$ loading_
57807 Skills & MCP tools — copy a prompt, zero pre-install, into Claude Code / Codex / Cursor.
🎓 Skill = teach the AI a way to do a job (make slides / review code / write reports), copy the prompt and go — no account needed.
Run cross-platform remote validation with Crabbox and report the actual provider ID.
Run or recover OpenClaw macOS signing, notarization, and release promotion.
Edit PDF content, pages, and structure with natural-language CLI instructions.
Build, debug, and extend end-to-end tests for the OpenClaw Control UI.
Transcribe audio to text locally with Whisper CLI, no API key required.
Access X from the CLI for posting, search, DMs, and API calls.
Search places, fetch details, reviews, and structured JSON from Google Places.
Control tmux sessions and panes to automate interactive terminal workflows.
Triage security advisories, drafts, and GHSA reports with trusted evidence.
Run Parallels smoke tests with Discord roundtrip verification across host and guest.
Generate spectrograms and feature-panel visuals from audio for analysis and presentation.
Automatically closes out code reviews with Codex as the default reviewer.
Discover and control Sonos speakers for playback, volume, status, and grouping.
An AI coding assistant for review, debugging, refactoring, and design checks.
Debug Python issues with pdb, breakpoints, post-mortem analysis, and debugpy.
Search the web, extract content, and organize research efficiently.
Diagnose OpenClaw node pairing, auth, routing, and connection issues.
Write, understand, and debug code in the Lobster programming language.
Helps maintainers triage, clean up, and resolve OpenClaw secret scanning alerts.
Automatically add redacted agent transcripts to GitHub PRs or issues.
Find meme templates, suggest formats, and generate shareable meme images.
Check Foodora order history and active delivery status from the command line.
Maintain an OpenClaw memory wiki with deterministic, source-backed page updates.
Audit and harden OpenClaw hosts for security and operational health.
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。