$ loading_
35650 Skills & MCP tools — copy a prompt, zero pre-install, into Claude Code / Codex / Cursor.
🎓 Skill = teach the AI how to do a task, copy & use; 🔌 MCP = connect the AI to an external tool/data source, usually needs a key.
Demonstrate MCP tools, resources, and prompts for comprehensive protocol capability testing.
Automate browser interactions, capture screenshots, and run end-to-end testing workflows.
Help development and operations teams investigate errors, manage issues, and analyze performance monitoring data.
Automate web interactions, scraping, and testing tasks using a headless browser.
Plan and run end-to-end pre-release validation for OpenClaw plugins.
Run cross-platform remote validation with Crabbox and report the actual provider ID.
Reproduce and record real Telegram interactions on Crabbox for behavior proof.
Refactor OpenClaw docs pages with source-checked preservation, clearer structure, and verification.
Debug Python issues with pdb, breakpoints, post-mortem analysis, and debugpy.
Choose and run the safest, cheapest OpenClaw test and validation path.
An AI coding assistant for review, debugging, refactoring, and design checks.
Run, debug, rerun, and interpret OpenClaw Parallels install and smoke checks.
Create OpenClaw Docker end-to-end tests and live provider lanes.
Capture and automate macOS UI actions with Peekaboo CLI for scripting and testing.
Inspect, patch, validate, and publish OpenClaw GHSA advisories securely.
Diagnose OpenClaw node pairing, auth, routing, and connection issues.
Build, debug, and extend end-to-end tests for the OpenClaw Control UI.
Debug Node.js apps with inspect, breakpoints, heap, and CPU profiling.
Audit and harden OpenClaw hosts for security and operational health.
Prepare and verify OpenClaw stable or beta releases and release notes.
Diagnose OpenClaw issues by choosing logs, probes, and proof paths first.
Automatically closes out code reviews with Codex as the default reviewer.
Run, debug, monitor, and summarize OpenClaw release CI workflows.
Preview local channel message flow fixtures to inspect conversation flow behavior.
从访谈内容留存、转写回看，到主题归纳与产品建议，一套串起用户研究整理流程。
从流量采集、营销归因到数仓查询与看板输出，一套串起自动取数和分析闭环。
从读取设计稿、提取上下文到映射组件库与同步评审，这套组合很适合设计到前端落地的协作链路。
In-depth guides on Skill / MCP setup and security — beyond the directory listings
普通聊天 AI 很难真正读懂大型仓库，因为它缺少结构、上下文和可验证的检索路径。本文从 0 到 1 搭一个只面向本地代码库的 Cursor 助手：能查结构、追调用链、看 diff、给重构建议，还能尽量压住幻觉。
Agent-hop 是一个基于 Rust 的 TUI，支持在进行中的 Claude Code 聊天里切换到其他编程代理，尽量不丢失上下文。项目作者提到，它最早源自一个简历与搜索工具，后来因为使用过程中的阻碍，单独做成了现在的界面。
Harden.run 表示，针对能够生成任意代码的 Coding Agent，单靠传统红队测试并不够。他们通过后训练网络安全小模型、调整推理方式，并结合 inline reference monitoring 等程序分析手段，在 LinuxArena 和 SleightBench 上取得了超过 GPT5.5-xhigh 的成绩。