Prevent 429 retry loops and wasted tokens. Use before expensive API calls or after hitting rate limits. Enforces preflight checks, backoff, and context shrinking.
This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.
Install skill "rate-limit-guard" with this command: npx skills add rate-limit-guard
Check: provider/model, recent failures, concurrency, context size.
Next action: proceed / recovery mode / pause.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Automatically detects, assesses, and safely mitigates incidents in OpenClaw production agents, providing detailed reports and verified recovery.
Workflow Checkpoint System - Save and recover from any point in multi-step AI workflows. Never lose progress mid-task.
Self-Improvement Engine - AI Agent that learns from mistakes and continuously improves. No more repeating the same errors.
Agent 执行可靠性体系的导航入口。当用户询问 agent 为什么停了、怎么防 agent 提前退出、execution harness 是什么、40 个 pattern 有哪些、6 轴架构、hook 怎么配时匹配。不执行具体操作——各子 skill 分别处理。