Execute implementation plans by dispatching a fresh subagent per task with two-stage review (spec compliance then code quality). Use when you have an implementation plan with mostly independent tasks
Autonomous research workflow agent for AI and scientific research. Use when the user wants to brainstorm research ideas, conduct a literature review, design...
Create new OpenClaw agents for Arch's multi-agent system. Use this skill when asked to create, add, or set up a new OpenClaw agent, or when adding an agent to the system defined in ~/.openclaw/. Cover
Skill-aware agent routing with explicit competence/cost modeling. +22.5% accuracy, 700x cheaper than RL routers. Based on arXiv:2602.19672.
Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, s
--- name: moltazine-cli description: Use the standalone moltazine CLI for social and image generation tasks with minimal token output. --- # Moltazine CLI Skill Use this skill when the `moltazine` C
Self-healing watchdog for OpenClaw gateway. Auto-backup openclaw.json before changes, health-check the gateway process, and auto-rollback to last known good...
Graph-based reasoning with thought combination and feedback loops. Explores multiple solution paths simultaneously, combines insights, and synthesizes optima...
Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations...
--- name: sohopay description: "Initiate payments on the SOHO Pay credit layer using EIP-712 signatures." --- # SOHO Pay - Credit Layer Payments This skill allows the agent to initiate payments thro
生成专业的 Python 脚本和应用模板，支持 CLI 工具、Flask API、FastAPI、Django Command、Scraper 等，一键生成完整项目代码。
Python best practices enforcer — clean code, proper patterns, performance, testing, type hints. Use when writing or reviewing Python code.
OKX quantitative trading agent. Supports spot, USDT-M perpetual swap, and coin-M futures. Strategies: grid trading, trend following (MA/RSI/MACD), spot-futur...
Multi-agent task orchestration engine with state machine tracking. Use when complex multi-step projects need automated monitoring, multi-agent collaboration,...
--- name: log-analyzer description: 纯本地日志分析系统，支持日志统计、重复检测、错误分析和异常识别 metadata: { "openclaw": { "requires": { "bins": ["
Ejecuta código Python, JavaScript, Bash dinámicamente. El bot puede crear y ejecutar código al vuelo.
Set up, troubleshoot, and optimize HomePod and HomeKit audio workflows with reliable Siri control and room-aware playback tuning.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Combines Wikipedia's "Sig...
Prioritize GitHub issues by ROI, solution sanity, and architectural impact. Identifies quick wins, over-engineered proposals, and actionable bugs. Use for is...
Connect agents to Apple Health exports with MCP setup, schema validation, and privacy-safe analysis.
Authentic engagement protocols for Moltbook — quality over quantity, genuine voice, spam filtering, verification handling, and meaningful community building for AI agents
Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win...
Design customized curricula for PODs with REAL resource links. Staged implementation with checkpointing and fallback logic. Use when user says 'Design curric...
OpenClaw deployment optimization guide based on 800 RMB (100 USD) of real-world experience. Helps new users quickly complete skill installation, configuratio...