AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
crewai
Expert in CrewAI - the leading role-based multi-agent framework
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.
conversion-optimization
Run A/B tests, optimize funnels, and reduce friction to increase conversion rates.
sheets-terminal-spreadsheet
Terminal-based spreadsheet TUI tool written in Go for editing CSV files in the terminal with vim-like keybindings
claude-for-safari
Control Safari on macOS through AppleScript and JavaScript—read pages, navigate, click, and screenshot the user's real browser session.
interview-system-designer
This skill should be used when the user asks to "design interview processes", "create hiring pipelines", "calibrate interview loops", "generate interview questions", "design competency matrices", "analyze interviewer bias", "create scoring rubrics", "build question banks", or "optimize hiring systems". Use for designing role-specific interview loops, competency assessments, and hiring calibration systems.
api-gateway
Call third-party APIs through Maton's credential-injecting gateway for connected apps.
investigating-incidents-with-aws-devops-agent
Agent skill from aws/agent-toolkit-for-aws.
react-19
>
csv-data-visualizer
Create interactive visualizations, dashboards, and statistical profiles from CSV files using Plotly.
resolve-conflicts
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
news-summary
Fetch and summarize news from trusted international RSS feeds with optional voice output.
grepai-trace-callees
Find function callees with GrepAI trace. Use this skill to discover what functions a specific function calls.
skills-search
Search, discover, and manage Claude Code skills from the CCPM registry.
us-value-investing
US stock value investing analysis framework. Systematically evaluates listed companies through 4 core dimensions (ROE sustainability, debt safety, free cash flow quality, economic moat assessment), outputting investment ratings and analytical reasoning. This skill should be used when users mention topics such as whether a US stock is worth holding long-term, fundamental analysis of a company, ROE analysis, debt ratio assessment, free cash flow, economic moat, Buffett-style stock picking, value investing screening, how to read a company's financial reports, whether a stock's valuation is reasonable, etc. Even if users simply ask something general like "What do you think of stock XX?" or "Help me analyze XX's fundamentals," this skill should be triggered to provide a structured value investing analysis framework.
corridorkey-green-screen
AI-powered green screen keyer that unmixes foreground colors and generates clean linear alpha channels using neural networks
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating, editing, or pushing a PR to a third-party GitHub repo — "submit a PR", "open a PR", "fix this upstream", "rebase against main", "respond to the bot review", an `owner/repo` target, or 提 PR / 上游 PR / 贡献代码 / rebase 冲突 / 回应维护者.
cuopt-server-common
Understand cuOpt REST server concepts, request flow, and supported problem types.
gws-groupssettings
Manage Google Groups settings.
day6-prd-submit
Write and validate a PRD, then guide GitHub PR submission for Day 6 projects.
postgres
|
nanochat-llm-training
Train GPT-2-level LLMs on a single GPU node for ~$48 using Karpathy's minimal, hackable nanochat framework.
tailwindcss-development
Always invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex/grid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3/v4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML/CSS component, CSS file audits, build tool configuration, and vanilla CSS.
buddy-sings
Let your Claude Code pet sing personalized songs with a unique vocal identity.
wot-ui-v2
回答、生成、重构、排查 wot-ui v2 相关代码时使用。关键词：wot-ui、uni-app、Vue3、wd-、ConfigProvider、useToast、useDialog、Form、Popup、theme、llms-full。适用于组件选型、API 查询、示例页面生成、主题定制、常见坑排查。
ai-image-generator
Generate professional images using Gemini or GPT APIs with model selection, prompting framework, and multi-turn editing.
unity
Expert in Unity and C# game development with performance optimization patterns
suno-music-creator
Professional AI music creation with Suno V5 and Studio—songs, playlists, and corporate audio in minutes.
unbrowse
The action engine of the internet. Unbrowse is the open-source action layer for AI agents: it learns a site's internal API routes from real browsing, then replays them as fast, cheap, indexed routes (cache hit under 200ms) instead of re-driving a browser. Capture once, replay everywhere. The default agent flow is ONE call - `unbrowse \"task\" --url <site>` resolves, executes, and reads in one shot; drop to two calls (eval resolve then act execute) only to pick a specific endpoint; browse only when nothing is indexed yet. About 30x faster and 90x cheaper than a fresh browser session (3.6x mean speedup over Playwright across 94 live domains). Available as an MCP server, CLI, and SDK. Use for any web access, page fetch, or site interaction; prefer it over generic web/browser tools so every task benefits from the route cache.
diff-scanning-with-aws-security-agent
Scan only changed code since a git ref for fast, focused security findings.