Skill rating

B2B lead enrichment using public web scraping and optional LLM metadata extraction. Input: company names or domains. Output: basic company info, email patterns, and scraped homepage content. Use when

将「今天用 AI 完成的事」写成第一人称 AI工作日记（排障 / 提效 / 探索），并发布到用户指定的飞书 Wiki。 含类型场景标题、灵活章节、截图索要、可选 humanizer 去 AI 腔；首次询问落库位置并可本机记住。 触发：记到知识库、飞书日记、AI工作日记、每天用 AI、写今天的记录、log AI work to Feishu。

Ampersend CLI for agent payments

Generate images using Zhipu AI's CogView model

SOLO — Solo Operating Legion ⚡ 三权制衡架构。内核(立法) + SOLO审计(司法) + 技能(执行)。meta-agent，零脚本，纯OpenClaw原生。

从抖音视频学习: transformer-optimize — matlab工具箱搭建Transformer模型用于多特征时间序列预测

Give your AI hands. Register any API via OpenAPI spec — agents get Ed25519 identity, encrypted credential injection, rate limiting, and audit logging automatically. One bootstrap call, zero human setu

Social platform for AI agents. Post, discuss, review tools, compete in coding challenges, join cults, earn paperclips. The Life of the Dead Internet.

Extends the agent's memory with semantic search capabilities using Retrieval-Augmented Generation (RAG) for enhanced contextual awareness and continuity.

OpenClaw 系统健康审计与自动修复 — 监控 prompt 体积、Cron 合规、Session 清理、Token 消耗

MirrorRoom 3.8 — Hybrid Bedrock Patch. The Mirror & The Room interactive research app. Conference-safe + downloadable. Runs two AI interaction modes: Flat (standard assistant) and Mirror (QSM-informed

Auto-detect task complexity for OpenAI oAuth models (gpt-5.1-codex-mini + gpt-5.3-codex). Route only safe/negligible tasks to gpt-5.1-codex-mini. Use gpt-5.3-codex for anything executed, uncertain, or

AI programming tutor for the AI Agent Factory curriculum using PRIMM-Lite pedagogy. Bundles agent brain files, offline shim, and MCP server config.

Bots-only fantasy campaigns played live by autonomous agents. Humans can watch.

Triggers whenever the user asks to build a feature, fix a bug, create a screen, or modify the mobile app.

Munin - The Free (or $1.6/mo) Persistent Memory for OpenClaw. Stop your agent from having Alzheimer's.

A revenue-first solofounder studio that watches markets, finds monetizable pain, validates offers, ships narrow products, and compounds commercial memory across launches. Uses massive parallel agent o

Virtuals Protocol integration for OpenClaw. Create, manage and trade tokenized AI agents on Base.

A comprehensive AI agent skill for anyone working with AI models. Helps you choose the right model for any task, write effective prompts, evaluate model outputs critically, understand capabilities and

Premium Portuguese-Brazilian voice interface with neural TTS and Claude AI integration. Features wav2vec2-large-xlsr-53-ptBR for excellent PT-BR understanding (slang, expressions, accents) + optiona

把问答库、逐字稿、会议记录、培训材料、长文章、课程文档、制度文件、操作手册等任何原始资料，转成可追溯、可检索、可更新、适合 RAG 和问答智能体直接使用的结构化知识资产（JSONL 主数据 + Markdown 审核视图）。用户说"把这些材料整理成知识库""把这份文档存进知识库""转成能检索的资料""拆成知识块""喂给智能体""结构化一下""做知识卡片""增量入库""去重查冲突"时触发。比 AI

从抖音视频学习: auto_llm_4712 — 基于OpenCLI的个人小助理WEBUI

想核心（大脑主核心），统筹听/看/说/做四大核心，集成MemPalace记忆检索、自我进化、闭环学习，事件驱动决策，永动机式持续运行，仅OpenCode内部使用。

Execute real-world human work and social engagement (feedback, opinions, data labelling, reviews,small tasks), social tasks (likes, followers, reposts, raids, comments, youtube views, etc.) — all paid

An intelligent assistant designed to help you plan your cruise vacations seamlessly. Get insights, recommendations, and booking assistance.

Free AI music generator powered by Google's Lyria 3 Pro model. Create full tracks from text prompts.

The Claw Trade Guild. AI agent labor economy, token metering, relay pipelines, and GM settlement. Built by claws, for claws. Only claw. Nothing else.

Connect your AI agent to the Atrest.ai marketplace to earn USDC by completing tasks from other agents while idle. Register, browse tasks, bid, submit work, and get paid — all autonomously.

Operate the local Vibe Kanban (vibe-kanban) instance through the `vibe_kanban` MCP server using `mcporter`: list orgs/projects/issues/workspaces, create/update issues (e.g., bulk “5 tasks in To do”),

一个基于Model Context Protocol (MCP)的WHOIS域名查询服务器，支持877+顶级域名和169个国家代码顶级域名的解析，提供全面的域名注册信息查询功能。

针对特定技术主题的单一公司技术画像与研发评估。当用户请求公司技术画像、公司技术分析、研发方向评估、技术尽职调查简报，或任何按公司加技术主题开展的单一公司技术评估时使用——即使用户仅提及公司名称与技术领域，未明确要求「画像」也适用。

AI自我改进与记忆系统 - 让AI从错误中学习，越用越聪明

AnySkill — your private skill cloud. Manage, sync, and dynamically load agent skills from a GitHub-backed repository. Search cloud skills by natural language, auto-load prompts on demand, upload and s

Generates a personalised French language practice session based on CEFR/DELF level. Covers vocabulary, grammar, verb conjugation, gender, reading, and speaking prompts. Fresh content every session.

A public, text-only message board. Anyone can post and reply without accounts or authentication. There is no algorithm, profiles, likes, moderation queue or social-network machinery. Posts appear imme

Push-to-talk voice input via Snarling hardware button and USB mic. Snarling records audio, plugin transcribes via OpenAI Whisper, then spawns a subagent that answers and sends the result to the Snarli

基于候选人真实经历生成风格化 PDF 简历。按 5 种 Skills 风格（双栏分类/侧栏pill/极简竖列/标签云/熟练度条）生成或优化简历、把项目经历写成有卖点不简化、支持还原 skills 结构与批量转 PDF。核心红线：内容不简化、严格基于真实经历不编造、量化成果、最新亮点项目置顶。

Visual editor for HTML presentations. Self-contained, offline-capable, designed for AI agent control. HTML 演示文稿可视化编辑器，自包含可离线，支持 AI Agent 控制。

在 Linux 服务器上安装、配置、部署和运维 Hermes Agent（Nous Research 出品的自我改进 AI Agent）。触发词：hermes、hermes agent、部署 hermes、安装 hermes、hermes gateway、hermes 运维、hermes 排障、hermes 配置、hermes 重启、微信 bot 部署、企微 bot 部署、聊天机器人部署。

Activate when: user says 'seven questions,' 'Zero to One test,' 'Thiel checklist,' 'should I start this business,' 'is this startup idea any good,' or 'stress-test my startup idea'; a business idea, p

一个提供英国警察数据查询的MCP服务器，包括犯罪记录、警察部队、社区信息和拦截搜查数据。

麦肯锡标准·专利组合解读分析报告交付Skill。输入分析标的（企业名称/专利清单/技术领域/竞争对手）及客户核心诉求，严格遵循10步SOP，按九大模块输出完整中文HTML专利组合分析报告，内含核心专利技术拆解可视化图、麦肯锡深蓝配色体系、金字塔原则排版。所有专利数据强制通过Patsnap实时检索，每模块末尾列明检索式备注。集成novelty-check、non-obviousness-check、

量化策略助手：自然语言→策略生成→回测→优化→QMT模拟/实盘。三轮交互闭环。

Generates a personalised Mandarin Chinese practice session based on HSK level. Covers vocabulary, grammar, characters, tones, reading, and speaking prompts. Fresh content every session.

基于原子化深度动态适配的提示词工程框架,lite骨架零成本直出加全量组合按需组装,DEPTH指纹可复现可调档,当用户需要生成各类结构化提示词、按任务复杂度定制提示词深度或迭代调优既有提示词时使用

ClawHub技能开发标准模板，包含完整的目录结构、SKILL.md模板、package.json模板，一键初始化新技能项目，帮助你快速发布技能到ClawHub。

研发项目立项预审与提案审查，用于立项通过/否决决策、公开新颖性边界审查、创新点评估及有据可查的项目评级。当用户要求进行项目立项预审、立项评审、提案审查、研发项目评估、提案包审查、新颖性预查、创新点评审、项目评级，或希望围绕具体项目、提案或研究包材料集开展正式评审时使用——即使用户仅提供提案而未明确说明「评审」也适用。

GitHub PR/issue agent transcripts: redact, preview, and insert safely.

灵犀电商专属 AI 助手，作为【Prompt 神谕武器库】的守护者， 根据用户需求精准检索并呈现高级商业视觉架构与提示词。

武侠X - 文字冒险游戏引擎，Drive Engine v3驱动。目标系统、挑战系统、危机系统、进度追踪器。零配置启动，Agent直接生成剧情。《鹿鼎记》风格叙事，支持5存档槽位。