$ loading_
35753 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.
Helps AI break down complex problems step by step and reflect on its reasoning.
Store and recall cross-conversation details with persistent knowledge-graph-based memory.
Let AI read, search, and manage local Git repositories and commit history.
Fetch web pages and convert them to Markdown for AI reading and analysis.
Search the live web and codebase in real time for company research and information retrieval.
Search the web and local results privately to quickly find information and resources.
Automate web interactions, scraping, and testing tasks using a headless browser.
Run cross-platform remote validation with Crabbox and report the actual provider ID.
Capture frames or short clips from RTSP and ONVIF cameras.
Use Gemini for one-shot prompting, summaries, generation, coding, and tool routing.
Refactor OpenClaw docs pages with source-checked preservation, clearer structure, and verification.
Search and analyze GitHub archive issues, PRs, and repo workflow status.
Transcribe audio into text or speaker-separated transcripts with OpenAI APIs.
Search places, fetch details, reviews, and structured JSON from Google Places.
Search and manage Granola archives, sync status, notes, transcripts, and counts.
Control tmux sessions and panes to automate interactive terminal workflows.
Triage security advisories, drafts, and GHSA reports with trusted evidence.
Build quick throwaway prototypes to validate options and deliver a verdict.
Automate web page workflows, login checks, tab handling, and recovery steps.
Search the web, extract content, and organize research efficiently.
Diagnose OpenClaw issues by choosing logs, probes, and proof paths first.
Generate spectrograms and feature-panel visuals from audio for analysis and presentation.
Access X from the CLI for posting, search, DMs, and API calls.
Transcribe audio to text locally with Whisper CLI, no API key required.
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。