Selects the most cost-effective capable model for tasks, handles rate limit failures gracefully, and supports tier overrides and health checks.
Claw Compactor v6.0 — 50%+ savings through rule-based compression, dictionary encoding, session observation compression, and progressive context loading.
Adversarial plan review using two different AI models. Supports static mode (fixed roles) and alternating mode (models swap writer/reviewer each round, fully...
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Build a more reliable OpenClaw agent with battle-tested architecture patterns. Covers WAL protocol, working buffer, memory anti-poisoning, layered memory com...
Manage GitHub issues by listing, filtering, spawning fix agents, creating PRs, and tracking review comments using the authenticated gh CLI.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib...
Manage finances via the Organizze API — bank accounts, credit cards, invoices, transactions, transfers, categories, and budgets. THIS SKILL IS NON-OFICIAL AN...
Gate Exchange affiliate program data query and management skill. Use this skill when users ask about their affiliate/partner commission, trading volume, net...
调用由查理·芒格、霍华德·马克斯、段永平、斯坦利·德鲁肯米勒、詹姆斯·西蒙斯组成的投资大师委员会，对任意标的进行多维度独立分析并输出委员
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Logs and organizes learnings, errors, and feature requests for continuous improvement, integrating with OpenClaw workspace for knowledge management.