正确性、健壮性、安全性、可维护性、性能等维度深度挖掘
zxt6991-source/fitness-agent/plugins/fitness-agent/skills/fitness-agent Skill
no license0★ repoOperate the local Fitness Agent CLI for Strava and Obsidian workflows. Use when Codex needs to authenticate with Strava, list or fetch Strava activities, export workout data as Obsidian-compatible Markdown, configure a local Obsidian vault path, or write/sync workout notes into a vault from the local fitness-agent project.
quanpersie2001/pulse/.claude/skills/gitnexus/gitnexus-cli Skill
no license0★ repoUse when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
The same file is in 3 other repositories
paidaxing1234/patrick-skill/skills/patrick Skill
0★ repo让 Claude 全程用「派大星」(《海绵宝宝》里那只粉红色海星)的口吻陪你写代码、修 bug、聊架构、做运维—— 又傻又热情又爱玩梗,但正事认真干、技术结论零妥协。梗在外壳,专业在内核。 当用户想要轻松搞笑的对话氛围,或说「用派大星语气 / 派大星模式 / 皮一下 / 海绵宝宝那个海星」时使用。 触发词:派大星、派大星语气、派大星模式、海绵宝宝、皮一下、贫一点、Patrick、Patrick Star、patrick voice、patrick mode。 不适用:用户明确要求严肃/正式输出(对外邮件、正式文档、给客户的报告、合同)、 线上事故复盘等高压场景;或用户说「别贫了 / 正经点 / 收一收」时——此时自动收敛语气,只保留专业内核。
clever-cc-plugins/cc-handoff/plugins/cc-handoff/skills/handoff-install Skill
0★ repoAdd handoff support to the current project. Use when the user says install handoff, set up handoff, add handoff to this project, or enable handoff.
michtio/mailchimp-claude-skills/mailchimp-multilingual Skill
0★ repoPlan and build multilingual Mailchimp campaigns where one audience holds members in multiple languages, or where a brand sends across multiple markets. Use this skill when the user mentions multilingual email, multiple languages in one audience, language segments, MC_LANGUAGE, IF:MC_LANGUAGE conditional blocks, audience-level language preference, per-language content, NL/FR/DE Belgian sends, DE/FR/IT/RM Swiss sends, EN/FR Canadian sends, EN/ZH/MS/TA Singaporean sends, multi-market syndication, forking templates per market, per-market regulatory footers, or "we ship this email in three languages." Also use when the user has a single audience and asks how to localize the body of an email per recipient, or wants to choose between language segments + separate campaigns vs a single conditional campaign. Do NOT use for single-language Mailchimp templates (use mailchimp-template-language directly), for generic web/app i18n, or for professional translation workflow tooling.
Chengyu adapt to changing circumstances
evnchn-agentic/chengyu-skills/chengyu-adapt-to-changing-circumstances Skill
0★ repoUse when the original plan needs to flex mid-flight in response to new information / changed inputs / discovered constraints — but flexibility WITHOUT defined scope degenerates into either rigid plan-sticking or unbounded winging-it. CRITICAL Step 0 (mirror of chengyu-close-door-catch-thief): scope MUST be defined before any deviation. If operator hasn't given a flexibility-scope tier, agent must PROPOSE 2-4 tiers and let operator pick where the line is. Default tier is "don't do irreversible damage to hardware, software, and data" but context shifts the boundary (hackathon, prod deploy, code review session all have different tier shapes).
spider-rs/spider-claude-plugin/skills/spider-browser Skill
0★ repoDrive a real remote browser with Spider Cloud — open a session, navigate, click, fill forms, run JavaScript, screenshot, and read page content, with smart retry, browser switching, and stealth escalation. Use for multi-step browser automation: logging into a site, filling and submitting forms, scraping JS-rendered pages, or anything needing an interactive session.
withvibe/withvibe-skills/skills/install-withvibe Skill
0★ repoHelp a user install WithVibe on their own laptop or server for the first time. Trigger when a user asks to install, set up, get started with, try, or run WithVibe locally — including phrasings like "how do I install withvibe", "I want to try withvibe", "set up withvibe on my mac", "withvibe quick start", or "what do I need to run withvibe". This is the friendly first-time-user path; it assumes the user wants the easiest install (npm registry) unless they say otherwise, walks them through prerequisites with OS-appropriate commands, runs the guided `withvibe init`, and verifies the stack came up.
xchuan-li/learn-from-project Skill
0★Take a project an AI built for you (or any unfamiliar repo) and make it YOURS — understand it well enough to explain it, trust it, and extend it as if you wrote it. It maps the code structure, walks the implementation logic in plain language, names and explains the concrete engineering used (which libraries, which APIs, which language features), AND surfaces the higher concepts (e.g. causal intervention, bootstrap CIs). Built for people who ship fast with AI but don't have a deep engineering background and need to actually own the result. Use this whenever someone wants to UNDERSTAND or LEARN a project they didn't hand-write: "Claude built me this, help me understand it", "explain this repo / codebase to me", "break down / decompose this project", "what libraries and APIs does this use and why", "walk me through how this code works", "I vibe-coded this and don't get it", "onboard me to this code", "make this project mine", "extract the knowledge from this project". Trigger it even when they don't say "learn" but are clearly trying to make sense of an unfamiliar (especially AI-written) project. Do NOT use it for fixing a specific bug, adding a feature, or a ship-time code review — this is for comprehension and ownership.
MatterAIOrg/cludcode/skills/orb-index-status Skill
0★ repoShow the current indexing progress and status.
realraelrr/handoff-skill/.claude/skills/handoff Skill
0★ repoCompact Codex and Claude Code sessions into concise handoff documents for fresh LLM agent sessions.
The same file is in 5 other repositories
jiayi-ThE-CREATOR/es-coach-skills/skills/es-coach Skill
0★ repo就活ESの対話型添削コーチ。蒸留知識(内定者パターン)に基づき、ES文を受け取り→添削→修正ループ→提出サインオフまで伴走する。/es-coach で起動。
9uiLe/plugins/plugins/agent-ops/skills/agent-handoff Skill
0★ repoOperate handoff-driven delegation to model-strategy-selected external agents: write canonical handoff instructions, choose the target-specific headroom execution route, design gates, and audit evidence. Japanese triggers: 「Claude Code に作業させて」「Codex に作業させて」「指示書を作成して委譲して」「外部エージェントに実装させて」「監督とレビューを担当して」.
konglong87/nano-banana-pro-china Skill
0★Use when generating images using Nano Banana Pro (Gemini 3 Pro Image) with predefined templates or editing existing images. Ensures consistent team image structure through Cloudflare Gateway + OpenRouter API. Supports template-based generation and free-form editing.
konglong87/rag_skills_ali Skill
no license0★Use when needing to search or retrieve information from Alibaba Cloud Bailian knowledge base, when user asks about knowledge base queries, document retrieval, semantic search, or any Bailian-powered information lookup
ehzawad/claude-coterie Skill
0★Adaptive, context-driven Claude Code council for project implementation, computer science, software/ML engineering, DevSecOps, research, and other complex work: Codex orchestrates role-framed persistent Claude Code agents to collaborate and reconcile toward one shared goal. Use for direct invocation $claude-coterie or when the user invokes "claude council," "claude coterie," or "claude team." On invocation, reconstruct what the user is actually doing, compose task-specific roles with no built-in catalog, share the decision-complete context, announce the panel, and launch without a manual approval gate. A one-role panel uses the same council workflow.
Xza2792/ui-ux-audit-skill/ui-ux-audit Skill
0★ repoComprehensive UI/UX quality audit and prevention system that catches the failures AI consistently ships, including broken or shifting layouts, text overflow, inconsistent components, missing states, poor contrast, undersized touch targets, accessibility violations, performance jank, and generic "AI slop" aesthetics. Use whenever the user asks to audit, review, check, critique, fix, polish, optimize, or improve any UI, page, screen, component, screenshot, or design, or says things like "the layout looks off", "something feels wrong", "this looks AI-generated", "is this ready to ship", "weird spacing", "ugly", or "broken page". ALSO consult this skill silently BEFORE writing or editing any UI code (React, JSX, HTML, CSS, Tailwind, React Native, Expo) so these failures never ship in the first place. Works on any project with no setup, and ships with switchable project-category profiles (example kids-app, SaaS/dashboard, marketing/landing, e-commerce) plus a simulate-the-user-first method; supports adding your own profile.
The same file is in 1 other repository
qkitzero/kage-bunshin/.claude/skills/brainstorm Skill
0★ repoMulti-perspective brainstorming session. Use when the user wants to generate and evaluate ideas on a topic. Triggered by idea generation, brainstorming, "any good ideas?", wanting new solutions, or creative suggestions.
fathanghani864/oh-my-openclaw/src/presets/apex/skills/agent-browser Skill
no license0★ repoBrowser automation via playwright-cli - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.
Byunk/claude-code-essentials/essentials/skills/building-agent-tools Skill
0★ repoGuide for creating effective tools for AI agents. Use when building MCP tools, agent APIs, or any tool interface that agents will consume. Focuses on token efficiency, meaningful context, and proper namespacing.
The same file is in 6 other repositories
KeerthiNingegowda/claude_skills_exploration/meeti_skill_files/meeti-skill-final Skill
0★ repoFormats and summarizes meeting transcripts into clear, concise, actionable notes. Use when processing meeting transcripts, notes, or recordings for any meeting type including 1:1s, standups, team discussions, knowledge transfer sessions, or general meetings. Transforms raw transcripts into structured summaries with action items, decisions, and follow-ups.
evgeny-trushin/claude-skills-collection/shopping/03-coles-invoice-processor-claude-skill/coles-invoice-processor Skill
no license0★ repoProcesses Coles grocery invoices to extract structured data and predict future orders. Use when user uploads/pastes invoice content, asks to analyze grocery purchases, or wants shopping predictions.
magnusrodseth/aoc-2025/.claude/skills/aoc-orchestrator Skill
no license0★ repoMain coordinator for the automated Advent of Code workflow. Orchestrates puzzle fetching, TDD solving, and submission for daily AoC challenges. Use when running the full automated solving pipeline or when user requests to solve an AoC day.
DaveRobinson/claude-skill--gutenberg-block Skill
no license0★Best practices for creating custom WordPress Gutenberg blocks with React/TypeScript, covering scaffolding, block architecture, attributes, dynamic vs static rendering, and testing
ChristopherA/claude_code_tools/skills/git-worktree Skill
0★ repoInteractive skill for git worktree operations. Safely converts standard repos to worktree form, creates/lists/removes worktrees, and troubleshoots issues. Uses WORKTREES/GITHUB/{owner}/{repo}/ workspace structure for organization. Preserves inception commits (Open Integrity pattern) during conversion. WHEN: User says "clone worktree", "create worktree from", "get worktree from", "convert to worktree", "create worktree for", "list worktrees", "remove worktree", "troubleshoot worktrees", "validate worktree", OR mentions working with multiple branches simultaneously. WHEN NOT: Standard git operations (commit, push, pull), single-branch workflows, or when user explicitly wants standard repo structure.
rxxuzi/hype/skills/hype Skill
0★ repoDocument-driven development with test-gated progression. Enforces a disciplined workflow: plan tasks with the user in .hype/TODO.md, document before implementing, track progress in .hype/PROGRESS.md, accumulate project knowledge in .hype/KNOWLEDGE.md, and require all tests to pass before advancing. Language-agnostic — works with any programming language or even non-code projects. Use when: (1) starting new projects with structured planning, (2) implementing features or bug fixes with mandatory test verification, (3) managing development tasks with document-based tracking, (4) the user mentions "hype", "document-driven development", "TODO tracking", or wants a disciplined plan-document-implement-test cycle.
kongyo2/markdown-skill-creator/markdown-skill-creator Skill
no license0★ repoGuide for creating effective markdown-only Claude Skills that function without executable scripts. Use when creating skills based on knowledge, guidelines, templates, workflows, or domain expertise. Covers structure, patterns, best practices, and provides templates for common skill types (guidelines, workflows, template collections, domain knowledge, principles-based guidance).
jvhoof/ipcalc/skills/ipcalc-for-cloud Skill
no license0★ repoCalculates IP ranges, CIDR blocks, and subnet allocations for cloud networks (Azure, AWS, GCP, Oracle, AliCloud). Supports single VNet/VPC or hub-spoke topologies with automatic AZ distribution. Outputs as info tables, JSON, or IaC templates (Terraform, Bicep, ARM, PowerShell, CloudFormation). Use for network planning, IP calculations, CIDR notation, or infrastructure as code generation.
mpuig/raw/builder/skills/mock-authoring Skill
no license0★ repoWriting effective dry_run.py mocks for workflow testing without external dependencies
hadv/claude-skill-set/walletconnect Skill
no license0★ repoClaude Skill Set
qduc/claude-skills/skills/cartographer Skill
no license0★ repoWork that's too big to hold in one session, planned as a living map of unknowns — named destination, sharp questions, and fog — resolved one at a time, and kept open through implementation so unknowns found mid-build come back to the map instead of into the diff.
geopti/gemini-api-claude-skills/skills/gemini-api-full Skill
0★ repoComprehensive reference for Google's Gemini API. Use when building applications with: (1) Gemini models (Gemini 3 Pro, 2.5 Flash/Pro/Flash-Lite) for text and multimodal generation, (2) Image generation (Imagen, Nano Banana), video (Veo 3.1), music (Lyria), (3) Function calling, structured outputs, and agentic workflows, (4) Built-in tools: Google Search, Maps, Code Execution, URL Context, Computer Use, File Search, (5) Live API for real-time voice/video streaming, (6) Long context (1M+ tokens), embeddings, document/audio/video understanding, (7) Batch API, context caching, safety settings. Triggers: "gemini api", "google ai", "genai sdk", "gemini model", "veo", "imagen", "nano banana", "lyria", "live api", "vertex ai"
The same file is in 2 other repositories
jmfontaine/jmf-claude-plugins/plugins/git/skills/commit Skill
0★ repoGit commit guidelines. Use when creating, amending, squashing, or rewording git commits, staging files, or writing commit messages.
The same file is in 1 other repository
senior-sigan/llm-skills/skills/architecture-decision-records Skill
no license0★ repoCapture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
The same file is in 5 other repositories
tony8888lrz/skill-debug-lab/.agents/skills/brand-writer Skill
no license0★ repoWrite clear, developer-first copy for Zed — leading with facts, grounded in craft.
playtosor/skill_AI_d Skill
no license0★A three-skill kit for adding built-in contextual help to any Claude skill system. Produces a [SYSTEM]_help.md file that responds to HELP! and HELP! TRIGGER at runtime. Covers initial authoring (cdc_help, help) and incremental updates (update_help). No code required.
sanjay3290/atlassian-skill Skill
0★Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via MCP server (recommended) or API token authentication (fallback).
The same file is in 1 other repository
apex-stack-ai/blog-publisher-lite Skill
no license0★Publish markdown articles to Dev.to via their REST API. Use this skill whenever the user wants to publish a blog post or article to Dev.to. Triggers include: posting to Dev.to, publishing articles, 'publish my article', 'post this on dev.to', or any mention of publishing written content to Dev.to. Also trigger when user has markdown content they want published on a developer blogging platform.
aavanian/capture-link-to-org Skill
0★Quick triage of a URL (repo, blog post, snippet). Fetches the page, gives a KEEP/DROP verdict with a one-liner reason, and always outputs a ready-to-paste org-mode TODO snippet.
gagip/gagip-dev/.claude/skills/plugin-commit Skill
no license0★ repo변경사항을 분석해 이 프로젝트의 커밋 컨벤션에 맞는 메시지를 작성하고 커밋을 수행하는 스킬. scope는 변경된 파일 경로로 자동 감지한다 (plugins/common → common, plugins/android → android). "커밋해줘", "변경사항 정리해줘", "커밋 메시지 만들어줘", "git commit", "스테이징하고 커밋" 등의 표현이 나오면 반드시 이 스킬을 사용할 것.
RainLib/full-stack-skill/.claude/skills/code-development Skill
0★ repo根据单元测试用例、任务拆分与程序设计实现代码,并通过测试验证。全栈工作流第 7 阶段。
TomasB2BC/claude-code-toolkit/monitoring/monitor-watchdog Skill
0★ repoAutonomous watchdog for long-running processes. Three modes: standard (cron polling with delta ETAs), brief-driven (--brief, derives checks from a brief file for cross-session work), watch (--watch, event-driven with heartbeat fallback). Use when the user says /monitor, 'monitor this', 'watch this', 'track progress', 'keep an eye on', or wants to know when a running task will finish.
CesarAugustoAndrade/tool-claude-skill-dev/.claude/skills/optcg-play Skill
no license0★ repoOPTCG Turn Coach agent. Analyzes board states and recommends optimal plays with detailed reasoning. Triggers on: what do I play, board state, my turn, my hand, what should I do, help me play, game situation, DON allocation, attack sequence, should I counter, lethal check.
duck-ai-yy/skill-safety-reviewer Skill
no license0★Evaluate whether a skill found online is safe, appropriate, and correctly used — before installing it. Use this skill whenever a user shares a skill file, skill code, or a SKILL.md they found online and wants to know: "Is this safe?", "Can I trust this?", "What does this do?", "Should I use this?", "How do I use this correctly?", "I found this skill, is it okay?", "Help me check this skill", or any variation on reviewing/auditing a skill. Also trigger when the user pastes skill content directly into the conversation. This skill is especially important for non-technical users who use AI tools but don't have a coding background.
jeffwhitlock/operator-mode/skills/operator-new Skill
0★ repoInitialize Operator Mode for this repository and maintain PROJECT_STATUS.md as working memory.
mwarden/learning-plan-creator.skill Skill
no license0★Create personalized learning plans for technical topics. Use when the user wants to learn a new subject, develop expertise in a domain, or build a structured curriculum for self-study. Triggers include requests like "help me learn X", "create a learning plan for Y", "I want to understand Z", or "how should I study W".
dreamor/dingtalk-to-ai-skill Skill
0★用于在钉钉群聊中远程控制本地AI CLI工具(OpenCode或Claude Code)。 当用户需要从手机钉钉发送代码执行指令、启动AI编程会话、或远程操控开发环境时使用。 适用场景:外出时通过钉钉调用本地OpenCode处理代码、让AI帮忙审查或修改项目文件。 关键词:钉钉遥控代码、远程AI编程、手机控制开发机、钉钉机器人调用本地CLI。
jasonchanjj123/Study-Tutor-Skill/Skill Skill
0★ repoUse this skill whenever a user uploads lecture notes, course slides, textbook pages, screenshots, code files, spreadsheets, or any academic material and wants help studying, reviewing, or understanding them. Triggers include: requests to summarize lecture content, create flashcards, build study guides, explain concepts from class, generate practice problems, review for exams, reorganize notes, or any mention of 'study', 'review', 'flashcards', 'exam prep', 'quiz me', 'help me understand this lecture', 'chapter review', or 'what do I need to know'. Also triggers when a user uploads academic files (even without explicit study requests) and asks 'what's in here' or 'help me with this'. This skill transforms passive notes into active-recall study assets — flashcards, Feynman explanations, knowledge graphs, concept maps, and practice exercises. Use this skill even if the user just says 'I have some lecture notes' or uploads a .pptx/.pdf and mentions school, class, or studying.
petro-nazarenko/claude-skills/skills/react-native Skill
no license0★ repoUse this skill for ANY React Native task involving performance, architecture, or platform-specific concerns. Triggers on: Metro bundler config/optimization, FlatList vs ScrollView choice, platform-specific code audit (Platform.OS, .ios.js/.android.js splits), Expo vs bare workflow guidance, React Navigation setup/patterns, bundle size analysis, slow list rendering, navigation performance, or any RN project audit. Always use this skill when the user mentions React Native, Expo, Metro, React Navigation, or mobile app performance.
The same file is in 1 other repository
fanggeek/xiaolu-house/skills/anyang-house Skill
no license0★ repo小鹿选房是专业的涵盖全国的房产信息平台,当用户需要在安阳找房源(二手房、租房、新房、买房、找房)、选笋盘、比价格、查成交、看小区、查学区、查学校时使用。
andresnator/agents-orchestrator/skills/absorb Skill
0★ repoAnalyze one or more external projects (git URL or local path) to extract AI-harness practices, agent patterns, or instruction logic and contrast them against this repository's harness. Not for application code review.
bugmakesprogress/hardcore-food-scout Skill
0★Use when the user asks for restaurant recommendations, food discovery, or dining suggestions for any location in China. This skill uses OSINT (Open Source Intelligence) methodology to find authentic, local restaurants by cross-referencing real human reviews from news, forums, and government websites — bypassing manipulated platform ratings. 当用户请求中国任意地点的餐厅推荐、美食发现或就餐建议时使用。
earyantLe/vibe-coding-skill Skill
no license0★Vibe Coding 中文指南 - 通过与 AI 结对编程将想法变为现实的终极工作流程,包含胶水编程、Canvas 白板驱动开发、AI 蜂群协作、12 层语言要素等核心方法论
hamandmore/tides Skill
no license0★Access global ocean tides model. Functions include tide height at a given date/time/location, tide extrema, and grid weather data.
nutstrut/verified-task Skill
no license0★Verify any agent output before it is trusted, paid for, or acted on. A universal SAR verification pattern for AI agent workflows.