Openclaw Debugging
技能 已验证 活跃Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.
Debug OpenClaw behavior by choosing the right logs, probes, and proof paths before making code changes, ensuring efficient troubleshooting.
功能
- Debug OpenClaw model transport and payloads
- Troubleshoot provider interactions and streaming behavior
- Diagnose code-mode execution and tool catalog issues
- Utilize specific environment flags for targeted debugging
- Follow a structured loop for identifying and resolving bugs
使用场景
- When OpenClaw behavior differs between local tests and live environments.
- When investigating issues with tool construction or provider responses.
- When trying to understand code-mode execution and tool activation.
非目标
- Making code changes directly.
- Guessing at the root cause of a problem.
- Debugging general system issues unrelated to OpenClaw.
安装
npx skills add steipete/clawdis通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Node Connect
100Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.
Using Git Worktrees
100在开始需要与当前工作区隔离的功能性工作,或在执行实现计划之前使用 - 通过原生工具或 git worktree 回退确保存在隔离的工作区。
Systematic Debugging
100Systematic debugging methodology emphasizing root cause analysis over quick fixes
Troubleshooting
100使用 Chrome DevTools MCP 和文档来排查连接和目标问题。当 list_pages、new_page 或 navigate_page 失败,或服务器初始化失败时,触发此技能。
Root Cause Tracing
99Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Query Agent Events
99Bug-investigation tool for the Netdata agent-events ingestion namespace -- triage crashes, panics, fatals across the fleet by downloading events of interest and clustering locally. Covers the three transports (Cloud API and direct agent API are primary; ssh is operator-only), the verified AE_* field map and enum meanings, the dedup model (23h client-side per agent and event signature), the after-the-fact event timing (POST only on agent restart), and the Netdata systemd-journal plugin multi-value filter syntax (FIELD in A, B, C) AND ... Use when investigating crashes / panics / fatals; when grepping for events touching a specific function or file or version; when looking for regressions across versions; when an agent is reported crashing in a way you want to triage. Ships scripts get-events.sh and analyze-events.sh that fetch events with index-friendly filters and compute group-by stats. Defaults to last 24 hours and to the latest stable plus latest 2-3 nightlies.