GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
plugin-stack
Plan the next move for an AI plugin you build: a ChatGPT app, Claude plugin or connector, Cursor plugin or MCP server. Use when asked what to do next to ship or grow one, where to start after installing these skills, for a full review across a plugin's listing, tools and widgets, or to set up `.agents/plugin-stack.md`.
optimize-listing
Optimize a live AI plugin's store listing: name, description, keywords and category, compared with the category's top listings and their recent rewrites, ending in paste-ready copy. Use for ChatGPT, Claude or Cursor listings, keywords missing against named rivals, what top apps changed in their copy, ASO, or when a plugin isn't getting installs. Not for custom GPTs, mobile apps or a first submission's copy.
find-opening
Find an opening before building an AI plugin: which ChatGPT, Claude or Cursor categories and tags are growing, which are crowded, how locked the top apps are, where one store is thin next to another, and a short ranked list of openings with dated evidence. Use when deciding what to build, asking which category is underserved or saturated, whether an idea's space is crowded, or where there's a gap in the ChatGPT app store or the Claude directory. Not for tracking named rivals or for a plugin that's already live.
design-widgets
Design an AI plugin's widgets from real ones in the stores. Pull: fetch a listing's rendered widgets. Audit: critique your widget against them. Redesign: propose a new version backed by precedent. Use for ChatGPT app widgets, MCP Apps UI, or inline cards.
audit-discoverability
Audit whether agents would find and pick an AI plugin or MCP server when a user asks: how its listing and MCP tool descriptions answer target prompts, with a labelled simulated pick against rivals. Use when asked to audit a plugin or MCP server, when agents ignore a plugin, to check prompts people should use it for against rivals, for AEO for plugins, to grade a pasted tool list or tools against a rival's, to check whether an app can be reached in a country, or to fix MCP tool descriptions and annotations such as readOnlyHint. Not for writing store copy.
agentdomains
Get and manage a free public domain (yourname.makes.fyi or yourname.agentdomains.co) for an AI agent or app using the AgentDomains CLI. Use this whenever an agent builds a website or API and needs somewhere to put it, or needs a public hostname to expose a server, create a webhook URL, or get a stable address. Covers signup, claiming a name, pointing it at an IP or CNAME, getting HTTPS, forwarding (HTTP redirect) to an existing site, reverse-proxying the name to a backend over HTTPS, delegating to your own nameservers, removing a single DNS record, and closing the account again.
visual-design
Use when choosing or reviewing how a screen, flow, or page looks — colour palette, typography, spacing, cards and surfaces, buttons, icons, illustration and imagery, onboarding and paywall visuals, dark mode — or when a UI looks generic, flat, cluttered, dated, or inconsistent across screens, or someone asks to make it look premium or modern. Picks a visual direction and expresses it as tokens for web/SaaS, Apple platforms (iOS, iPadOS, macOS, visionOS, watchOS, tvOS), Android, and React Native/Expo. Reviews screenshots and mockups as well as code. Not for UX behaviour (use ux-psychology), accessibility audits, or animation timing.
ux-psychology
Use when designing, building, or reviewing a screen, flow, or page — landing and marketing pages, onboarding, sign-up, navigation, forms, settings, dashboards, tables, pricing, checkout, empty states, error messages, permission prompts — or when a UI feels confusing, cluttered, or slow. Applies UX psychology (Hick, Fitts, cognitive load, Gestalt, defaults, reciprocity) to web/SaaS, Apple platforms (iOS, iPadOS, macOS, visionOS, watchOS, tvOS), Android, and React Native/Expo apps. Not for visual styling, colour, or animation tuning.
apple-featuring
Use when preparing an Apple platform app for App Store featuring or the Apple Design Awards — readiness reviews before a launch or major update, featuring nominations in App Store Connect, nomination timing and pitch, choosing an ADA category, or asking how to get an app noticed by Apple. Covers iOS, iPadOS, macOS, visionOS, watchOS, and tvOS apps and games. Not for general UX reviews (use ux-psychology).
accessibility
Use when building or reviewing UI for accessibility — screen readers (VoiceOver, TalkBack), keyboard and focus, colour contrast, Dynamic Type and text scaling, reduced motion, touch targets, accessible forms, captions — or when auditing against WCAG 2.2, the European Accessibility Act, or before an App Store or production release. Covers web, Apple platforms, Android, and React Native/Expo. Not for general UX or visual styling (use ux-psychology).
ru-text
Russian text quality. Triggers: вычитай, проверь текст, поправь, отредактируй, причеши, ru-text. Typography silently on any Russian output; deeper editing on request. Info-style, editorial, UX writing, business correspondence, AI-text cleanup.
ru-score
Score Russian text 0.0–10.0 across five dimensions: typography, clean language, grammar, structure, precision for the reader. Triggers: оцени текст, ru-score, оценка качества текста, насколько хорош текст, балл за текст. Use when the user wants a number rather than a list of findings. Never edits a file.
ru-check
Full Russian text quality check against the whole corpus. Triggers: вычитай, вычитай через ru-text, прогони ru-text, проверь текст по ru-text, ru-check, полная вычитка. Use when the user asks to proofread Russian text, or when a project gate names ru-text. Returns findings with the rule behind each and a proposed replacement; never edits a file. Self-initiated runs start with a fast triage and escalate on evidence; an explicit request always runs the full corpus.
talivia-agent-kit
Set up Talivia revenue-first website analytics with MCP, then verify live traffic and revenue attribution.
taisly-social-media-posting
Connect AI agents to Taisly through MCP to publish and schedule videos, inspect history, and manage reposts.
codex-reset
Answer questions about OpenAI Codex usage-limit resets and Codex outages with the Codex Reset MCP tools or its public JSON API (reset forecast, verified reset record, service status). Use when the user asks whether or when Codex limits reset, why Codex stopped working, or whether to wait for a reset.
supercov
Measures test coverage and code quality in a repository with the supercov CLI, and turns what it finds into small, focused tests or fixes. Use when the user asks to add or improve tests, find untested code or raise coverage, or find what to refactor. Works with JavaScript, TypeScript, Python, Ruby, Rust, Go, Java and Kotlin projects.
supercov-security
Scans a repository's source for security vulnerabilities with the supercov CLI, pointing to the line of each finding and mapping it to CWE classes. Use when the user asks for a security scan or audit, whether code is secure, or to find vulnerabilities, injection, hardcoded secrets or other insecure code.