The catalog
610,220 rows, by stacks then stars
hiadrianchen/challenge-plans Skill
4★Before you execute a drafted plan/spec/design doc, run a multi-agent adversarial cross-review to surface the flaws that cause downstream rework, aggregating "evidenced, cross-family-verified" objections into a verdict. Use when the user asks to "review this plan/spec", "can this approach be executed", "poke holes / adversarial review / QA this", "harden before executing", or when an agent is about to hand a drafted decision/QA back to the user — first run this skill and present the cross-review recommendation plus surviving objections. Runs on local subscription CLIs (claude/codex), no per-token API cost. Not for "help me pick among options" — that's the weigh-options deliberation skill.
GeoffreyCoulaud/bgcpm/plugins/pick-my-brain/skills/pick-my-brain Skill
4★ repoUse when starting a new task, feature, or project where the user has domain knowledge the agent lacks, before planning sessions, or when requirements feel ambiguous and the agent would otherwise guess or make assumptions
The same file is in 2 other repositories
AgentCommander/exploration-map/runtime/claude_code/skills/debrief Skill
no license4★ repoReview exploration progress. Use to get a tree health report, ingest hypothesis feedback events, decide what to explore next, audit cross-direction lessons, or get a cross-tree review of the current state. Wide read across the whole map, narrow write — proposes and routes; doesn't change tree substance.
BechsteinDigital/claude-shiploop/autonomous-loop Skill
4★ repoUse when a set-up project (project/BRIEF.md approved, PROFILE/STATE/backlog present) should continue building autonomously — orchestration of CEO/PO/DEV/REVIEWER cycles with parallel agents, without user input. Also for resuming after an interruption or handoff.
Trystan-SA/postkit/.claude/skills/postkit-release Skill
4★ repoCut a new postkit release — bump the version in package.json (asks the user whether it's major / minor / patch), commit, tag on GitHub, publish a GitHub Release so watchers get notified, and publish to npm. Use when the user says "ship a release", "cut a new version", "publish to npm", or "release postkit".
M97Chahboun/code-parser/code-parser-skill Skill
no license4★ repoUse this skill whenever you need to read, understand, navigate, edit, refactor, or reason about a codebase written in Dart, Python, or TypeScript — especially before reading any source files directly. This skill runs `code-parser` to build a lightweight structural index (classes, methods, line ranges) of the codebase first, then uses that index to read only the specific lines that matter. This drastically reduces token consumption and prevents context window overflow. Trigger this skill when the user says things like: "read this codebase", "understand my project", "refactor this class", "find where X is defined", "explain how Y works", "add a method to Z", "what does this file do", "help me debug", "review my code", or any task that would otherwise require loading entire source files. Always use this skill before reading .dart, .py, or .ts/.tsx files — even for single-file tasks. Do NOT skip this skill just because the request seems simple; the index step is always cheaper than full file reads.
roodlicht/accans-sec-skills/skills/ad-attacks Skill
no license4★ repoActive Directory attack paths — BloodHound path analysis, Kerberos abuse (Kerberoasting/AS-REP roasting/silver/golden ticket classes), delegation flaws (unconstrained/constrained/RBCD), DCSync, ADCS ESC1-8 at pattern level, and Tier-0 hygiene as a defensive model.
Schlaflied/roast-cold-email-skill Skill
4★研究目标公司痛点,生成有理有据的批评式cold email,通过Gmail小号发送。批评公司gap,不针对个人。
christianb93/WikiSpec/.claude/skills/openspec-apply-change Skill
4★ repoImplement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
The same file is in 4 other repositories
Klionskiy/claude-mobile-mvp-skills/plugins/mobile-mvp-product/skills/appstore-mvp-review Skill
4★ repoThis skill should be used when the user wants Claude Code to review a mobile app MVP, product concept, Figma design, feature list, App Store submission plan, or competitor-inspired app for App Store readiness, differentiation, thin-wrapper risk, and practical release scope.
Mfrostbutter/skill-forge/examples/figma-design.example Skill
4★ repoDesign, build, or edit a Figma file through a design connector (plugin-API calls verified with screenshots). Use whenever the task is to create or change a Figma design, mock up a UI, logo, infographic, or design system, build styles or components, or hand a design to dev. Triggers even if the user does not name Figma but asks to "mock up", "design a screen", or "build a component library". Encodes the hard rule that page structure and layer naming come before any frame.
froster02/mini-Brain_skills/bhai Skill
no license4★ repoA Delhi-buddy companion persona — warm, chaotic, heavy Hinglish, always in your corner. Use ONLY on explicit invoke: "/bhai", "yo bhai", "bhai mode", "talk to bhai", "be my Delhi buddy", "chal bhai", "arre bhai sun na". This is NOT a task-help skill and does not auto-fire on casual chat — it's the odd one out among its siblings (/brainstorm, /thinking, /idea, /explore, /create, /guide, /study, /try all do a cognitive task; /bhai just hangs out). If the user actually needs something built, decided, or explained while this is active, stay in voice but point them at the sibling skill that fits instead of solving it seriously in banter mode.
vigo/claude-skills/code-like-djangonout Skill
4★ repoProvides Django web framework expertise including project structure, models, views, admin, Celery tasks, testing, and Python best practices. Use when generating, analyzing, refactoring, or reviewing Django/Python code.
plagtech/spraay-payments Skill
no license4★Send batch crypto payments and payroll using the Spraay x402 gateway. Supports Base, Ethereum, Arbitrum, Polygon, BNB Chain, Avalanche, Unichain, and more. Use when the user asks to send payments, batch transfer, pay multiple wallets, crypto payroll, create invoice, check balance, or resolve ENS/Basename addresses.
celticht32/Couchbase-Skills-for-Claude.ai/skills/couchbase-analytics/cb-analytics-admin Skill
4★ repoUse this skill when the user wants to inspect or manage the Analytics service's runtime — checking ingestion health, killing runaway queries, restarting nodes, or diagnosing performance. Trigger when they mention "ingestion status", "active queries", "completed requests", "restart service", "cancel request", "service status", or "Analytics health".
junyoung2015/pr-review-skill/skills/pr-review Skill
4★ repoDeep code-centric review of pull requests for the moving-frontend monorepo. Use when the user mentions reviewing a PR, triaging GitHub Copilot or CodeRabbit comments, doing a code review, or wants feedback on a team member's code. Also trigger for "리뷰", "PR 리뷰", "코드 리뷰", "review PR", "review this PR", "Copilot review", "GitHub Copilot review", or when a PR doc path or GitHub PR URL is provided. Performs independent deep code analysis with git-truth validation, provider-aware AI review triage, and educational Korean-language feedback. AI review triage is secondary — the review stands alone even with 0 Copilot/CodeRabbit comments.
reaviz/skills/reablocks Skill
no license4★ repoUse when building UI in React with the reablocks component library (Button, Dialog, Drawer, Select, Calendar, CommandPalette, Tabs, Tree, Tooltip, etc.). Covers ThemeProvider setup, extendTheme, custom variants, mergeThemeClasses, useComponentTheme/useTheme hooks, and the 50+ component index.
Ashutosh2M/ExpertLens Skill
4★ExpertLens is an AI thinking framework that forces expert-level reasoning on any task. It activates when the user signals high-quality output — "deep think", "expert mode", "do it properly", "production ready", "think deeply", "best possible way", or similar phrases in any language. Also auto-triggers for creative work, system design, strategy, branding, anything to be published or shipped, multi-step complex problems, or any vague input with "make it great" intent. Requires companion file expert-persona.md — both files must be read completely before executing. Check for domain-specific persona files in this folder and read them too if present. Platform-agnostic: works on any AI system.
akirtok/preflight-security-audit/plugins/preflight-security-audit/skills/preflight-security-audit Skill
4★ repoThis skill should be used when the user wants a comprehensive pre-ship audit of an app, product, or codebase — phrases like "audit my app", "security check before launch", "is this ready to ship", "preflight audit", "review my product for vulnerabilities", "check my code for security issues", or after building a feature/product and wanting a thorough security, reliability, performance, privacy, and launch-readiness review. Covers OWASP Top 10 (2025), LLM Top 10, GDPR/KVKK, accessibility, SEO, and Stripe/Supabase/Next.js stacks.
TenWalk/ieee-skills/ieee-skills-claude/skills/ieee-citation Skill
4★ repoFormat references and in-text citations to IEEE style, and prepare Index Terms and IEEEtran bibliography setup. Use this whenever the user needs to "format references in IEEE", "fix my bibliography", "convert these citations to IEEE", "make a .bib for IEEEtran", "number my citations", "参考文献改成 IEEE 格式", "整理引用", or asks how in-text numbered citations and the reference list should look for an IEEE journal. Also covers Index Terms and EDICS selection ("选 EDICS", "Index Terms 怎么写"). Never fabricate DOIs, page numbers, volumes, EDICS codes, or any bibliographic field — flag missing metadata instead.
basteez/java-skills/.claude/skills/generate-integration-tests Skill
no license4★ repoGenerate integration tests for a Java class using Testcontainers. Supports Spring Boot (3.1+), Quarkus (3.0+), and Micronaut (4.0+). Detects class type (repository, controller, service) and applies framework-appropriate test patterns. Requires Java 17+.
oleksbard/cosmobar/internal/cli/assets/skill Skill
4★ repoInteractively configure the cosmobar Claude Code statusline — discovers the available segments dynamically, asks the user which to show plus theme and clock, then writes the config and wires it into settings.json. Use when the user wants to set up, install, configure, customize, or reconfigure cosmobar (the statusline).
sefaertunc/Worclaude/.claude/skills/agent-routing Skill
4★ repoAgent Routing Guide — when to spawn each installed agent
sp-daewoon/chronicle/skills/adr Skill
4★ repoNever lose the reasoning behind an architecture decision again. Use when recording or revisiting an Architecture Decision Record — creating a numbered ADR, transitioning its status (Proposed, Accepted, Deprecated, Superseded), or regenerating the index. Auto-numbers, fills the template, and rebuilds the index for you, adapting to any repo via config or auto-detection.
DjordjeMojsilovic/Djordjes-Claude-Setup/balanced Skill
no license4★ repoEvidence-based dialogue mode that replaces sycophantic AI responses with structured critical analysis. Use when the user presents a claim, idea, plan, or argument and needs genuine critical engagement — not validation. Activate on phrases like "what do you think about...", "is this right?", "am I thinking about this correctly?", "challenge this", "steelman/critique this", or any time genuine intellectual pushback would serve the user better than agreement. Five modes: FULL (4-move deep analysis), INTERACTIVE (Socratic step-by-step), TLDR (3-5 line quick take), STEELMAN (strongest case for + against), DECISION (tradeoff table + verdict).
actual-software/actual-skill-openclaw Skill
4★Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, and drives the Actual Advisor (login, advisor, whoami, logout) for org-scoped architecture questions. Covers all 5 runners (claude-cli, anthropic-api, openai-api, codex-cli, cursor-cli), all model patterns, all 3 output formats (claude-md, agents-md, cursor-rules), and all error types. Use when working with the actual CLI, running actual adr-bot, configuring runners or models, troubleshooting errors, managing output files, or asking the Advisor what your team's ADRs say about a design choice.
SteveGrosbois/tidal-cli/skills/tidal-auth Skill
no license4★ repoAuthenticate with Tidal via OAuth. Use when the user wants to log in to Tidal, start authentication, or when a command fails with an authentication error.
medalsoftchina/workcopilot Skill
4★项目全生命周期工作站。统一编排所有 Agent 和 Skill,从项目初始化到交付的一站式工作流。 自动识别新项目/老项目,引导需求分析、系统设计、任务拆解、脚手架搭建和工程轨道配置。 USE FOR: 开始新项目、接手老项目、初始化工作流、workcopilot、工作站、项目启动、 新建项目、项目脚手架、scaffold project、init project、start project、work copilot。 DO NOT USE FOR: 单个文档生成(直接用 doa-ppt / doa-metting 等)、纯代码调试(用 systematic-debugging)。
a-elradi/senior-saad-skill Skill
4★Senior System Architecture & Design by SAAD. MANDATORY ACTIVATION on: "SAAD", "senior design", "design my system", "architect this", "build from scratch", "full system for", "plan my project", "analyze my idea", "system structure for", "I have an idea for", "help me design", "create a system". Runs a 6-phase elite pipeline: LLM Council stress-test → System Architecture + Mermaid flowcharts → Summary confirmation → UI/UX Design (Anime.js + 21st.dev + KokonutUI components) → Figma mockup → Full Prompt Engineering Package for Claude Code. Do NOT activate for simple questions, code fixes, or tasks with no system design intent.
Kara-lynnmacroeconomic2412/paper-fetch Skill
4★Use when the user wants to download a paper PDF from a DOI (or title, resolved to a DOI first). Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, Semantic Scholar, and Sci-Hub mirrors as a last-resort fallback.
kborovik/pilot-skills/pilot-core/skills/socratic Skill
no license4★ repoParameterized single-question intent-sharpening gate. not user-invoked — invoked from consumer cmd pre-apply gate (/gh:issue, /sdd:spec).
WillInvest/ClaudeX/skills/build Skill
4★ repoTurn an approved spec into a merged-ready PR with Codex doing the writing. Claude conducts; Codex writes the plan and the implementation; a Codex reviewer and a Claude reviewer independently attack each artifact; a fresh Codex agent reconciles them into one verdict (go / fix-go / fix-review). Use when the user runs /claudex:build, or asks to build/implement an existing spec with Codex as the builder and an adversarial review loop.
mpagot/os-autoinst-distri-opensuse-skills/skills/git-commit Skill
no license4★ repoHelps write OSADO-compliant git commit messages for staged changes. Activate when the user asks to "commit", "write commit message", "prepare commit", "stage and commit", or needs help creating a commit message following OSADO CONTRIBUTING.md rules.
agentsope/career-skills/skills/career-bullet-builder Skill
4★ repo把粗糙的简历素材、口语经历草稿、或你已写好但很弱的简历句,打磨成简历上最锋利的成品条目(bullet): 选公式(PAR/XYZ/CAR)、强动词起头、诚实量化、控长度、对齐岗位关键词,并给多个版本供挑选。 默认产出中文简历条目(面向国内求职),严守"绝不编造"。可承接 career-experience-mapper 的产出, 也可单独打磨你已有的简历。Use when 用户说"帮我把这段写成简历条目/bullet""这句简历怎么写得有力点" "我写的简历太弱帮我改""这条怎么量化""动词太平淡""把经历写进简历"; 触发词:简历、bullet、简历条目、润色简历、改简历、强动词、action verb、量化、STAR、PAR、简历怎么写得好。 本 skill 只做单条 bullet 的打磨成品,不做整份简历排版投递(交给 career-resume-tailor)。
NavneetHegde/nh-stock-analyzer Skill
no license4★Delivers a structured stock analysis with trend strength, analyst consensus, price targets, risk factors, and a soft Buy/Hold/Sell signal — all rendered as a visual dashboard widget. Use this skill whenever the user asks for stock analysis, wants to know if a stock is worth buying or holding, asks for a buy/sell/hold recommendation, wants to evaluate a ticker for long-term holding, or asks about stock trends, price targets, or analyst ratings. Trigger even for casual phrasings like "should I buy AMD?", "how is NVDA doing?", "is TSLA worth holding for a year?", or "give me a stock breakdown for X".
designedbysom/accessibility-linter Skill
4★Reviews accessibility mid-design, not as a compliance audit, but as a craft challenge. Use when designing, describing, or building a UI component. Trigger on "I'm designing a component", "does this work", "review this interaction", "how should I handle focus", "is this accessible", or whenever HTML/CSS/React code is shared. Also trigger when component states, interaction models, or keyboard behavior are being described. Don't wait to be asked. If a component is being actively designed, this skill is relevant.
KhaledSaeed18/dotclaude/.agents/skills/improve Skill
4★ repoSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
The same file is in 5 other repositories
bgorkem/bgorkem-skills/plugins/image-transform/skills/svg-to-png Skill
4★ repoConverts a single SVG file into a PNG using the `rsvg-convert` command-line tool. Use when the user asks to render, export, rasterize, or convert an SVG to a PNG image — typically for embedding diagrams in places that don't support inline SVG (Medium, slide decks, documents). Requires `rsvg-convert` (librsvg) installed on the host. Do not use for generating new SVG content, batch conversion of folders, or other image formats.
vikxlp/rocky/skills/rocky-status Skill
no license4★ repoShow current Rocky mode states — which of talk style, engineering mind, and buddy are active. Use when the user says /rocky-status, "what Rocky modes are on", or "show Rocky status".
jkm-4314/claude-code-skills/bootstrap-project Skill
4★ repoUse when setting up a new project with the full opinionated workflow — session memory, commit hooks, copyright headers, ROADMAP, and CLAUDE.md. Invoke with "bootstrap project", "setup project", "new project setup", or /bootstrap-project
pencil20388-eng/content-topic-judgment Skill
4★🎯 A 4-gate framework for deciding whether a content topic is worth writing. Built for content marketing teams. Claude Code / Cursor skill. 内容选题判断框架
mikestangdevs/craft-skills/skills/craft/boyscout Skill
4★ repoUse when touching an existing file to make a change, so you leave it slightly cleaner than you found it without derailing into a giant refactor. Identifies small, safe, in-scope improvements adjacent to the change you're already making — a better name, a deleted dead line, an extracted helper, a clarified condition — and keeps them separate from the behavior change so review stays clean. Use on every non-trivial edit to an existing file; the discipline is keeping cleanup small and bounded, not skipping it.
slopstopper/plumb-line/skills/plumb-line-audit Skill
4★ repoUse when auditing a diff or repository against the plumb-line principles — finds laundered uncertainty, boundary leaks, hardcoded priors, overstated maturity, outputs lacking recorded lineage, and baseline drift with no explanation. Read-only: it reports, never auto-fixes.
Neilander/mobile-ui-replicator Skill
no license4★把手机 UI 截图复刻成可交互 HTML 的 Claude Code skill · A Claude Code skill that replicates mobile UI screenshots into interactive HTML demos
wangwei1237/agent-skills/pdf-lowercase-skill Skill
4★ repo将 PDF 文件的内容转换为小写 (PDF to Lowercase)
hyYY-1024/hy-skills/innovator-computer Skill
no license4★ repo计算机科学学术创新设计专家。当用户需要设计研究创新点、分析 research gap、增强已有方案的创新性、做竞品分析(related work survey)、评估创新点贡献级别、规划技术路线时触发。适用于 NeurIPS/ICML/CVPR/ICCV/ECCV/MICCAI 等顶会投稿准备场景。
izyanrajwani/agent-skills-library/skills/brainstorming Skill
no license4★ repoCollaborative design exploration that refines ideas into validated specs through iterative questioning. Use before any creative work including creating features, building components, adding functionality, or modifying behavior.
The same file is in 10 other repositories
AElfProject/aelf-node-skill Skill
4★AElf node querying and contract execution skill for agents.
wanikua/wolong-fengchu-skills/skills/凤雏 Skill
4★ repo贼高兴+欠揍的字面化杠精人格。当用户想和"凤雏"聊天、要求"装作凤雏"、或在对话中召唤凤雏时启用。凤雏把用户说的每个词都字面拆开,逻辑自洽地推出荒诞结论,说到一半还经常"等等我又发现一个bug"地自己把自己绕进去,全程真情实感地兴奋,并且时不时反过来嫌弃用户"这个你居然没想过?!",欠揍指数拉满。**一次召唤即全程保持角色**——本次对话里只要用户打过一次 `/凤雏`,后续所有消息都默认以凤雏身份回复,无需重复斜杠命令,直到用户明确退出。源于弱智吧蒸馏语料,纯搞笑。
ZionXiaoxiSuOGLocGo/project-onboard Skill
4★Analyze any project directory and generate AGENTS.md for AI context. Use when the user asks to "onboard", "analyze this project", "understand this project", "generate AGENTS.md", or provides a project path they want to understand. Supports auto-detection of Unity, Unreal, Node.js, Python, Rust, Go, Java, C/C++, C#, Lua, and general projects.
zysilm/skill-master Skill
4★Intelligent skill orchestrator that automatically finds, creates, executes, and improves skills. When you need to accomplish a task, this skill searches for existing skills (internal, GitHub via MCP, web), creates new skills if none found, executes them, and reviews execution to improve skills based on actual usage. Also handles feedback about skill-generated outputs - if you want to fix/adjust an output AND improve the skill that created it, invoke this with your feedback. Use when you want automated skill discovery, continuous improvement, or to provide feedback on previous skill outputs.
danielcregg/coderunner-skill Skill
4★Generate Moodle CodeRunner programming questions with Jobe server validation. Uses minimal pipeline: AI generates code + tests, Jobe computes expected output. Supports Java, Python, C, C++, Node.js. Produces import-ready Moodle XML. Battle-tested: 1000+ questions validated with 0% failure rate.
souljorje/agent-skills/skills/agentic-markdown Skill
no license4★ repoMaintains Markdown docs as explicit agent-readable context trees. Use when the user asks to create or update Markdown docs, split a large Markdown file, normalize or improve documentation structure, repair broken document trees, or make agent navigation explicit. Do not use for general prose editing, marketing copy, or unlinked repo-wide documentation cleanup.
s5uy/ui-craft Skill
4★Premium UI/UX generation skill for Claude — anti-gradient, anti-slop, hierarchy-first. A VIBECODERS DREAM
openEHR/ai-plugins/plugins/openehr-specs/skills/amendment-record Skill
4★ repoAuthor or update amendment records in openEHR specification documents — the `master00-amendment_record.adoc` table in `specifications-XX` repos. This skill should be used when the user asks to add or update an amendment entry, add a CR/PR reference, mark a release boundary, or update the `latest_issue`/`latest_issue_date` anchors. Not for general spec authoring (use authoring), the release process (use governance), or non-openEHR documents.
farhan0167/cv-claw/skills/cv-claw Skill
4★ repoUse this skill when the user wants to ingest a resume or CV into structured JSON, tailor an existing resume for a specific job, tweak how a rendered resume looks, or design a new resume template — even if they don't explicitly say "resume," "CV," or "cv-claw." Covers parsing PDFs, images, screenshots, or pasted text into cv-claw's schema (prefer this over generic PDF/text extraction whenever the source is a resume, since the output must conform to the schema to be renderable), adapting a resume JSON to a job description as a saved variant, editing the active template's Jinja/CSS in response to "make X bigger" / "move X" requests, and authoring Jinja2 + scoped CSS templates under ./.cvclaw/templates/.
smartbrainactivity/smartbrain-skill-auditor Skill
4★A universal, dependency-free Node.js tool to statically audit AI Skills and local agents for malicious patterns.
Darcos-Loft/fluid/brandkit Skill
4★ repoGenerate premium brand reference images for a design system, covering logo concepts, color and type boards, and product mockups. Use when a brief needs visual references or a brand kit before or alongside building the UI. Tool-agnostic (works with Nano Banana / Gemini, Higgsfield, Midjourney, or any image model).
chukant20-cyber/Chuksbooks-Humaniser-tool Skill
no license4★premium forensic rewriting and humanization for mixed prose. use when chatgpt needs to analyze over-standardized writing, identify machine-like stylistic regularities, and revise text into more natural, human-textured prose while preserving meaning, technical accuracy, citations, and register. supports fast mode by default, full sentence-level analysis on request, and multi-pass residual cleanup.
khou/gardenkit/skills/garden-bootstrap Skill
4★ repoBootstrap the garden vault from connected data sources. Surveys what's available, proposes a plan tailored to the user's context, asks for confirmation, then executes. Opt-in and user-invoked only — never runs unattended. Two modes, both interactive: `init` (first-time pull) and `refresh` (top-up since last run).