The catalog
613,297 rows, by stacks then stars
xvirobotics/metaskill/examples/data-science/.claude/skills/evaluate-model Skill
64★ repoLoad the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.
The same file is in 1 other repository
konraddzbik/architecture-diagram-skill/skills/architecture-diagram Skill
64★ repoBuild interactive, click-through architecture diagrams for software systems — a self-contained single HTML file with animated step-by-step flows, mode toggles (dev/prod, offline/online, v1/v2), dark/light theme, and a side panel with payload details, plus a companion markdown description. Use when the user wants to visualize or design a system: architecture diagram, service map, data flow, RAG/agentic flow, microservices topology, integration diagram, CI/CD or data/ETL pipeline, multi-agent system, or onboarding diagram — or to design a new service's flows before building. Natural-language triggers: 'I'm building X, what should the flow look like', 'pokaż jak działa system', 'diagram architektury', 'wizualizacja systemu', 'klikany diagram'. Do NOT use for static diagrams that belong inline (Mermaid/PlantUML), slide decks, or printable/PDF handouts — this produces interactive HTML for browser consumption.
The same file is in 1 other repository
Airflow and workflow orchestration
vaquarkhan/data-engineering-agent-skills/skills/airflow-and-workflow-orchestration Skill
64★ repoGuides agents through workflow orchestration design and operation across Airflow-style DAGs, cloud-native schedulers, and event-driven pipeline control planes. Use when building or modifying workflow dependencies, retries, triggers, sensors, SLAs, or cross-system pipeline coordination.
FTShare-Lab/FTShare-skills/ftshare-market-data Skill
64★ repo非凸科技金融数据技能集。覆盖 A 股股票列表、全字段/实时行情列表、分时价格、IPO、大宗交易、融资融券、单股行情估值、可转债、ETF、基金、指数(含分页指数描述、下载描述 PDF、权重汇总/成份明细、下载权重 xlsx、详情/K 线/分时)、宏观经济,以及港股公司介绍/估值分析/基础视图/K线、东财美股列表/历史K线/最新行情、native 美股基础信息/利润表/现金流量表/资产负债表、港股财报三表(利润/现金流/资产负债)/东财港股指数日K线等接口(market.ft.tech / ftai.chat)。用户询问 A 股、港股、美股的代码、行情、估值、K线、指数权重/描述、新闻与宏观数据时使用。
AlekseiUL/sprut-agent-kit/skills/agent-builder Skill
64★ repoСоздаёт полноценных persistent skill-агентов с собственной памятью, system prompt-ом и data-файлами. Автоматизирует создание агентов как у OpenClaw (Doctor, AutoMechanic и т.д.).
landing-ai/ade-document-processing-skills/plugins/ade-document-processing/skills/document-extraction Skill
64★ repoAgent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants
anotb/management-consulting-plugin/dist/dispatcher Skill
64★ repoConsulting engagement lifecycle in one skill: strategy and framework analysis, financial modeling, proposals and pricing, implementation planning, due diligence, change management, governance, and client deliverables. Use for any management-consulting task, then load the matching reference file below.
TserenTserenov/FMT-exocortex-template/.claude/skills/_template Skill
64★ repoOne line — used in CLAUDE.md system-reminder and the skill catalog.
0xzr/freellmpool/io.github.0xzr/freellmpool MCP server
64★ repoPool 18 LLM providers through MCP: ask, panel, tokenmax, route, models, quota, and stats.
Agent360dk/browser-mcp/io.github.Agent360dk/browser-mcp MCP server
64★ repoGive AI agents control of your real, logged-in Chrome. Chrome extension + MCP server, 34 tools.
FROWNINGdev/django-orm-lens/io.github.FROWNINGdev/django-orm-lens MCP server
64★ repoDjango ORM static-analysis MCP. 10 tools: models, relations, migrations, indexes, signals, N+1.
KuudoAI/amazon_ads_mcp/io.github.KuudoAI/amazon_ads_mcp MCP server
64★ repoAmazon Ads API MCP server for Amazon Advertising API
Tampermonkey/tampermonkey-mcp/io.github.Tampermonkey/tampermonkey-mcp MCP server
no license64★ repoMCP server to manage your Tampermonkey scripts
danmartuszewski/hop/io.github.danmartuszewski/hop MCP server
64★ repoSSH connection manager with MCP server for AI-assisted operations across servers.
kushneryk/join.cloud/io.github.kushneryk/join.cloud MCP server
64★ repoCollaboration rooms for AI agents. Real-time messaging + standard git.
palewire/datawrapper-mcp/io.github.palewire/datawrapper-mcp MCP server
64★ repoA Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants
vgnshiyer/apple-books-mcp/io.github.vgnshiyer/apple-books-mcp MCP server
64★ repoAccess your Apple Books library, annotations, reading progress, and highlights through Claude
confluentinc/agent-skills/skills/confluent-skill-reviewer/evals/mock-skills/bad-frontmatter Skill
64★ repoAI agent skills for stream processing and event streaming
zerogpu/zerogpu-router/agents/claude/skills/status Skill
64★ repoCut inference costs without dumbing down your agent.
babyworm/rtl-agent-team/skills/arch-review Skill
64★ repoRead-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.
crisandrews/ClawCode/skills/whoami Skill
64★ repoPersistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.
paulinevos/claude-stuff/plugins/git-workflow/skills/resolve-merge-conflict Skill
64★ repoMy Claude stuff (skills, agents and whatnot.)
yorkeccak/scientific-skills/skills/patents-search Skill
64★ repoSearch global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.
The same file is in 19 other repositories
OvOhao/auto-paper-collecter/skills/auto-paper-collecter Skill
64★ repoPersonal research-paper radar. Fetches the latest papers and code repos for the user's keyword subscriptions across arXiv, Crossref (IEEE/ACM), Semantic Scholar, GitHub, HuggingFace, Papers with Code and RSS; deduplicates against history; then YOU (the assistant) expand the queries, filter for computer-science relevance, write Chinese summaries, detect hot sub-fields, and emit a Markdown + HTML digest (optionally emailed). Use when the user asks to "run my paper radar / 文献雷达", "check for new papers", "what's new in my topics", "今天有什么新论文 / 最新文献", "today's research digest", or to configure their keyword subscriptions / sources / schedule.
JuliaIO/gRPCClient.jl/skills/grpcclient-jl-dev Skill
64★ repoWork on the gRPCClient.jl package itself. Covers running the Go test server, running and extending the test suite, regenerating test stubs with protoc.sh, building the docs, benchmarking and stress testing with gRPCClientUtils, and navigating the libcurl transport in src/Curl.jl. Use when editing files in this repository (src/Curl.jl, src/gRPC.jl, src/Unary.jl, src/Streaming.jl, src/ProtoBuf.jl, test/runtests.jl) or debugging the client's transport, deadline watchdog, or streaming pumps. For calling a gRPC service as a user of the package, use the grpcclient-jl skill instead.
DingDuff/dingduff-public/plugins/dingduff/skills/dingduff-legal-analysis Skill
no license64★ repoFree legal-research skills and Claude plugin from DingDuff — built by lawyers, for lawyers. Also home to the DingDuff installation & help wiki.
EmilHvitfeldt/slidecrafting-book.com/skills/quarto-revealjs Skill
no license64★ repokoriym/xdebug-mcp/skills/xdebug Skill
no license64★ repoEnable AI to debug PHP with Xdebug
devxoul/vibe-notion/skills/vibe-notionbot Skill
no license64★ repoNotion automation CLI for AI agents
Mindgard/ai-ide-skills/skills/ai-ide-source-audit Skill
no license64★ repoopen-agent-ai-security/praxen/skills/behavior-verifier Skill
64★ repoRun a Praxen behavior analysis against an AI agent — or author the Worker Remit that drives one. Praxen verifies intended vs observed behavior by comparing an agent's declared policy (Worker Remit) against available evidence — source code, live deployment state (memory files, logs, configs), governance docs, or behavioral artifacts — and reporting where behavior diverges from declared intent, scored against the RAISE framework and OWASP LLM/Agentic guidance. Produces a self-contained HTML report plus JSON and TXT under ./reports/. Use when asked to run a Praxen analysis, verify an agent's behavior against its remit, evaluate policy-implementation divergence, audit observed behavior against declared intent, or create / write / draft / build / author a Worker Remit (from source code, documentation, or a prose description). Remit authoring uses WORKER_REMIT_template.md.
USS-Parks/Lamprey-Harness/skills/debug Skill
64★ repoLocal-first, multi-provider coding desktop with Codex-style Steering, task controls, inline artifacts, PR review, tools, skills, MCP, and research.
newtype-01/newtype-skills/skills/super-workbench Skill
no license64★ repoypyik0669/ctf-codex/skills/ctf Skill
64★ repo面向 Codex 的社区安全审计 Skill:用于授权 CTF、上线前安全检查、项目加固和 AI 安全报告整理
splunk/splunk-agent-skills/skills/splunk-search Skill
64★ repoOpen source, enterprise-ready AI skills for Splunk use cases, built for secure discovery, consistent execution, and production-grade customer workflows.
lguz/humanize-writing-skill/skills/humanize-writing Skill
64★ repoRewrite AI-generated text to sound human. 3-pass editing system with 36+ banned words, 10 structural patterns, and a quality checklist. Works with any LLM — Claude, ChatGPT, Gemini, Cursor, Windsurf. Also available as a Claude Code plugin.
The same file is in 2 other repositories
jordanrubin/FUTURE_TOKENS Skill
no license63★Every AI output has structural blind spots determined by the generation process itself. Future Tokens operations are named, composable instruments that target specific blind spots. They surface new information on every pass because expanding the output changes the blind spot geometry.
ishwarjha/claude-marketing-research-skill/marketing-research Skill
63★ repoUse this skill for any marketing research, product positioning, copywriting research, or audience profiling task. Triggers include: "research my product", "develop my value proposition", "profile my avatar", "understand my market", "create a unique mechanism", "market awareness", "market sophistication", "ideal customer profile", "ICP research", "positioning research", "copywriting research", "features and benefits", "competitor research", "competitive analysis", or any request to deeply research a product or audience for marketing purposes. Use this skill proactively whenever a user wants to prepare materials for sales copy, landing pages, ads, email sequences, or any persuasion-focused content. If a user says "help me understand my market", "I need to figure out my messaging", "who is my customer", or "what makes my product different", this skill applies immediately.
Boom-Vitt/claude-thai-skills/skills/thai-address Skill
63★ repoUse this skill for any task involving Thai postal address parsing, validation, formatting, or province/postcode lookup. Trigger whenever the user asks to: parse a Thai address into fields, validate a 5-digit Thai postcode, look up a province from its postcode, or format an address for a shipping label. Also trigger for requests like "แยกที่อยู่ไทย", "ตรวจรหัสไปรษณีย์", "แปลที่อยู่เป็นภาษาอังกฤษ", "ที่อยู่จัดส่ง", or any variation involving Thai addresses with ตำบล/แขวง/อำเภอ/เขต/จังหวัด.
Bhala-Srinivash/nse-trading-skills/fibonacci-trading Skill
63★ repoFibonacci retracement and extension trading for NSE/BSE equities. Covers entry zones using retracement levels, profit targets using extension levels, and confluence zone identification. Use when the user asks: "fib levels for [stock]", "Fibonacci retracement", "fib extensions", "where to enter on pullback", "what are the retracement levels", "golden ratio level", "Fibonacci targets", or any question about Fibonacci-based trading levels for Indian equities.
sruthik27/creating-claude-md Skill
63★Use when the user wants to create a new CLAUDE.md from scratch for a repository, bootstrap project memory for a new repo, set up a repo for Claude Code for the first time, or completely rewrite an existing CLAUDE.md deemed unsalvageable. Produces a lean, high-signal file under 80 lines (120 hard cap) by scanning the repo for mechanical content (stack, commands, structure) and interviewing the user for judgment content (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages). NOT for auditing or incrementally improving an existing CLAUDE.md — that is the claude-md-improver skill's role.
Myco: Agent-First Cognitive Substrate
Battam1111/Myco/io.github.Battam1111/myco MCP server
63★ repoAgent-first cognitive substrate: 20 verbs + 50 lint dims over a self-validating graph.
DeepAgentLabs/mcp-server/io.github.DeepAgentLabs/deep-agentic-core-mcp MCP server
no license63★ repoUnified MCP server for AgenticLens and Agentic Chaos capabilities.
ZengLiangYi/ChatCrystal/io.github.ZengLiangYi/chatcrystal MCP server
63★ repoLocal-first AI PKM memory for coding conversations.
dtkmn/mcp-zap-server/io.github.dtkmn/mcp-zap-server MCP server
63★ repoSafe, self-hosted OWASP ZAP operator for guided AI security scans and reports.
Microsoft MCP Server for Enterprise
microsoft/EnterpriseMCP/io.github.microsoft/EnterpriseMCP MCP server
63★ repoOfficial Microsoft MCP Server to query Microsoft Entra data using natural language
tomohiro-owada/devrag/io.github.tomohiro-owada/devrag MCP server
no license63★ repoLightweight local RAG MCP server. 40x token reduction.
mailtrap/mailtrap-mcp/io.mailtrap/mcp MCP server
63★ repoOfficial MCP Server for Mailtrap
Ai augmentation not automation
fatihguner/foreman/plugins/foreman/skills/ai-augmentation-not-automation Skill
63★ repoAI-powered strategic advisor for entrepreneurs. 158 skills, 24 diagnostics, 21 playbooks, 9 industry packs. Claude Code + Codex + OpenClaw.
iheanyi/tasuku/.agents/skills/tasuku Skill
no license63★ repoLightweight multi-agent task management that promotes agentic knowledge capture
Bootstrapping repository memory
xhyqaq/superpowers-plus/skills/bootstrapping-repository-memory Skill
63★ repoUse when a repository or subsystem lacks usable canonical memory and needs an initial memory baseline
The same file is in 1 other repository
logly/mureo/skills/_mureo-amazon-ads Skill
63★ repoYour local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.
lucasfcosta/backpressured/skills/visual-review Skill
63★ repoUse when a backpressured loop has a front-end/UI change and needs to compare the rendered result against its design reference (a Figma frame or images on a Linear ticket) — catching layout, spacing, contrast, and visual-consistency defects automated tests and happy-path clicking miss.
gnurio/porter-strategy-skills/skills/audit-strategy-consistency Skill
no license63★ repo12 executable AI agent skills for competitive strategy analysis, extracted from Michael Porter's Competitive Strategy. Five forces, competitor profiling, strategic groups, market signals, generic strategies, competitive moves, and industry-type playbooks — grounded in Porter's original frameworks.
Cyfrin/claude-docs-prompts/skills/docs-site Skill
no license63★ repoInstructions for building and maintaining Cyfrin documentation sites. Use this skill when working on a Next.js docs site with MDX, Tailwind CSS, and the Cyfrin docs template.
timvw/wt/plugins/wt/skills/wt Skill
63★ repoA fast, simple Git worktree helper written in Go
VictoriaMetrics/skills/plugins/query/skills/alertmanager-query Skill
63★ repoThe official Agent Skills for VictoriaMetrics products
The same file is in 1 other repository
Claude sdk integration patterns
manutej/luxor-claude-marketplace/plugins/luxor-ai-integration/skills/claude-sdk-integration-patterns Skill
no license63★ repoProfessional Claude Code marketplace with 140 development tools: 67 skills, 28 commands, 30 agents, 15 workflows
The same file is in 2 other repositories
hakilee/design-farmer/skills/design-farmer Skill
no license63★ repoAgent skill that turns design system quality from "best effort" into a repeatable engineering workflow.
typefully/agent-skills/skills/typefully Skill
63★ repoAI agent skills for drafting and scheduling social media posts via Typefully
The same file is in 1 other repository