The catalog
608,352 rows, by stacks then stars
adam-N-singh/fleet/skills/fleet-delegation Skill
1★ repoSupervise a fleet of AI coding workers from many providers (OpenAI Codex, Google Antigravity CLI, xAI Grok Build, Cursor CLI, GitHub Copilot CLI, Qwen Code, Factory Droid, Amp, Claude Code headless, plus 75+ providers via OpenCode including DeepSeek, Kimi, GLM, and local models on LM Studio or Ollama) as background subagents. Decide which coding tasks to delegate, pick the best provider and model via the registry, cost cascade, and outcome ledger, dispatch workers in parallel, monitor progress, verify results before accepting them, and cascade to the next provider or do the work yourself when one is rate-limited or unavailable. Works from any Agent Skills-compatible supervisor. Use proactively in any multi-task build whenever an independent, well-specified task could run in parallel with your own work, not only when the user says "delegate" or names a provider or model. Also use when the user mentions background coding workers, multi-model orchestration, or running tasks on a cheaper model.
davidchoi0313/samsin-saju/plugins/samsin-saju/skills/saju-reading Skill
no license1★ repoOrigoZero/zeromind-plugin/dist-publishing/codex-plugin/skills/zeromind-library Skill
1★ repoZeroMind plugin for Claude Code
jtpio/jp-claude-plugin/plugins/jupyter-maintainer/skills/galata-tests Skill
no license1★ repoClaude Code plugin for maintaining Jupyter ecosystem repositories
serenaxxiee/skilluminator/plugins/skilluminator/skills/skilluminator Skill
no license1★ repoSkill Assistant - Detect, Create, Share reusable AI skills from repeated processes
z5labs/devex/plugins/daggerverse/skills/plan-dagger-module Skill
1★ repoHome for all Z5Labs developer experience related components
tallesborges/dotkit/skills/dotkit Skill
no license1★ repoA fast Rust CLI for the Triangle/Trinity ecosystem: Bulletin storage, DotNS naming, and People/Statement Store
tae898/academic-de-llm/skills/academic-de-llm Skill
1★ repoStrip the markers that make text read as machine-generated. Ordered by measured frequency in agent-written prose: formatting first, paste-era artifacts last. Sources cited, unsourced claims labelled.
appboypov/pew-pew-plugins/plugins/workspace-management/skills/workspace-management Skill
1★ repoPew Pew Plugins
shivae372/nodo/.claude/skills/nodo Skill
1★ repoMap any codebase: dependency graph + issue detection + AI-agent context. Zero dependencies, one self-contained HTML file.
yigitkonur/claude-code-herdr-plugin/skills/claude-to-codex Skill
no license1★ repoClaude Code skill: drive a Codex sub-agent end-to-end through one tool over the herdr terminal multiplexer.
HarrisonOg/manifest/plugins/android-review-plugin/skills/android-review Skill
no license1★ repoClaude skills marketplace for Android app development.
The same file is in 1 other repository
pluginagentmarketplace/custom-plugin-aspnet-core/skills/aspnet-core-devops Skill
no license1★ repoASP.NET Core Development Plugin
The same file is in 4 other repositories
gitbutlerapp/claude-plugin/skills/gitbutler Skill
no license1★ repoCommit, push, branch, and manage version control with GitButler. Use for commits, selective dirty-file or hunk commits, branches, diffs, PRs, history edits, squashes, amends, undo, merge, apply, and unapply. For selected dirty files or hunks, inspect with `but diff`; use compact `but status` for commit order, branch/stack placement, or conflict overview; use `but status -fv` when file/hunk IDs or per-commit file details matter. Replaces git write commands.
StuMason/edator/skills/edator Skill
1★ repoTurn a raw screen/camera recording into a finished, edited video. Claude reads the transcript (and your codebase, if it's a dev video) and writes an "edit pack"; a deterministic FFmpeg renderer executes it. Use when someone says "/edator", "edit this recording", "cut this video", "make a video from this footage", or hands you an MP4 to turn into a watchable cut. Record once — no timeline, no scrubbing.
robertgorsuch/AI-JasperReports-Generator/plugins/jasper-deploy/skills/jasper-deploy Skill
1★ repoDemos and artifacts for BI pipeline automation using Jaspersoft and Claude Code Desktop
Barneyjm/prompt-fidelity/skills/prompt-fidelity Skill
1★ repoSelf-checks how much of a request is verifiable vs guesswork before answering it. Use when handling search, filtering, recommendation, or data-retrieval requests over any dataset (API, database, files, spreadsheet) that mix objective criteria (checkable via a query, count, or calculation) with subjective judgment (mood, style, quality, "feels like", "best"); when the user asks how confident, reliable, or verifiable an answer is; or when giving a substantive factual or technical answer whose claims mix tool-checked facts with the model's trained-in knowledge or judgment. Decomposes the request into constraints, computes a fidelity score, and reports which parts of the answer are verified vs inferred.
ThomasRohde/decision-workbench/skills/decision-workbench Skill
1★ repoTurn messy choices and proposals into transparent, defensible decisions.
wan-huiyan/promptback/plugins/promptback/skills/promptback Skill
1★ repopromptback — feedback that comes back as a prompt. Claude Code skill: turn findings/plans/triages into a single-file interactive HTML review page (per-item decision chips + notes) whose decisions copy back as one structured prompt. No backend.
TulanCN/skill-evolver/skills/skill-evolver Skill
no license1★ repo一个能进化skill的skill
QTSurfer/strategy-skills/skills/qtsurfer-java-strategy Skill
1★ repoWrite, review, and debug QTSurfer Java trading strategies — classes extending a strategy base class (AbstractTickerStrategy, AbstractKlineStrategy, or AbstractFundingRateStrategy). Use when configuring indicators, window listeners, or per-instrument state, or submitting a strategy to backtest via the MCP server.
stcomiin/claude-helpers/skills/team-code-review Skill
no license1★ repoComprehensive 6-stage code review pipeline that orchestrates multi-perspective review of code changes: agent-team debate via /simplify, frontier-model Codex/GPT-5.4 security & design review, CC-native /everything-claude-code:code-review, adversarial /bmad-review:bmad-code-review, consolidation, and Devil's Advocate capstone challenge. Use this skill whenever the user wants a thorough code review, says "run the team code review", "full review", "6-stage review", "multi-model review", "comprehensive review", "team review", or is finishing a feature/story and wants quality assurance before committing or opening a PR. Trigger even when the user just says "code review" in a context where they have completed work and want layered review, since this pipeline provides the most rigorous review available.
bazsup/claude-skillz/plugins/tactical-ddd/skills/tactical-ddd Skill
no license1★ repoYafimK/claude-skills/progressive-dynamic-research/skills/progressive-dynamic-research Skill
1★ repochickensintrees/autopsy/skills/autopsy Skill
1★ repoForensics for agentic work. Finds what your agent failed to retain -- corrections that didn't stick, tools it forgot it had -- and turns each finding into a durable fix.
quickdesignio/quickdesign-cli/skills/quickdesign Skill
1★ repoThe same file is in 1 other repository
wrzonance/agent-kit/agentkit/skills/onboard-repo Skill
1★ repoA sub-agent hook and skill system for parallel execution of Github project boards
codefoundry-io/triad-dispatch/skills/triad-gemini-dispatch Skill
1★ repoUse when the leader (Triad orchestrator) needs to dispatch a single-shot Gemini CLI call via the wrapper framework. Triggering signals — leader is about to run `python3 gemini_wrapper.py` raw; the user asks to call gemini once, have gemini handle a task, or run a one-shot gemini analysis; a higher-level orchestration SKILL needs the Gemini leg of a fan-out; classification-aware routing with self-improving repair-agent fallback is needed instead of raw subprocess. Symptoms of skipping this SKILL — unknown classification failures don't reach the repair sub-agent, run-log files accumulate uncleaned, the framework's self-improving classifier never grows. Do NOT use for Codex (`triad-codex-dispatch`), Antigravity (`triad-antigravity-dispatch`), or an isolated Claude worker (served in this plugin by the in-session `Agent` tool).
hardwood-hq/hardwood-skills/skills/hardwood-cli Skill
1★ repoAI skills based on Hardwood
parkktech/shrinkage/skills/shrinkage Skill
1★ repoWrite less, better code by extending what exists instead of adding new code — and safely remove code the repo no longer needs — guided by a token-lean symbol map. Use this skill whenever writing, modifying, refactoring, planning, reviewing, or cleaning up code in an existing codebase — adding a feature, fixing a bug, implementing an endpoint, extending a class, planning a GSD phase, hunting dead code or duplication, or any task that will produce a diff. Also use for any /srk:* or srk command, or when the user mentions shrinkage, reducing code, code cleanup, dead code, duplication, keeping diffs small, backwards compatibility during refactors, code maps, codebase intelligence, or token-efficient exploration. Not needed for brand-new empty projects or single-file throwaway scripts.
st-gr/abap-adt-skill/skills/abap-adt Skill
no license1★ repoCLI for SAP ABAP ADT operations, usable standalone or as a Claude Code skill
rosenjcb/spec-md/.agents/skills/spec-md Skill
1★ repoThe single entry point for *.spec.md work. It does three jobs — author or update a spec, check (lint) specs, and report test-case coverage — and identifies which job the request needs, or presents the options when the intent is unclear. Authoring produces OKF metadata, Intro, Definitions, Scope, Functional Requirements (FR-N), and QA Test Cases with stable TC-XXXX ids, plus the optional *.review.md sign-off record. Check validates frontmatter, FR/TC structure, and id integrity. Coverage cross-references each Test ID against its [TC-XXXX] tests.
ScottfreeLLC/skills/skills/ai-engineer Skill
no license1★ repoEnforce senior-level AI engineering standards when designing, implementing, or reviewing retrieval/RAG systems, embedding pipelines, LLM integrations, agentic workflows, prompt and context engineering, evals, LLM observability, MCP tools, fine-tuning decisions, classical NLP/text-processing code, or applied ML/data workflows that feed AI products. Trigger before writing "naive" AI code: ad-hoc prompt strings, vector-only retrieval by default, unbounded agent loops, missing eval plans, missing tracing, hard-coded text-processing rules where established libraries exist, train/test leakage, or context stuffing without selection/compression. Do NOT trigger for general scripting, frontend work, web APIs unrelated to AI/ML, DevOps/CI/CD unrelated to LLMOps, or pure infrastructure work.
anycloud-sh/anycloud-skills/skills/anycloud Skill
no license1★ repoAnyCloud agent skill — run AI training/batch jobs on the cheapest cloud GPU across AWS/GCP/Azure. Claude plugin + Agent Skills standard.
thevrus/consistent-ui/skills/consistent-ui Skill
1★ repoEnforce UI consistency across an entire codebase, regardless of language, framework, or styling approach. Detects drift in spacing, typography, colors, components, iconography, and interaction patterns across every UI surface. Works for web (React, Vue, Svelte, Angular, Solid, plain HTML/CSS), native mobile (SwiftUI, Jetpack Compose, Flutter, React Native), and server-rendered templates (Blade, ERB, Twig, Razor, JSP, Pug, Liquid). Generates a consistency report with P0-P3 findings and a remediation plan, then optionally fixes drift in place. Use when the user mentions "consistency", "looks different on page X vs Y", "design drift", "unify styles", "audit components", or wants to align a codebase to its design system.
Piyabordee/test-copilot/skills/test-engineer-skill Skill
no license1★ repoComprehensive test engineering knowledge base for creating, reviewing, and improving test strategies and test cases. Use when writing test cases, designing test strategies, performing security testing, checking OWASP Top 10 vulnerabilities, generating REST API contract tests, writing BDD-Gherkin scenarios for web applications, testing GraphQL queries and mutations, creating mobile app test matrices, testing microservices with circuit breakers and event-driven patterns, setting performance benchmarks, prioritizing tests by risk level, detecting project type for test framework selection, reviewing existing test coverage, generating executable test code (Playwright, Jest, Vitest, pytest, JUnit, etc.) from an approved strategy, or scaffolding CI pipelines for tests. Invoked by test-engineer-agent (strategy generation) and test-codegen-agent (code generation).
markbrutx/bannerlord-modder-plugin/skills/bannerlord-modder Skill
1★ repoA Claude Code plugin that helps you create professional Mount & Blade II: Bannerlord mods using the BUTR modding stack.
nathanonn/claude-skills-wp-abilities-api/.claude/skills/wp-abilities-api Skill
1★ repoThe same file is in 4 other repositories
roeimichael/cartographer/skills/cartographer Skill
1★ repo🗺️ Claude Code plugin: maps, audits and refactors codebases with parallel specialist reviewers
gagoar/html-effectiveness/skills/doc Skill
1★ repoClaude Code skill for generating rich, self-contained HTML documents
otoshek/otoshek-local-setup/skills/otoshek-local-setup Skill
no license1★ repoClaude Code skill to set up a local development environment for Otoshek-deployed SaaS projects
RubenBranco/Manim-Slides-Skill/skills/manim-slides Skill
1★ repoBuild animated presentations with manim-slides 5.6.0 (Manim CE + RevealJS). Use when the user wants to author slides with Python animations, render them, or convert to HTML/RevealJS, PPTX, or PDF. Includes scaffolder for new presentations and a one-shot render-and-build pipeline.
scagogogo/npm-skills/skills/npm Skill
1★ repoNPM Registry client for AI agents and developers — Skill, Go SDK, CLI, and MCP server. Query packages, manage dist-tags, publish, audit, and more with 8 mirrors and proxy support.
Shiling42/paper2notes/skills/paper2notes Skill
1★ repoClaude skill to expand a paper to self-contained lecture notes
leanspark/skills/plugins/leanspark/skills/interview Skill
no license1★ repoLEANSpark Playbook Skills — Running Lean for your AI agent (starter editions). Full packs at leanspark.ai/skill-packs.
alexandrecoura96/react-native-mvvm-guardian/skills/rn-mvvm-guardian Skill
1★ repoMVVM-first Claude Code skill + agent for React Native. Enforces MVVM, SOLID, best practices, conventions, and scalable architecture.
TheMizeGuy/ios-code-review/ios-senior-review/skills/review-ios Skill
1★ repoClaude Code plugin: senior iOS code review agent simulating both Apple App Review and a senior Apple platform engineer — 12 dimensions in 4 tiers, evidence-tagged findings, dual submission/engineering verdicts, optional multi-agent team mode with runtime simulator verification.
codacy/codacy-specs/skills/spec-improve Skill
1★ repoClaude Skill that audits any specification for AI-agent readiness
jiwangyihao/orca-conductor/skills/orca-conductor Skill
1★ repoCoordinator-side discipline for Orca multi-agent orchestration sessions: worker briefs with read-back gate, phase/step checkpoint-rewind, evidence-based interruption recovery, acceptance & safe worktree reclamation.
node-real/nodereal-skills/skills/meganode-skill Skill
1★ repoProvides NodeReal MegaNode blockchain infrastructure APIs for 25+ chains including BSC, Ethereum, opBNB, Optimism, Polygon, Arbitrum, and Klaytn. Covers standard JSON-RPC endpoints, Enhanced APIs (nr_ methods for ERC-20 token balances, NFT holdings, asset transfers), MegaFuel gasless transactions via BEP-322 paymaster, Direct Route MEV protection, Debug/Trace APIs, WebSocket subscriptions, ETH Beacon Chain consensus layer, Portal API usage monitoring, API Marketplace (NFTScan, Contracts API, SPACE ID, Greenfield, BNB Staking, PancakeSwap, zkSync), non-EVM chains (Aptos, NEAR, Avalanche), and JWT authentication. Use when building blockchain dApps with NodeReal, querying token or NFT data, setting up RPC infrastructure, configuring gasless transactions, protecting against MEV, tracing transactions, verifying smart contracts, resolving .bnb domains, or monitoring validators and API usage.
MohamedFekryyy/fekry-plugins/plugins/fekry-design/skills/match-fekry-design-core Skill
1★ repomy design taste as a portable agent skill. five style modes, motion decision gates, RTL-native rules. install it, or fork it and make your agent design like you.
nanameru/japan-localize-builder/skills/japan-localize-builder Skill
1★ repofurkanzt/claude-agenting/skills/agenting Skill
1★ repoRoute every subagent to the right model and effort — a PreToolUse gate that asks before a Claude Code workflow spends.
yennanliu/104Skill/skills/104-job-auto-apply Skill
no license1★ repo104 auto job apply Claude code skill
fabianobuscemi/Symfony-UX-LiveComponent-Skill/skills/symfony-ux-turbo Skill
1★ repoBuild SPA-like experiences in Symfony with Turbo (Drive, Frames, Streams) and Mercure broadcasting. TRIGGER when: user works with Turbo Frames, Turbo Streams, turbo_stream_listen, Mercure broadcasting, or #[Broadcast] attribute in Symfony. Covers Turbo Drive, Frames, Streams, and real-time broadcasting. DO NOT TRIGGER when: user works with traditional full-page reloads or non-Symfony Hotwire projects.
shaik-zeeshan/mnema/.agents/skills/mnema-data Skill
1★ repoPrivate, searchable memory for your Mac — records screen, audio, and activity locally; scrub it, search it, ask AI about it.
collinpeters/collin-claude-skills/plugins/github-pr-comment-reviewer/skills/github-pr-comment-reviewer Skill
1★ repoA Claude Code skill (packaged as a plugin) for systematically reviewing and resolving GitHub pull request comments.
MIPyao/useful-skills/skills/vidwise Skill
1★ repoMIPyao's open-source Agent Skills collection for Claude Code, Cursor, Codex, and all AI coding agents that support the SKILL.md format.
bnb-chain/bnb-bounty-reviewer/skills/bnb-bounty-reviewer Skill
no license1★ repoUse when reviewing BNB Chain bug bounty submissions or security findings against in-scope BNB repositories such as bsc, bsc-genesis-contract, opbnb, op-geth, greenfield, greenfield-cosmos-sdk, greenfield-contracts, greenfield-storage-provider, or tss-lib. Trigger on reports involving BSC/Parlia, Greenfield/SP, cross-chain packages, system contracts, validator logic, RPC/P2P, threshold-signing/TSS, mnemonics/keys, or exploit PoCs.
drtey/scala-spark-plugin/skills/spark-scala Skill
no license1★ repohi data engineers