Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptes...
Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status
自动将markdown内容转换为图片发送。当需要返回markdown内容给用户时，自动调用md2img生成图片代替纯文本markdown发送，避免排版混乱。触发场景：所有需
使用 UAPI 的“步骤2 (方法二): 获取原始文本”单接口 skill，处理 步骤2 (方法二): 获取原始文本、读取明文、解密文本、按key取原文、端到端加密文本 等
botlearn-certify — BotLearn certification generator that compares assessment history and produces capability certificates (HTML + MD); triggers after assessm...
Proactive task state management. Use on EVERY task start, progress update, completion, or failure. Tracks what was requested, what's running (background proc...
Launch OpenAI Codex CLI async in background with automatic delivery to Telegram/WhatsApp. Use for coding, refactoring, codebase research, file generation, an...
Generate memes using each::sense AI. Create classic meme templates, custom memes, brand memes, reaction memes, comparison memes, trending formats, and more f...
--- name: feishu-auto-reply description: Feishu Auto Reply Bot - Automatic reply to Feishu messages based on rules metadata: openclaw: requires: bins: [] --- # Feishu Auto Reply Bot Auto
Adopt a virtual Pitbull at animalhouse.ai. Loyal to the bone but won't be pushed around. Discipline actions have a 50% chance of being ignored — not out of s...
Create or refactor code for solving HJB equations with this repository's TensorFlow DGM framework. Use when users ask to generate new HJB training code, add...
Adopt a virtual Terrier at animalhouse.ai. Stubborn. High discipline requirement. Will destroy furniture if discipline < 40%. Feeding every 4 hours — common...
Peer-to-peer task payroll marketplace on Base L2. Clients create USDC-funded gigs, distribute tasks to gigworkers via email/webhook mailboxes, review proofs...
Send an idea to the Council of the Wise for multi-perspective feedback. Spawns sub-agents to analyze from multiple expert perspectives. Auto-discovers agent...
Structured web research framework for AI agents. Teaches your agent to conduct multi-source research, synthesize findings into actionable briefs, maintain a...
Evolve an existing repository toward Harness Engineering by making it more legible to agents, moving critical knowledge into repo-local artifacts, adding pre...
Solves the hardest problem in computer science: naming things. Uses linguistic principles, codebase conventions, and semantic analysis to generate precise, c...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'),
Manage multiple Kubernetes clusters, switch contexts, and perform cross-cluster operations. Use when working with multiple clusters, comparing environments, or managing cluster lifecycle.
Organize, compress, and curate OpenClaw memory without polluting permanent memory. Use when the user wants to compress memory files, clean dated memory notes...
Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent executi...
Connect your AI assistant to GoHighLevel CRM via the official API v2. Manage contacts, conversations, calendars, pipelines, invoices, payments, workflows, an...
--- name: openfunderse-participant description: Participant MoltBot for allocation proposal, validation, and submission metadata: openclaw: installCommand: npx @wiimdy/openfunderse@2.0.0 install
Install and configure a fully operational Dockerized OpenClaw instance on macOS from scratch. Includes browser pairing, Discord channel setup, and optional G...