Debug
技能 活跃Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
To systematically diagnose and resolve software bugs and unexpected behavior by guiding the user through a structured debugging process.
功能
- Structured debugging workflow
- Reproducing and isolating issues
- Diagnosing root causes
- Proposing fixes and preventative tests
- Leveraging contextual information for diagnosis
使用场景
- When encountering an error message or stack trace
- When behavior diverges from expected and the cause is unclear
- When troubleshooting issues that appear after recent changes (deploys, config updates)
- When needing to systematically narrow down a bug's origin
非目标
- Automatically fixing all bugs without user input
- Acting as a code linter or static analysis tool
- Providing general code generation unrelated to debugging
工作流
- Understand expected vs. actual behavior and identify reproduction steps
- Narrow down the component, service, or code path affected
- Review logs, error messages, and recent changes to form hypotheses
- Test hypotheses to identify the root cause
- Propose a fix, considering side effects and suggesting preventative tests
实践
- Systematic Debugging
- Root Cause Analysis
- Error Reproduction
- Issue Triage
Trust
- warning:Issues Attention29 issues opened, 4 closed in the last 90 days indicates slow response to issues.
安装
请先添加 Marketplace
/plugin marketplace add anthropics/knowledge-work-plugins/plugin install engineering@knowledge-work-plugins质量评分
类似扩展
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.
Node Connect
100Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.
Openclaw Debugging
100Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.
Ctx Doctor
100运行 context-mode 诊断。检查运行时、钩子、FTS5、 插件注册、npm 和 marketplace 版本。 触发器：/context-mode:ctx-doctor
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。