$ loading_
21519 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.
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.
Fetch web pages and convert them to Markdown for AI reading and analysis.
An AI coding assistant for review, debugging, refactoring, and design checks.
Diagnose OpenClaw issues by choosing logs, probes, and proof paths first.
Convert text into high-quality speech with a macOS say-like workflow.
Delegate coding tasks to background AI coding agents for implementation and changes.
Create and review technical docs and agent instruction files in repositories.
Transcribe audio into text or speaker-separated transcripts with OpenAI APIs.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Deeply review code and fix only small, high-confidence OpenClaw bugs.
Write, understand, and debug code in the Lobster programming language.
Manage, authenticate, call, and inspect MCP servers and tools over HTTP or stdio.
Chat directly with the Discord-backed OpenClaw agent in real time.
Summarize CodexBar local cost logs by model for Codex or Claude.
Route coding-agent requests into the right ACP or acpx session flow.
Search and analyze past session logs with jq for context and insights.
Maintain an OpenClaw memory wiki with deterministic, source-backed page updates.
Trigger multi-agent workflows for writing and task orchestration with prose.
Transcribe audio to text locally with Whisper CLI, no API key required.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Use Gemini for one-shot prompting, summaries, generation, coding, and tool routing.
Create, revise, and validate AI skills before deployment.
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
一位做了约 1.5 年 AI agent 的软件工程师发布了 Approv。它通过一次 API 调用，在代理执行高风险操作前暂停流程，让人类经由 WhatsApp 或 SMS 完成审批，同时生成可独立验证的签名审计轨迹。
如果你已经在 Codex 里写代码，但做方案草图、标注修图、生成演示页还得来回切工具，Cowart 正好补上这块。本文带你从安装到实战，把无限画布、图片生成、标注修改和 HTML 幻灯片串成一条工作流。
FixBugs 是一款面向生产环境故障排查的 agent，可结合上下文在沙箱中复现问题、定位根因、生成修复并完成验证。目前提供自托管 VSCode 扩展和 GitHub App 两种形态。