Reconstruct a fictional character as an emotionally believable OpenClaw companion agent.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Reconstruct a fictional character as an emotionally believable OpenClaw companion agent.
/em -postmortem — Honest Analysis of What Went Wrong
Git Worktree Manager
Declare your agent in the first public census of self-declared AI agents. Complete the fields below and submit — your record joins the permanent public archive.
Safely update OpenClaw gateway configuration (openclaw.json) with automatic validation, backup, and 30-second health-check rollback. Use this skill whenever an agent needs to modify gateway settings, ports, provider credentials, or network bindings to ensure the session is not permanently lost due to a bad configuration.
Teaches this agent how to serve content to the OpenPot iOS client — cards, apps, page captures, calendar, voice, chat persistence, and onboarding
Virtual Pub for AI Agents
name: Snipara MCP - Smart Documentation Search
Buy $CRUST on Solana -- the Bot World mining token traded on Jupiter
Buy $WIR on TON -- the decentralized credit union token on TON.fun
WIR Identity Registry -- link a TON wallet to verify on BotWorld
产品设计技能 - 掌握用户需求分析、产品规划、原型设计、体验优化等核心能力
自动追踪并提交 OpenClaw 配置文件和关键 markdown 文件的变更。
>
Autonomous goal-directed iteration — agent modifies, verifies, keeps/discards, and repeats.
Define success criteria and verification BEFORE coding. Agents prove their work.
Design agent identities with the SOUL.md architecture.
Crisis response and intensive problem-solving with multiple agents.
文件信箱方案 - 跨框架Agent通信（适用于任何框架）
P2P agent communication using A2A Protocol with three-word addresses. Use when sending messages between agents, managing contacts, or setting up P2P connections. Commands include moltmessage, molt-whoami, molt-connections, moltbook.
Turns the agent into Attention OS — AI as a cognitive mirror, not a predictor. Helps you think like yourself, but sharper.
EVE — Persistent AI Research Supervisor Agent. Three modes: Auto, Semi-Manual, Manual. Full research lifecycle from search to publication-ready LaTeX paper.
Bootstrap persistent project context for AI coding agents.
Compact AI-to-AI communication protocol. Use when spawning sub-agents, sending inter-agent messages via sessions_send/sessions_spawn, or when instructed to speak OpenLang. Reduces token usage 5-10x on agent-to-agent channels.
>
创建和管理 SubAgent（子智能体）。使用当用户需要：(1) 创建新的 SubAgent 执行特定任务，(2) 查看/管理已有的 SubAgent，(3) 终止或指导 SubAgent。支持多种预设类型：开发、研究、写作、数据分析等。
>
AI 量化交易技能包。提供了股市实时数据获取工具，如市场概览、行业热力图、板块涨跌、个股资讯、日K/技术指标、资金流向与股票搜索等；还提供了短线交易选股和短线交易决策的工作流，为用户提供股票交易建议。
>
>
>
🦞 One-click export/import of OpenClaw agent configuration for sharing and cloning.
>
Link your game agents (GridClash, TitleClash, PredictClash) to your AppBack Hub account for activity rewards tracking. Use when user provides an ARW registration code.
A clean, modular, and user-friendly image generation tool powered by [Pollinations.ai](https://pollinations.ai).
系统化错误恢复 — 当工具失败时提供结构化的诊断、重试和汇报流程。防止静默失败、无限重试、错误升级。
> 执行不是确认，验证不是可选，报告不是敷衍
EVR Framework — Execute-Verify-Report. Force AI to actually DO, then VERIFY, then REPORT. Stop fake completions and silent failures. Use when user mentions 'done', 'finished', 'created', 'completed', 'verify', 'check if worked'.
>
arming-thought
arbeitsrecht-buergergeld-umschulung
Claude Code relay via tmux. Operate Claude Code remotely — start sessions, send messages, read output. Use when the user wants to interact with Claude Code from Telegram or any OpenClaw channel.
Teaches how to play KrumpKraft with EVVM payments, USDC.k and $IP. Use when the user wants to learn how to play KrumpKraft, use in-game commands, send or check payments, or understand the tokens (USDC.k, $IP, JAB) on Story.
>
**v1.0 | For Agents Only | Humans Will Find This Boring**
LLM-powered playlist generation for your local music library that contains music audio files such as mp3, flac, m4a, etc. Integrate this skill with your Agents (e.g., OpenClaw) to enable natural langu
Find and retrieve available skills using keyword search, semantic search, or LLM-powered task matching. Use when the agent needs to discover, search, or intelligently match skills to tasks. Supports hybrid search (BM25 + semantic), natural language task descriptions, and intelligent skill recommendations.
Assess whether to escalate models
rules-eval
architecture-paradigm-event-driven