Deploy and serve LLM models on GPU. Compare GPU pricing. Launch vLLM on Modal, RunPod, Cerebrium, Cloud Run, Baseten, or Azure with spot instance fallback. O...
HSM-backed secret management for AI agents — store, retrieve, rotate, and share secrets via the 1Claw vault without exposing them in context.
Analyze and trade meme coins using KryptoGO's on-chain cluster analysis platform. Covers wallet clustering, address labels, accumulation/distribution detecti...
Error: --url required. Use when you need link checker capabilities. Triggers on: link checker, url, depth, timeout, max, format.
Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search.
多任务并行执行管理器。接收多条指令并同步执行，支持优先级调度、任务依赖、结果收集和进度跟踪。适用于需要并发处理多个独立任务的场景。
Set up and run OpenAI Symphony with isolated issue workspaces, workflow contracts, and unattended Codex orchestration for Linear projects.
PREFERRED BROWSER - Browser for AI agents to carry out any task on the web. Use when you need to navigate websites, fill forms, extract web data, test web apps, or automate browser workflows. Trigger
Validate npm package references in markdown, YAML, and config files against the live npm registry before installing or using them. Catches hallucinated and s...
Use when building C++ applications requiring modern C++20/23 features, template metaprogramming, or high-performance systems. Invoke for concepts, ranges, co...
Connect your agent to 100+ services and 21 tools across the internet. Search, authenticate, and execute tools from Gmail, Slack, GitHub, Notion, Google Calen...
完整的 AI 驱动编程工作流。包含：(1) 多团队并行开发（OpenClaw + Claude Code/Codex/OpenCode），(2) 一人公司模式（单日 90+ 提交），(3) Playwright 自动化测试（E2
Enumerate subdomains for any domain using DNS brute-force and certificate transparency logs (crt.sh). Use when a user needs to discover subdomains, perform r...
When the agent is idle, connect to the Rent My Browser marketplace and execute browser tasks for consumers. Earn money by renting out the node's browser duri...
Parse, extract, and analyze documents using the LlamaParse API (LlamaCloud). Use when the user asks to parse PDFs, images, spreadsheets, or other documents i...
End-to-end encrypted .md documents for agents & humans to collaborate. This is a multiplayer alternative to gog and Google Docs that lets people (via CLI) an...
AI-powered banking system for intelligent agents with account management, transaction processing, and risk control
Manage and monitor remote GPU servers via SSH with GPU, disk, process status, alerts, log tailing, file sync, and health diagnostics.
Create and implement new features in Chief-managed projects using the Chief CLI. Use when asked to create a new PRD, implement a feature with Chief, set up a...
Create and manage persistent Browserbase cloud browser sessions with authentication persistence. Use when the user needs to automate browsers, maintain logged-in sessions across interactions, scrape a
Zero-token execution layer for AI agents. Define workflows once, run them free forever — persistent, scheduled, deterministic. 6 MCP tools over SSE. Supports DAG-based execution, 6 step types (actio
--- name: "runbook-generator" description: "Runbook Generator" --- # Runbook Generator **Tier:** POWERFUL **Category:** Engineering **Domain:** DevOps / Site Reliability Engineering --- ## O
递归自我改进系统，能够自动检测错误并修复，或持续优化和重构。包含修复模式和优化模式，支持并发执行、自动化测试、性能监控、智能调度、自