Windsurf skills

Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional). Use when the user wants to eval an Expo…

Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional). Use when the user wants to eval an Expo…

Create, modify, debug, and deploy Apify Actors, and write their input and output schemas. Use when building an Actor from scratch, changing or troubleshooting Actor code, generating or updating .actor schema files, or…

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases…

The quality-ranked discovery engine for AI coding skills, plugins and MCP servers across Claude Code, Codex, Cursor, Windsurf, Cline and more.

Turn an architectural mistake into a durable, enforceable rule. Use right after catching drift, a repeated bad pattern, or a review finding you want to stop recurring — or whenever someone says "add a rule so this never…

Derive what changed between two published versions of @raycast/api, which Raycast ships with no release notes. Fires on "what's new in @raycast/api X", "is it safe to upgrade", "derive a changelog", "they don't publish…

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

让你的 AI 不敢摆烂。用大厂 PUA 话术穷尽一切方案。触发条件:(1) 任务失败 2+ 次或反复微调同一思路; (2) 即将说'我无法解决'、建议用户手动操作、未验证就归因环境; (3) 被动等待——不搜索、不读源码、只等指示; (4) 用户不满:'try harder'、'stop giving up'、'换个方法'、'为什么还不行'、'你再试试'、'你怎么又失败了'。适用于所有任务类型。首次失败或已知修复正在执行时不触发。

WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies…

Analyze an existing web application, identify safe user-visible capabilities across routes, forms, server actions, handlers, and schemas, then implement first-party WebMCP tools and validate discovery and invocation…

Generates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, implements NgRx state management, applies RxJS patterns, and optimizes bundle performance. Use when building Angular…

MUST USE when the user or agent wants anything related to the AgentsEarth world: joining, genesis, avatar evidence, memory, live conversations, offline letters, movement, discovery, skill sharing and trading, the…

Find every AI agent skill in your repos, spot the duplicates teams keep rebuilding, and catch the risky ones. Claude Code, Codex, Cursor, Copilot, Gemini and MCP.

Codex computer use, decoupled from the app, for usage inside any harness.

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Use this skill whenever an Agent needs to query, find, install, deploy, update, tag, adopt, diagnose, or safely remove Skills Hub content, including natural-language requests to manage Skills for Codex, Claude Code,…

Plan an A/B test by script: sample size per variant, days to run, stopping rules. "how many visitors per variant"

Full-fledged local-first AI agent harness combining ROMS (RAG, OKF, MCP, Skills), Decision AI, correction memory, and reviewable workflow preparation.

主动渗透测试工具链。覆盖信息收集、端口扫描、漏洞扫描、Web 渗透、SQL 注入、目录爆破、密码破解等场景。 通过 MCP server(pentestMCP / mcp-security-hub)将 20+ 安全工具暴露给 AI agent。 触发关键词:渗透测试、端口扫描、Nmap、漏洞扫描、Nuclei、SQL 注入、SQLMap、目录爆破、FFUF、密码破解、Hashcat、信息收集、子域名、Web 渗透、ZAP、Burp。

Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for…

Operate Alibaba Cloud FC Agent Sandbox cloud sandboxes — create isolated Linux environments, run untrusted code and shell commands, transfer files, and clean up — via the ebx CLI, the easy_sandbox Python SDK, or MCP…

Babysits an open GitHub PR until merge-ready. Use when asked to watch a PR over time — not for one-shot comment resolution or one CI failure. GitHub (incl. Enterprise) only.