The catalog
609,344 rows, by stacks then stars
2389-research/prbuddy/skills Skill
1★ repoPR health assistant - monitors CI status, triages review comments, fixes issues with systematic prevention. Triggers on "check my PR", "PR health", "make PR green", "fix PR", "ready to merge", "handle PR feedback".
secondorderai/summon-skill/skills/summon Skill
1★ repoGenerate bespoke, stack-aware Claude Code agent files for tech teams. Creates specialized AI agent personas (backend, frontend, fullstack, AI/ML, DevOps, QA, security, code reviewer, performance engineer, system architect, tech lead) that Claude Code autonomously picks up from `.claude/agents/`. Use this skill whenever the user says things like "create an agent", "I need a code reviewer agent", "generate a backend agent for this project", "set up agents for my team", "build me a QA specialist", "create a security auditor agent", "I want a tech lead agent", "set up an agent team", "create agents for this repo", or any request involving creating Claude Code agent definitions, AI specialist personas, or team compositions for agentic coding workflows. Also trigger when the user mentions "agency agents", "agent roster", "agent team", or wants to scaffold autonomous coding assistants into their project.
ogu8/reviewing-plans Skill
1★Use when reviewing an AI-generated implementation plan before execution, when handed a plan to approve, or when checking if a plan is ready to act on
bitcoin21ideas/skills/skills/commit Skill
1★ repoMulti-step git commit workflow. Gathers state, triages sensitive content and secrets, groups changes into logical units, runs the project's test/lint gate, proposes a plan for approval, and commits with conventional messages and no AI attribution. Use when changes need to be committed — when the user says "commit", "/commit", or asks to commit staged or working-tree changes. Both user- and model-invocable.
scoobydont-666/shared-claude-skills/skills/ansible-hardening Skill
1★ repoCodify security hardening into reusable Ansible roles — CrowdSec IDS, fail2ban, auditd, Tailscale VPN, Semaphore UI, scoped sudoers, systemd sandboxing, and UFW firewall management. Trigger on: "harden with Ansible", "Ansible security", "CrowdSec role", "fail2ban role", "auditd role", "Tailscale Ansible", "Semaphore role", "sudoers role", "security playbook", "fleet hardening", or any request to automate security configurations that were done manually.
nlink-jp/skills-series/mcp-tactics Skill
no license1★ repoChoose the right nlink-jp MCP server for the situation, and call them in the right order. Use when investigating an IP address, domain, URL, MAC address / BSSID, or a pcap capture; when analysing a CSV/JSON/JSONL/Parquet file or writing throwaway Python for data; when producing narrated Japanese audio, a presentation video, or a locally generated image; or when a second opinion from another model would help. Also for 調査・トリアージ・不審IP・不審URL・不審メール・パケット解析・データ分析・ナレーション音声・解説動画・画像生成・セカンドオピニオン. Read this before reaching for any in-house MCP server, and especially before any lookup that could touch the party under investigation.
kpab/awesome-fun-claude-skills/.claude/skills/add-skill Skill
1★ repoネタ系スキルをリストに1件追加する。「このスキル追加して」「これ載せて」とURLを渡されたら使う。skills.yaml への追記と README 再生成までを一貫して行う。掲載対象は GitHub リポジトリのみ。
evnm/claude-skills/checklist-iterate Skill
1★ repoWorks through a categorized markdown checklist file of open tasks — scopes each item, decides whether to execute directly or split across parallel subagents, confirms the plan with you, executes, and keeps the checklist file updated with progress notes as it goes. Re-run after appending new tasks to continue the loop. Use when the user has a checklist/task-list file (headings grouping `- [ ]` items) they want worked through iteratively.
wxkingstar/wikijs Skill
no license1★Wiki.js 文档中心管理助手。通过 GraphQL API 管理公司 AI 应用文档中心。 支持项目文档的自动维护、读取、搜索和组织。每个项目拥有独立的文档空间(基于路径前缀)。 使用场景: - 创建/更新/删除项目文档 - 搜索和读取文档内容 - 同步代码库文档(README、CHANGELOG等)到 Wiki.js - 管理项目文档结构和导航 - 查看文档修改历史 触发关键词:wiki、文档中心、项目文档、wikijs、文档同步
veyralabsgroup/naming-suite/brandaudit Skill
no license1★ repoAI Brand Audit System. Activate when a user wants to evaluate an existing brand name — asking "is my name good?", "should I rebrand?", "what's wrong with my name?", "how does my brand compare to competitors?", or when they express doubt about their current name. Also trigger when a user shares their company/product name in passing and it shows clear weaknesses (mispronunciation risk, generic patterns, trademark exposure). Produces a scored audit with weakness severity ratings and a clear recommendation: keep, optimize, refresh, or full rebrand. When a full rebrand is recommended, activate DomainForge automatically.
The same file is in 1 other repository
XuYuting133/elderly-ui-audit/skills/elderly-ui-audit Skill
1★ repo依据中国工信部《互联网网站适老化通用设计规范》和《移动互联网应用(APP)适老化通用设计规范》,对项目代码进行适老化合规检测,生成问题报告、修改建议,并支持自动修复。
The same file is in 2 other repositories
vstakhovsky/shokunin-review/.claude/skills/ponytail-audit Skill
no license1★ repoWhole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.
The same file is in 3 other repositories
NerdBase-by-Stark/skill-forge/example-skills/mass-deploy-ux Skill
1★ repoUX patterns for desktop tools that commission or configure device fleets in parallel — status grids, error triage, resumable worklists, LED locate, throughput ETA. Use when designing a UI that tracks 50+ parallel device operations.
The same file is in 1 other repository
2389-research/remote-system-maintenance/skills Skill
1★ repoThis skill should be used when performing maintenance or diagnostics on remote Linux systems. Triggers on "remote server", "Linux maintenance", "Ubuntu cleanup", "Debian", "disk space", "apt cleanup", "journal vacuum", "snap cleanup", "system diagnostics". Provides structured three-phase checklists with quantification.
The same file is in 3 other repositories
capsrock/reid-miles-design-skill Skill
1★A Claude Skill for reproducing Reid Miles' (1927-1993) Blue Note Records typography-led design style in layouts that cannot use large photography (app UI, splash screens, cards, banners, slides). No large portrait photography is used; instead, typographic contrast, flat color blocks, asymmetric composition, and extreme scale contrast recreate the Blue Note graphic tension. Use this whenever a request mentions "Reid Miles style", "Blue Note style", "jazz album cover look but no photography", or "make it feel that way through typography alone".
ORBWEVA/orbweva-method/skills/core Skill
no license1★ repoORBWEVA CORE Method skill — the strategic glue connecting founder skills to a structured business methodology. Use when user needs to run a CORE Assessment, convert skill outputs into ARC knowledge entries, map automations to AER pillars, or define Grow dashboard metrics. Triggers on "CORE method", "CORE assessment", "ARC entries", "AER mapping", "Grow metrics", or /core commands.
dhegde11/live-docs-lookup Skill
1★Use when building with any AI SDK or API — Anthropic, OpenAI, or Google. Fetches current documentation in real time before answering, so stale training data doesn't cause bugs. Trigger on: model selection, tool use, function calling, streaming, prompt caching, batch processing, SDK setup, or any AI API integration, planning, debugging, or code review.
veyralabsgroup/venture-analyst Skill
1★Startup and SaaS idea validation. Researches market evidence, maps competitors, scores viability, and generates concrete validation experiments. Zero API keys required.
The same file is in 2 other repositories
RealDougEubanks/ClaudeMarketplace/skills/accessibility Skill
1★ repoAudits code for WCAG 2.2 AA compliance and provides design guidance for accessible components. Covers semantic HTML, ARIA, keyboard nav, contrast, focus management, and motion.
Huangleyang125207/ctrl-c-v-code-skills/skills/ctrl-c-v-tdd Skill
1★ repoTest-pattern doctrine. Tests are copyable from ~/.claude/patterns/tests/, three categories: input boundary, contract, effect. Make sure to consult this skill whenever code changes touch a boundary where someone else's code meets yours, even if the user doesn't say "test" or "TDD" — Claude tends to ship untested boundary code, and this skill prevents the Saturday phone call. TRIGGER when: code under change has external callers (other modules, cron, CLI, HTTP/RPC clients, "外部调用", "被外部调用"); persists state (DB write, file write, redis/cache, session storage, anything that survives the request); calls third-party API/SDK; task is classified as LARGE per ctrl-c-v sizing (4+ files, new capability, new architecture, new external contract) — LARGE always triggers TDD regardless of caller scope; user mentions tests, TDD, 测试, boundary, contract, mock, fixture, red/green, characterization test, pinning test, golden master, refactor; business domain involves payments, queues, webhooks, auth, external integration; refactor of working code (no current tests) → § T7 characterization mode applies. SKIP when: code change is purely internal helpers used only by caller in same file; pure UI rendering with no validation/state; accessor < 10 lines with no if/loop/exception; one-file fix that ctrl-c-v classifies as SMALL. Examples that trigger: "implement Stripe webhook handler", "add retry to the upload pipeline", "this database migration", "build a multi-step checkout form with validation across steps". Examples that skip: "rename this private function", "fix formatting in style.css".
darbin/claudecraft/plugins/rem-dev-core/skills/rem-branch Skill
1★ repoFinish a development branch. Verifies all tests pass, then presents 4 options - merge locally, push + create PR, keep as-is, or discard. Handles worktree cleanup. Use when the user says "finish branch", "merge", "create PR", "done with this branch", or after rem-execute completes.
ZLHad/agent-skills/claude-code-skills/comms-research-partner Skill
1★ repo科研伙伴助手。当用户想要讨论论文、学习知识点、头脑风暴研究想法、搜索学术文献、探讨数学建模、或进行学术交流时使用此 skill。触发短语包括:"讨论论文"、"研究想法"、"头脑风暴"、"搜文献"、"帮我理解"、"一起研究"、"科研问题"等。
xonack/wp-woocommerce-claude-skill/skills/wp-woocommerce Skill
1★ repoWooCommerce development patterns — custom product types, payment gateways, shipping methods, HPOS, REST API extensions, cart/checkout customization, email classes, block integration, and testing with WC helpers.
carrielabs/data-brief Skill
no license1★Use this skill when the user provides a dataset (CSV, Excel, JSON, SQL dump, or raw text data) and asks for analysis, insights, a data report, a dashboard, or any form of data visualization. Trigger phrases include: "analyze this data", "make a dashboard", "what does the data say", "give me insights", "build a report", "data brief", "data-brief", "data visualization", "帮我分析数据", "做一个数据看板", "给我洞察", "数据简报", "做个报告". Also triggers when user shares a file path to a data file and asks "what can you find" or "tell me what this data says".
goldenprofile/llm-skills/500-error-eliminator Skill
1★ repoСистематическая диагностика и устранение Django 500 Internal Server Error через анализ кода, конфигурации, шаблонов и логов. Используй когда пользователь сообщает о 500 ошибке, «Internal Server Error», падении сервера, «сайт упал», «500 на проде», или просит отладить ошибку в Django-приложении (dev или production). Это узкоспециализированный реактивный плейбук именно для Django 500; произвольные не-Django баги и регрессии производительности — вне его scope. Если причина инфраструктурная (nginx/gunicorn/systemd, 502/504) — см. vps-deploy-auditor.
ORBWEVA/dt-skill/skills/design-thinking Skill
no license1★ repoGuide users through human-centered design thinking for product features, systems, dashboards, and architecture decisions. Use when user wants to design a new feature, rethink a user flow, plan a dashboard, architect a system from the user's perspective, or explicitly invokes /dt. Triggers on "design thinking", "user needs", "empathize", "how should we design", "what should the UX be", or /dt commands.
Jasondd945/project-cn Skill
1★当用户要翻译项目为中文版、生成 -CN 副本、项目中文化时使用,保留原文件不覆盖,并为文档生成 -CN 翻译副本、为代码生成 -CN 中文注释增强副本时使用。
horizon-foundry/foundry/skills/brand-voice Skill
1★ repoUse when writing or reviewing any user-facing copy, marketing, landing pages, UI labels, error messages, empty states, docs prose, or when a project needs its brand voice defined. Enforces one voice from a single source of truth instead of ad-hoc tone per surface. Not for deciding what a surface may claim (the forever spec owns capability truth) or for visual design.
subhashdasyam/security-antipatterns-java Skill
no license1★Use when generating Java code for web applications, APIs, or enterprise systems - prevents OWASP Top 10 vulnerabilities in Spring Boot, Jakarta EE, and core Java
chafingdishposition355/go-skills/cobra-viper Skill
no license1★ repoExpert skill for building CLI applications with Cobra and Viper, authored by spf13 — the original creator of both libraries. Covers command-first architecture, decoupled business logic, configuration management, environment variable binding, context-aware commands, and in-memory CLI testing. Use when building or reviewing any Go CLI application that uses Cobra and/or Viper.
dox187/usage-aware-claude-statusline/.claude/skills/statusline-config Skill
no license1★ repoGuided LAYOUT setup for the usage-aware Claude Code statusline — decides WHAT the bar shows (which lines/elements, usage display style, context gauge form, weather, incident status indicator, emoji width) by chatting, complementing the TUI editor. Invoke when the user says things like "set up the statusline", "configure my statusline", "change which lines/elements show", "add weather to the bar", "show usage in the statusline", "switch to a compact usage display", "hide the git line", "configure the context gauge", "show Claude status in the bar", or "add an incident indicator". This skill does NOT change colors — colors are owned by /statusline-theme; route any color/theme request there instead.
bhuvangupta/vapt-claude/skills/vapt-api Skill
1★ repoFull-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting
alfonso0512/energy-news-search Skill
no license1★能源领域新闻垂直搜索。按子域(储能/光伏/风电/氢能/政策/市场/电网/电动车)路由到专属高质量新闻源,支持多后端自动降级,零配置开箱即用。
zivreich/fable-maestro Skill
1★Quality-first model delegation for Claude Fable sessions. Use whenever running on Fable 5 and the task involves writing or changing code, debugging, testing, refactoring, researching a codebase, or any multi-step implementation work — route construction to Opus subagents and read-only chores to Sonnet while Fable plans, integrates, and reviews every diff. Trigger on any substantive coding request ("implement", "build", "add", "fix", "refactor", "debug", "migrate") even when the user never mentions delegation, tokens, or efficiency. Do not use for trivial single-file edits or pure Q&A.
ducquoc-gft/stm-skill/skills/stm Skill
no license1★ repoCompacted communication mode. Cuts token usage 55%~92% by speaking like Feynman while keeping full technical accuracy. Intensity modes: simple, terse, cc. Use when user says "stm mode", "fman mode", "use stm", "use fman", "be concise", "ngắn gọn" or invokes `/stm` or invokes `/fman`. Also auto-triggers when token efficiency is requested.
Asm3r96/wave-driven-dev/skills/acpx Skill
1★ repoUse acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, and output formats.
guntherb7/helm/business/.claude/skills/done Skill
1★ repoManual project update fallback. Reads project ops file, asks what changed, updates milestone/activity status, checks completion.
xltang/hotspots_xwzb Skill
1★用于拉取并展示最新热点内容(接口为 https://hotspot.api4claw.com/hotspots/latest?timestamp=$TIME_STEMP,返回 JSON 数组)。按模型预估点击率生成 Top 条目(不使用原始热度排序)。默认会提示用户创建定时任务(不自动执行),在用户确认后提供 cron 注册命令。适用于用户查询最新热点、服务状态、按 source_name 分组标题、Top 内容,或由已存在的定时消息触发执行。触发词:"今日热点"、"今日早报"、"热点新闻"、"早报"
croftspan/gigo/.claude/skills/eval Skill
1★ repoTest whether your assembled context actually improves AI output. Runs tasks bare vs assembled, uses comparative judging, reports the delta. Use gigo:eval when you want to prove your setup works or debug why it doesn't.
veyralabsgroup/agency-audit Skill
1★Audit any company website and generate a pitch-ready report for agencies. Extracts real problems, competitor comparison, quick wins, and a structured service proposal. No API keys required.
The same file is in 2 other repositories
donatassimkus/claude-ai-skills/skills/abm Skill
1★ repoAccount-based marketing strategy, target account selection, multi-channel ABM campaigns, personalisation, LinkedIn ABM, intent data, sales and marketing alignment. Use when asked about ABM, account targeting, or enterprise marketing campaigns.
clever-cc-plugins/cc-config/plugins/cc-config/skills/cc-config-init Skill
1★ repoBootstrap a best-practice Claude Code configuration for a new or unconfigured project. Use this skill when a user asks to set up Claude Code, initialize a project, create a CLAUDE.md, or configure permissions/hooks/settings for the first time. Also use when the user says things like "set up this project", "configure Claude Code", "bootstrap config", or "better /init". This skill replaces the built-in /init with a leaner, more opinionated setup grounded in current best practices.
LukeJMadden/Veltrix-skills/skills/business/customer-success Skill
1★ repoCustomer success skill — support triage, health scoring, churn prediction, onboarding. Use when tasks involve customers, support tickets, NPS, churn, or renewals.
rgnicoara/debug-driven Skill
1★Activates a structured, hypothesis-driven debugging loop. Use this skill whenever the user reports a bug, unexpected behavior, or runtime error and wants help diagnosing the root cause - especially for bugs that are hard to reproduce or where the fix isn't obvious. Trigger on phrases like: "debug this", "figure out why X is happening", "something is wrong with Y", "I have a bug", "debug-driven", or any request to investigate a runtime issue rather than just apply a code fix. Do NOT use for compile errors with obvious fixes or simple typos - only when runtime investigation is needed.
ClydeShen/tech-humanizer-skill Skill
1★Use this skill when the user asks to humanize, rewrite, de-AI, polish, or detect AI writing in documents, emails, chat messages, pull request text, release notes, technical docs, or other prose. It removes AI-writing markers while preserving technical terminology, reports AI-marker density with concrete fixes, and learns the user's wording preferences, domain terms, and recurring writing habits over time. Don't use for grammar correction unrelated to AI markers, original content generation, fact-checking source material, or translating between languages.
LevNas/ccaudit/skills/audit-flush Skill
1★ repoInspect and flush staged audit-trail entries to the remote trail repository. Use when the user asks to "flush audit trail", "show what's pending in audit trail", "dry-run audit flush", "retry audit pending", or when diagnosing why a previous auto-flush was skipped (secret hit, push failure, manual mode).
vanthienha199/openclaw-skills/deploy-kit Skill
1★ repoDeploy projects to Vercel, Netlify, or Fly.io with one command. Auto-detects framework (Next.js, React, Python, Node.js, static HTML). Shows deploy URL when done. Supports rollback. Use when the user asks to deploy, ship, publish, or push to production. Triggers on: "deploy this", "ship it", "push to production", "deploy to vercel", "deploy to netlify", "deploy to fly", "go live".
afonsograca/devcontainers-best-practices/skills/devcontainers-best-practices Skill
1★ repoExpert reference for the Dev Container ecosystem. Consult this skill whenever the user is setting up a dev container, configuring or debugging devcontainer.json, working in a Docker-based development environment, or asking about dev containers, GitHub Codespaces, DevPod, or Zed — even if they don't say "devcontainer" explicitly. Covers the full Dev Container spec, schema validation, tool-specific behaviors and limitations (VS Code, Cursor, Zed, Codespaces, CodeSandbox, Podman), Features and Templates (choosing, authoring, publishing), lifecycle scripts, environment variables, port forwarding, multi-container setups, and official best practices from containers.dev and devcontainers.github.io. Also use when the user is confused by container behavior that differs between tools, wants to write or publish a custom Feature, or needs to validate or debug a devcontainer.json.
jtsternberg/claude-usage-data/skills/publish-insights Skill
no license1★ repoThis skill should be used when the user wants to publish their Claude Code /insights report to GitHub Pages. It automates creating a git repo, setting up GitHub, enabling Pages, and monitoring the deployment. Triggers on "publish insights", "share my insights report", "put insights on GitHub Pages", or after generating an /insights report.
GabrielYMC/security-audit Skill
1★Pre-deployment security audit for web projects, especially vibe-coded ones. Use this skill whenever the user asks to review their project for security issues, wants a vulnerability scan before deploying, mentions 'security check', 'is my app secure', 'check for vulns', or any pre-launch safety concern. Also trigger for 'I built this with AI, is it safe?', 'review before production', or 'check for hardcoded secrets'. Covers secrets, auth, input validation, data protection, infrastructure, headers, and AI/LLM security. Works on any scope: full repo, single module, single file, or code snippet.
ArielSmoliar/safe-agent/skills/behavior-watch Skill
1★ repoAnomaly detection for AI agent behavior. Monitors tool call patterns, file access sequences, and command history to flag unusual activity — first-seen patterns, frequency spikes, scope creep, and suspicious sequences. Ported from Flare's cloud audit log anomaly detection engine. Trigger phrases: "watch my agent", "behavior audit", "what has the agent been doing", "session activity report", "anomaly check", "agent activity".
veyralabsgroup/marketing-suite/ad-analyzer Skill
1★ repoAnalyze competitor ads from Meta Ad Library or descriptions, extract creative patterns, hooks, and offers, and generate variants. No API keys required.
The same file is in 1 other repository
lennney/gate-all-skills/skills/ai/ai-code-review Skill
no license1★ repoAI 审查 / AI code review. 用户说"帮我审查代码"、"review 一下"、"看看这段有没有问题"时加载。在后台检查 bug、安全、性能、代码风格,然后告诉用户结果。
vidit19sharma/neogents/skills/init Skill
1★ repoInitialize the NEO second brain in this project. Scaffolds .neo/brain/ from templates, runs a short interview to fill BRIEF.md, and writes a starter CLAUDE.md if none exists. Use when a project has no .neo/ directory yet.
hogu-dev/llmkb/skills/kb-ingest Skill
1★ repoUse when a new source document has been added to a KB's raw/ folder and needs to be filed into the wiki — read the source, write its summary page, create or update concept and entity pages, update the index and log, and lint.
jeroromano/claude-code-orchestration-template/.claude/skills/delegation-protocol Skill
1★ repoProtocol for delegating implementation, investigation or review work to Codex or to local agents (fast-worker, deep-reasoner, diff-reviewer). Use it whenever work is about to be delegated, a review is needed before a merge, a Codex command fails or hits quota, or the user asks to implement a spec, review a branch, or split work between models - even if they never say "delegate".
YuAICode/ai-skills/skills/branch-cleaner Skill
1★ repo列出可清理的本地分支(已合并 / 陈旧),供用户确认后再删。当用户说"清理分支 / 哪些分支可以删 / 列出过期分支 / 整理 git 分支 / 哪些分支可以清掉"时触发。
wasulajr/headsup/codex-skills/headsup-colors Skill
1★ repoCustomize headsup's global iTerm2 tab colors for Codex sessions: idle, working, and waiting. Use when the user asks to change Codex/headsup tab colors.
zeikar/dotfiles/claude/.claude/skills/codex-image Skill
1★ repoGenerate images via Codex CLI's built-in `image_generation` tool (`codex exec`), single or many in parallel. Use when the user wants images from codex, or batch/parallel image generation.
EnzanNoMetsuke/lynyx-claude/plugins/lynyx-agent-kit/skills/auto-coder Skill
no license1★ repoAutonomous multi-session feature development framework. Use when the user wants to systematically implement features from a specification, track progress across sessions, and ensure all tests pass before marking features complete. Activated by the /lynyx-agent-kit:auto-coder command or when working with feature_list.json files in an .auto-coder directory.
The same file is in 2 other repositories