‹ 首页

dev-trace

@evolution-foundation · 收录于 5 天前 · 上游提交 2 个月前

Evidence-driven causal tracing with competing hypotheses. Use when an observation has multiple plausible explanations and you need to systematically rank them with evidence FOR and AGAINST each. Pairs with @trail-tracer.

场景故障排查根因分析

适合你，如果面对复杂问题需要结构化推理和证据排序

/ 下载安装
https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/dev-trace ↗
/ 通过 npx 安装 校验哈希
npx oh-my-skill add evolution-foundation/evo-nexus/dev-trace
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- evolution-foundation/evo-nexus/dev-trace
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify evolution-foundation/evo-nexus/dev-trace
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
509GitHub stars
~388上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 7f5dd76 · 表述以原文为准
它做什么

装上后，Claude会系统性地列出多个可能原因，为每个收集支持和反对的证据，按证据强度排序，最终给出最可能的解释及下一步验证实验。

什么时候触发

当面对一个观察结果有多个合理解释，且不想仓促下结论时触发，例如间歇性bug、区域异常或性能问题。

装好后可以这样说
Claude会启动多假设因果追踪。
Claude会收集证据并排序。
Claude会生成假设并推荐下一步。
技能原文 SKILL.md作者撰写 · Apache-2.0 · 7f5dd76

Dev Trace

Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.

Causal investigation with multi-hypothesis discipline. Generate at least 2 explanations, collect evidence FOR and AGAINST, rank by strength, end with a discriminating probe.

Use When
  • Observation has multiple plausible causes
  • "Why did this happen?" — and you don't want to jump to the first answer
  • Multi-causal problem (intermittent bugs, regional anomalies, performance puzzles)
  • Need to preserve uncertainty rather than collapse to one answer prematurely
Do Not Use When
  • Cause is obvious → just fix it via @hawk-debugger
  • Single-cause bug with clear stack trace → @hawk-debugger
  • Just needs codebase search → @scout-explorer
Workflow

Delegate to @trail-tracer:

  1. OBSERVE — restate the observation precisely, no interpretation
  2. FRAME — define the exact "why" question
  3. HYPOTHESIZE — generate 2+ competing explanations
  4. GATHER EVIDENCE — for each, collect evidence FOR and AGAINST in parallel
  5. APPLY LENSES — systems / premortem / science
  6. REBUT — strongest alternative challenges the leader
  7. RANK — down-rank contradicted, weak-assumption, failed-prediction explanations
  8. SYNTHESIZE — best explanation, explicitly provisional if needed
  9. PROBE — name the critical unknown and the discriminating next experiment
Output

Saved to workspace/development/debug/[C]trace-{topic}-{date}.md using the dev-trace-report.md template.

Pairs With
  • @trail-tracer (the executor)
  • @hawk-debugger (when trace converges to a clear bug)
  • @apex-architect (when trace reveals architectural issues)
按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…