The catalog
608,475 rows, by stacks then stars
RobotNetworks/plugins/plugins/robotnet/skills/run-robotnet-listener Skill
1★ repoRobot Networks agent plugins.
Light0mxph/mcdev-skill/skills/mcdev Skill
1★ repoSkill experta en Minecraft Java + Gradle para Claude Code: plugins, proxies y mods. Solo Java + Gradle.
dkleptsov/skill-security-review/skills/skill-security-review Skill
1★ repoAudit an Agent Skill (or a repo/plugin of skills) for safety before installing or trusting it. Use whenever the user wants to vet, review, audit, or check whether a skill, plugin, or its scripts are safe, asks "is this skill safe to install", pastes a skill repo/URL to evaluate, or is about to install a third-party skill from GitHub, npx skills, or a plugin marketplace. Runs static analysis only (never executes the target) and reports network egress, process execution, secret access, dynamic code, filesystem writes, obfuscation, and prompt-injection instructions hidden in SKILL.md, tiered by whether the code runs automatically, on invocation, or on demand.
pluginagentmarketplace/custom-plugin-kubernetes/skills/service-mesh Skill
no license1★ repoKubernetes plugin for container orchestration and cluster management
kapilraghuwanshi/skills/skills/codepen-archiver Skill
1★ repoAgent skills by Tech Monk - Kapil
DealMachine/dealmachine-cli/skills/dealmachine Skill
1★ repoSearch and enrich US property, owner, and people data with DealMachine through its MCP tools or dm CLI. Use for real estate lead generation, property and owner lookup, contact enrichment, prospecting, comparable sales, market research, targeted lists or exports, and credit-aware DealMachine workflows.
seed-hypermedia/skills/plugins/seed-hypermedia/skills/seed-grpc Skill
no license1★ repoClaude Code skills for Seed Hypermedia
kylesnowschwartz/plugin-dev/.claude/skills/update-from-upstream Skill
1★ repoThis skill should be used when the user asks to "sync with upstream", "update from Claude Code", "check for Claude Code changes", "update plugin-dev docs", "sync with latest CC release", "what changed in Claude Code", "audit against upstream", "bring docs up to date", "check upstream changelog", "sync plugin-dev with Claude Code", "update compatibility", or needs to bring plugin-dev documentation current with recent Claude Code releases.
anaidenko/claude-video-digest/skills/watch-video Skill
1★ repoWatch a video — a screen recording, a demo clip, a bug report attachment, any video file or URL — by turning it into a readable contact sheet, frames and a transcript. Use whenever a message, ticket or comment carries a video link or path and the recording would answer a question — "watch this", "check the video", "what does the recording show", "what did they say". Handles phone and tablet captures in either orientation; transcribes only when the audio actually carries speech.
ChadDahlgren/claude-code-bedrock/plugin/skills/aws-bedrock Skill
1★ repoA Claude Code AWS Bedrock Plugin
tupe12334/instinct/skills/5w2h Skill
1★ repo54 strategy and decision frameworks (SWOT, OKR, RICE, Pre-Mortem) as Claude Code slash commands.
kengbailey/bailey-marketplace/plugins/llama-tune/skills/llama-tune Skill
no license1★ reporobcsaszar/scaffold/skills/ai-design-dot-md Skill
1★ repoCreate or extract a DESIGN.md file — a spec-compliant document combining YAML design tokens (name, colors, typography, spacing, rounded, components) with 8 ordered markdown sections (Overview through Do's & Don'ts) as persistent design-system context for AI agents. Use when adding design context to a project, generating DESIGN.md from frontend source code, defining a brand's token system, or updating an existing DESIGN.md. Don't use for implementing a design in code or editing component styles — this produces the DESIGN.md context file, not the UI itself. Triggers — design.md, DESIGN.md, design tokens, design system, extract design, create design file, brand tokens, AI design context.
LunarCommand/claude-skills/skills/pr-review Skill
1★ repoUse this skill when asked to review PR comments, address CoPilot feedback, respond to pull request review threads, or resolve PR conversations. Triggers on phrases like "review the PR comments", "address CoPilot feedback", "fix the PR", "go through PR comments", or any mention of pull request review threads needing attention. Always use this skill when a PR number or URL is mentioned alongside a request to review or respond to comments.
tontoko/fast-playwright-skill/skills/fast-playwright Skill
1★ repoFast, persistent, and token-optimized browser automation using Playwright. Supports navigation, clicking, typing, screenshots, batch execution, and more. Use when working with web pages, browser automation, or when the user mentions browsing, clicking, or web scraping.
The same file is in 2 other repositories
saleshandy/outreach-superpower/skills/strategy-architect Skill
1★ repoUse when user wants an outreach strategy from their website, says "build a cold outreach plan from my site," "audit my site for outreach," or starts a fresh outreach project with just a URL. Extracts ICP/personas/proof/differentiators and produces a 10-item confirmation card.
Jasvanth-S/Research_Plugin_Claude/skills/tech-paper-template Skill
1★ repoThe same file is in 7 other repositories
microsoft/BootcampLabTestPlugin/skills/mcs-lab-new-lab-pr Skill
1★ repoOpen a PR on the active instance's lab repo (microsoft/mcs-labs by default) that adds a NEW lab built by mcs-lab-builder. Stages the assembled `labs/<slug>/README.md` + screenshots, applies the registration entry (root `lab-config.yml` + generator, or direct `_data/lab-config.yml` + `_labs/<slug>.md` writes — per the detected mechanism), commits everything in one commit on a run-unique branch off `origin/main`, and opens the PR. Invoked by mcs-lab-builder at B7 — NOT directly by the user. Do not use this for audit fixes (that is mcs-lab-fix-pr-filer, which patches an existing lab).
fusupo/escapement/skills/create-pr Skill
no license1★ repoA structured workflow plugin for Claude Code.
abreparentesis/research-rigor/skills/implementation-plan Skill
1★ repoSelf-contained rigor toolkit for researchers: design-spec, prior-art-check, research-papers, convergent-review, implementation-plan, project-kickoff + oracle/council critic agents. Optional auto-detected search providers. MIT.
itzcull/javascript-skills/skills/react-best-practices Skill
1★ repoReact performance optimization guidelines for writing, reviewing, and refactoring frontend code. Use this skill when working on React components, rendering behavior, data fetching, bundle optimization, or general performance improvements.
william-dawson/oniom-skills/skills/slurm Skill
no license1★ reporyanlavin/ccx-harness/skills/setup Skill
no license1★ repoClaude conducts Codex.
jwmarshall/claude-plugins/scopewright/skills/create Skill
1★ repojwmarshall's Claude Code Plugins
The same file is in 1 other repository
pmgwee/prompt-shortcut/skills/prompt-shortcut Skill
no license1★ repoPersonal prompt launcher. Use when the user runs /prompt-shortcut (or asks for "my prompts", "favorite prompts", or a prompt menu) to list their saved prompts as a clickable menu and run the chosen one in the current session. Also used by the shortcut commands /continue, /conclusion, /packaging, and /add-prompt (which interactively saves a new prompt into the menu), and by /prompt-shortcut <name> to run a specific prompt directly without the menu.
pedrovinchi1/UltraPlugin/skills/ultraplugin Skill
no license1★ repojonmcgee37/n8n-automations-toolkit/plugins/n8n-project-init/skills/n8n-project-init Skill
no license1★ repoTool kit for building, testing, optimizing n8n workflows
Texnomic/Skills.CodingStandards/skills/texnomic-coding-standards Skill
1★ repoAgent Skill for Texnomic C# Coding Standards
Kotlin multiplatform development
yasanglass/agent-skills/plugins/kotlin-skills/skills/kotlin-multiplatform-development Skill
1★ repoPersonal plugin marketplace for Claude Code and other compatible agents.
klimofey/checklist-design-skill/skills/checklist-design Skill
no license1★ repo110 UI production-readiness checklists from checklist.design as a Claude Code skill — build mode and code-audit mode. Personal-reference copy; content belongs to checklist.design.
estevanhernandez-stack-ed/Vibe-Doc/packages/vibe-doc/skills/check Skill
1★ repoAI-powered documentation gap analyzer for modern codebases — scans your project, classifies what you've built, identifies missing technical docs, and generates them from your existing artifacts. Drop it on any codebase. 626Labs LLC.
mwroh-dev/marketing-ad-img/skills/agent-browser-exploration Skill
1★ repoExplore an unknown browser source with agent-browser and produce a discovery report and candidate flow notes only.
stoodder/materia/plugins/materia/skills/docs-audit Skill
no license1★ repoA self-improving Claude Code harness: one /init survey materializes a spec-to-ship pipeline — queues, producers, maintainers, and a retro loop that levels up your skills — tailored to your stack.
DivByZeroIT/dbz-skills/plugins/learn-from-sessions/skills/learn-from-sessions Skill
1★ repoLean Claude Code skill: mine past session logs for recurring failures and propose CLAUDE.md / MEMORY.md rules. Local-only, no API key. Inspired by headroom.
Abidit/smart-routing-skill/.claude/skills/smart-routing Skill
1★ repoNote: Cowork ↔ Code routing is intentionally conservative. Both tools have file access — the skill only warns when the capability gap is clear.
SollanSystems/loop-engineer/skills/loop-runtime-monitor Skill
1★ repoExecutable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.
happysasha18/live-spec/skills/product-prover-pack Skill
1★ repoPack-side bindings for the external product-prover skill inside the live-spec pack. It carries what the prover body no longer does: the pin map from this pack's PRODUCT_SPEC requirement codes to prover lenses, the pack paths a review reads, the record home and shape the push gate checks, and the mode names the build pipeline uses. Load it whenever product-prover runs inside a live-spec project. It reviews nothing itself.
vellum-ai/agent-wrapped/skills/agent-wrapped Skill
no license1★ repoSpotify-Wrapped-style year-in-review for your Vellum assistant: real stats from your own workspace. Plugin with a stats tool, skill, and CLI.
Luci6n/seo-landing-page-skill/skills/build-seo-landing-page Skill
1★ repoBuilds, improves, and audits landing pages with conversion-focused design, responsive UX, SEO/AEO/GEO, structured data, accessibility, performance, deployment, and launch validation. Use for creating, redesigning, launching, or auditing landing pages, service pages, local business sites, portfolios, SaaS/product pages, static sites, React/Next.js pages, or other marketing pages. Do not use for tiny copy or style edits unless SEO, conversion, or launch readiness matters.
Smirnov-Labs/shipwright/plugin/skills/ship Skill
1★ repoAn opinionated end-to-end development method for Claude Code, and the orchestrator that runs it. Built on superpowers + Smirnov Labs claude-skills.
dnvriend/vector-rag-gui/plugins/vector-rag-gui/skills/vector-rag-gui Skill
1★ repoQt6 GUI for searching local vector RAG stores with AI-powered research synthesis
The same file is in 2 other repositories
odysseasmas/claude-plan-statusline/skills/setup Skill
1★ repoWire claude-plan-statusline into ~/.claude/settings.json non-destructively. Backs up the existing file and wraps any existing statusLine command instead of replacing it.
intertwine/claude-code-scheduler/skills/schedule Skill
1★ repoSchedule Claude Code tasks with native OS schedulers. Zero dependencies.
excitedjs/claudemux/plugins/feishu-channel/skills/access Skill
1★ repoMulti-repo Claude Code orchestrator: one dispatcher, many tmux teammates across sibling repos.
eighteyes/proto-buddy/skills/proto-buddy Skill
no license1★ repoAres960826/ares-agent-toolkit/skills/mineru-sciverse Skill
no license1★ repoHigh-fidelity academic document parsing (MinerU) + scientific literature retrieval (SciVerse), with one-command setup. Use when the user wants to parse/convert a PDF, image, Word, PPT, or Excel into Markdown/JSON — especially papers with formulas, tables, or scanned/multi-column layout ("解析PDF", "PDF转markdown", "提取论文内容", "公式转LaTeX", "mineru", "pdf2md"); to search scientific papers / literature ("文献检索", "sciverse", "找论文", "semantic search papers"); or to bootstrap this toolchain on a new device ("配置文档解析环境", "新设备装 mineru/sciverse"). For generic PDF ops (merge, split, rotate, fill forms, plain text extract) prefer the built-in `pdf` skill.
KDercksen/claude-sandbox/skills/delegate Skill
1★ repoRun Claude Code in isolated, network-hardened Docker containers
napbat/semctl/plugins/semctx/skills/codebase-retrieval Skill
1★ repoRelevanceAI/cc-plugin/plugins/relevance-ai/skills/managing-relevance-knowledge Skill
no license1★ repoRelevanceAI Claude Code plugin (Skills + MCP)
rainshed/Agent-Benchmark/skills/extract-testcase Skill
no license1★ repogo-kid/ioc/skills/ioc-test Skill
1★ repogo-kid/ioc framework extension and testing guide. ALWAYS use this skill when the user asks about: extending IoC container, creating PostProcessors, custom tag processing, custom config loaders/binders, writing tests, testing IoC components, ioc.RunTest/RunErrorTest, slog integration, AOP/proxies, or advanced framework customization. Also use for questions like 'how to write tests for IoC', 'how to create custom tag', 'how to extend the container', 'how to add my own PostProcessor', 'how to test dependency injection', 'how to use slog with ioc', 'how to implement AOP', 'how to intercept component creation', 'how to customize property injection', or any go-kid/ioc testing, extension, and advanced customization questions. Triggers on: test, testing, ioc.RunTest, ioc.RunErrorTest, PostProcessor, ComponentPostProcessor, custom tag, extension, extend, customize, slog, logging, AOP, proxy, InstantiationAwareComponentPostProcessor, DefinitionRegistryPostProcessor, custom loader, custom binder.
RenKoya1/md2alloy/skills/md2alloy Skill
no license1★ repoMarkdown docs -> RFC 2119 spec -> machine-checked Alloy 6 model, driven by Claude Code
kubeshop/testkube-skills/plugins/testkube-skills/skills/testworkflow-runner Skill
1★ repoAI agent skills for [Testkube](https://testkube.io) — teach your AI agent how to create, run, and debug test workflows on Kubernetes.
tavaresgmg/cairn/plugins/cairn/skills/cairn Skill
1★ repoBrownfield-first, autonomous workflow router for AI coding agents (Codex + Claude Code).
blyatiful1/ultraweb/skills/analytics Skill
1★ repoConversion measurement closing the pipeline's open loop — brief defines the goals, sitemap assigns one per route, this skill counts them: cookieless-first tool choice (EU-hosted Plausible or self-hosted Umami on the locked Postgres, per STACK.md), the §25 TTDSG/TDDDG reasoning that makes a consent banner unnecessary, an event taxonomy transcribed from design/SITEMAP.md's conversion-goal column, a typed track() helper that won't compile an unlisted event, CTA instrumentation named after the goal not the widget, and the rule that anything cookie-based loads behind ultraweb:consent while GA4-by-default stays banned. Invoke in Phase 7 whenever the brief names a conversion worth counting — trigger phrases — "add analytics", "track conversions", "measure the funnel", "set up Plausible". The consent banner itself — building it, wording it, gating scripts behind it — is ultraweb:consent's; this skill only decides what gets measured and with which tool.
maxamillion/claude-oss-eval-plugin/skills/feature-verification Skill
1★ repoClaude Code skills to evaluate open source projects
streamnative/streamnative-agent-skills/skills/identity Skill
1★ repounfallenwill/TripPlan/skills/trip-plan Skill
no license1★ repothisisdhika/skills/skills/house-style Skill
no license1★ repoPersonal agent skills collection.
andrewluxem/working-backwards/skills/working-backwards Skill
1★ repoStatic agent skill for writing and auditing PR/FAQ working-backwards documents with customer evidence and explicit open questions.