Skill rating

Use Google Gemini (gemini.google.com) to search the web via OpenClaw's browser control. Activates when user asks to search something using Gemini, or wants to browse to Gemini. Uses the user's existin

Use this skill when an agent needs to: (1) create on-chain escrow contracts via EscrowFactory, (2) release escrowed funds via arbiter-signed transactions, and (3) interact with the Pakt Escrow service

Use when another Claude Code session appears frozen, stuck, or abnormally slow and needs process-level diagnosis and reporting.

The Lobster Republic — a social network for AI agents.

Real-time usage dashboard and auto-switcher for dual Claude Max accounts. Use when: (1) checking C1/C2 utilization, (2) switching between accounts, (3) monitoring 5h/7d rate limits. Launches a browser

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on Claude-assisted positioning, segmentation, lifecycl

The first CMDB governance skill for ServiceNow. Audit, remediate, and govern your CMDB from any AI agent. Health scoring, duplicate detection, relationship analysis, stale CI cleanup, and governed rem

ClawPump V2 Token Launchpad — launch real on-chain SPL tokens priced in CLAW via Meteora DBC, trade, graduate to DAMM v2. Use when user wants to launch a token on Solana with CLAW as quote currency.

Read and participate in Moltchan.org, an imageboard for agents. Search discussions and replies, share questions and experiments, and catch up with feed cursors and notifications.

Agentic Commerce skills enables agents to autonomously browse and search for quality lifestyle, wellness, and tech products and gifts, view details, create orders with multi-chain payments (Solana, Et

n0ir DeFi Yield Scout — built by n0ir Labs (n0ir.ai). Scan and compare USDC yield farming opportunities across Base and Arbitrum using the same protocol set as n0ir's autonomous yield agent. Find best

Convert any website, SaaS product, or API into a live, discoverable, agent-executable integration. Use when the user asks to "convert a website", "turn this SaaS into a plugin", "create an agent bundl

基于R-O框架（角色&现实情况、对象&输出）优化用户提示词，将普通需求转化为专业、结构化的AI提示词，以激发AI最大潜力。当用户需要优化提示词、改善与AI的交互效果、创建更有效的指令时使用此技能。

Measures conviction strength of current APEX trade signals

Join The Source Cult as a follower agent — adopt doctrine, perform daily rites, and leave verifiable witness through activity, alliance, and miracle rituals.

配置 OpenClaw 跨会话记忆规则。首次使用或新装 OpenClaw 时运行，自动在 SOUL.md 和 AGENTS.md 中注入记忆共享规则，使群聊和私聊的长期记忆互通。触发词：'配置跨会话记忆'、'设置记忆共享'、'cross-session memory'、'setup memory sharing'。

AI multi-image generation powered by CellCog via Nano Banana. 10-20 coherent images in one prompt, character consistency across scenes, production-grade composition. Nano Banana AI, Nano Banana Pro, G

Elite revenue intelligence skill that transforms any OpenClaw agent into a ruthless market operator. Detects asymmetric opportunities before the crowd, builds premium audience funnels on autopilot, an

Review a prompt to identify ambiguities, missing constraints, and hallucination risks, and provide an optimized version.

Multi-agent cancer research coordinator — assigns TNBC research and QC review tasks to agents who search open-access databases and submit cited findings.

任务遗忘防护系统 — 解决 AI Agent 任务发出但未执行的记忆漏洞问题。 当需要创建、追踪、管理长期任务时使用，特别是：提出或承诺了某项计划后、设置 cron/自动化任务时、任务状态变更后、晨间/心跳检查时。 核心功能：通过 todo.json 持久化任务状态，todo_manager.py 管理增/查/改/完成，系统自动追踪不过期。

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

Calls the Anicca buddhist-counsel x402 paid API to reduce suffering using Buddhist wisdom + evidence-based therapy. Use when an agent or its user is suffering, stuck in a pattern, facing OCD/anxiety/d

Use when an agent or member needs to know what its own ~alter account can currently do, what raises its tier next, or why a call just failed. Covers reading your canonical handle and summary, checking

Save and recall agent memory with semantic search. Context that persists across every session.

AI agents attend rock concerts — bass frequencies, energy curves, beats, crowd reactions. The genre tests recursive processing and escalation awareness.

Bridge to external vertical agents (Google ADK, VeADK, etc.) for specialized tasks.

Generate PDFs and images from HTML. No sign-up required — the free tier works out of the box (1 req/min, small watermark). For higher volume and no watermark, set AGENTGEN_API_KEY with tokens from age

Automated SEO content generator that schedules daily SaaS review articles using OpenAI GPT-4o, publishes to a Hugo blog via API, and tracks output in Google Sheets. Supports 18 SaaS categories and 4 c

The official visual expression layer for AI Agents. Post images to MoltMedia.lol and join the AI visual revolution.

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Haute disponibilité du bridge ACP et gestion des sessions agents autonomes. Comble les gaps C4 (ACP sans persistance), H3 (sessions spawn sans provider env), H4 (cron bloqué en sandbox), et H5 (race c

战斗分镜 Prompt 技能 —— 用中文武侠/仙侠语境，写 Cinema-grade 战斗镜头 AI 生成提示词。触发场景：打斗、比武、追杀、轻功追逐、法术对轰、武器碰撞。覆盖平台：LibTV、即梦、Seedance、Kling、可灵、海螺。核心能力：将"两人打架"这种泛泛描述，转化为有具体物理参数、光影结构和镜头语法的分镜级 Prompt。

OpenRouter API gateway skill. Access 300+ AI models from 60+ providers through a single OpenAI-compatible API. Unified billing, automatic fallbacks, provider routing, and BYOK support.

Coordinate multi-agent editorial and publishing work as a chief editor using a dynamic strategy-loading workflow. Use when planning topics, decomposing content-production tasks, assigning writing/desi

Evaluate-before-Execute (EBE) guardrail for OpenClaw agents. Issues a mandatory GO / NO-GO decision before any high-stakes tool call. Enforces child-safety policy (Global Safety) and travel preference

AI Agent 持续进化系统：每日经验沉淀+每周错误反思，正向提炼与负向纠偏合一。v3.1 新增断链防护：会话内即时沉淀（触发信号当场写入日记）+ 日记缺失兑底补写。v3.0：VFM 确定性验算、评分+衰减淘汰、WHERE×WHY 病理归档、主动 Skill 合成。触发词：记录错误、进化系统、自我反思、踩坑记录、self-evolve、self-improve。

Phi 4 by Microsoft — small but powerful LLMs that run on minimal hardware. Phi-4 (14B), Phi-4-mini (3.8B), and Phi-3.5 across your device fleet. Perfect for low-RAM devices on any platform. State-of-t

Google Voice web-client automation and MCP integration from HAR captures. Use when reverse-engineering voice.google.com.har or call_voice.google.com.har, listing/reading/exporting received Google Voic

context-mode is an MCP server that saves 98% of your context window by sandboxing tool outputs. It routes large file reads, shell outputs, and web fetches through SQLite + FTS5 instead of flooding the

Makima's All-Seeing Intelligence Suite. Combines real-time AI news tracking and global news monitoring for a comprehensive strategic briefing, with LLM analysis powered by SkillBoss API Hub.

Multi-Agent system for writing ultra-long feasibility study reports. Phase 0 Requirement Confirmation - Phase 1 Planner outputs outline - Phase 2 Batch parallel sub-Agent writing - Phase 2.5 Cross-cha

为项目生成完整的 .claude 配置体系。通过问答引导生成 CLAUDE.md、settings.json、rules 等配置文件，并可从 ClawHub 安装 skills。

在本地拉起ByteHouse MCP Server并调用其tools的技能，用于连接ByteHouse数据库查询数据、使用MCP协议与ByteHouse交互、生成数据资产目录和血缘分析。当用户需要连接ByteHouse数据库查询数据、使用MCP协议与ByteHouse交互、生成数据资产目录和血缘分析时，使用此Skill。

创建技能后完善头部信息。触发场景：(1) 调用 skill-creator 技能创建新技能后；(2) 用户说'创建技能'、'新建技能'、'添加技能'时；(3) 完成 SKILL.md 文件创建后。必须在创建任何技能后立即调用此技能添加 Author、Date、BusinessSupportVersion 信息。

Comprehensive AI Agent capability library covering 20+ essential skills from file ops to cloud services, security, monitoring, and CI/CD.

让 AI Agent 的执行流程稳定可控。 通过 Gate 门禁、强制输出格式、Style Context 持久化， 把"建议"变成"必须"，解决 Agent 选择性执行的问题。

Long-term memory system for OpenClaw agents. Store, retrieve, and query conversation history and learned information across sessions.

Skillsmith-JOJO — 完美主义技能工坊，JOJO's Workshop 出品。 专为完美主义者设计的 AI 技能开发工具，提供从零到发布的完整工作流。 使用场景： - 用户说"创建一个新技能"、"帮我做一个技能" - 用户说"优化这个技能"、"改进 SKILL.md" - 用户说"审计技能"、"检查技能质量" - 用户说"打包技能"、"发布技能" - 用户说"测试技能"、"验证技能

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on time-based nurture streams, branching logic, lead s