investigate-first

juliusbrussee/caveman/investigate-first

该技能用于在修改产品代码前诊断模糊故障。它强调将观察到的症状与推断的原因分开，追踪输入、状态转换、所有权边界和失败输出，并根据证据和低成本证伪价值对假设进行排序。在找到一个可信机制解释证据之前，不要编辑代码；当证据足以确定原因或确切阻塞点时，停止探索。最终报告原因和证据，除非任务授权实施，否则不进行修复。

安装量 · 1,236查看来源

Installation

npx skills add https://github.com/juliusbrussee/caveman --skill investigate-first

技能文件

SKILL.md

最近同步 · 2026年10月22日

agents/openai.yaml›

interface:
  display_name: "Investigate First"
  short_description: "Find credible cause before editing code"
  default_prompt: "Use $investigate-first to diagnose this failure before proposing edits."

SKILL.md›

---
name: investigate-first
description: Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
---

# Investigate first

Gather evidence before changing product code.

- Separate observed symptom from inferred cause.
- Trace inputs, state transitions, ownership boundaries, and failure output.
- Rank hypotheses by evidence and cheap falsification value.
- Do not edit until one credible mechanism explains evidence.
- Stop exploration when evidence is sufficient to name cause or exact blocker.

Report cause and proof. Make no fix unless task authorizes implementation.