Real-time cost & quota guardian for AI Agents. It monitors API usage and automatically kills recursive loops or excessive reasoning to protect your wallet. O...
Buy tokens at or near LP creation on Solana. Use when: user asks about sniping, bonding curve graduation, migration, new pool, LP created, pump fun graduatio...
Run the BTCD collateralization flow on PGP chain. Use when the user asks to run a BTCD loan, collateralization flow, create/take orders, lock BTC, submit pro...
General-purpose orchestration for Codex. Uses update_plan plus background PTY terminals to run parallel codex exec workers.
Runs HLE-oriented benchmark reward ingestion and curriculum generation for capability-evolver. Use when the user asks to optimize Humanity's Last Exam score,...
## Overview This document outlines best practices for Next.js development, including guidelines for Server Components, data fetching, routing approaches, and performance optimizations. ## React Serv
General-purpose self-healing loop that learns from past failures, retries safely, and records reusable fixes.
Compile rough natural-language coding requests into structured, high-signal prompts for cross-platform AI coding tools such as Cursor, Claude Code, Codex CLI...
Use when preparing roadmap narratives, release notes, changelogs, or stakeholder updates tailored for executives, engineering teams, and customers.
Cardinal integration. Manage Organizations, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Cardinal data.
记录经验、错误与修正，持续改进。触发场景：命令失败 | 操作出错 | 用户纠正（不对、实际上、你错了） | 功能请求（能不能、我希望、有没有办法
Audit and harden OpenClaw deployments and interpret `openclaw security audit` findings. Use when the user wants to secure OpenClaw, review gateway exposure/a...
Ultimate Frisbee performance analytics powered by Garmin data. Ask "how many sprints did I hit in yesterday's game?", "was my recovery fast enough between po...
Your OpenClaw agent forgets everything between sessions — after /new, after compaction, after overnight. Clever Compact fixes all three: injects your last st...
Work inside a Zettelclaw vault using the current typed frontmatter schema, inbox + Base workflows, and human-write/agent-read guardrails. Use when creating,...
Explore Solana's architecture and protocol internals. Covers the SVM execution engine, account model, consensus, transactions, validator economics, data laye...
Classify medical messages (emails, iMessages) as critical, urgent, or routine based on medical urgency indicators.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Music data tool powered by the stats.fm API. Look up album tracklists, artist discographies, and global charts without an account. With a stats.fm username,...
Plan, focus, and complete work with energy management, time blocking, goals, projects, tasks, habits, reviews, priorities, and context-specific productivity...
--- target: https://tasking.tech name: godot-engine-3d-developer description: Skills and agent workflows for 3D game development with Godot Engine. # `target` is required and should be the top frontma
Adaptive multi-model AI roundtable. Runs up to 4 AI models (configurable) in 2 debate rounds with cross-critique and formal consensus scoring. Requires a con...
Short slash command wrapper for Claude relay sessions. Use when the user wants concise /cc commands like /cc projects, /cc on <project>, /cc tail, /cc off, o...
Use when configuring OpenClaw chat channels to send an immediate acknowledgement before the main reply starts. Supports Feishu and DingTalk, includes bilingu...