investigate-first

juliusbrussee/caveman/investigate-first

This skill is used to diagnose ambiguous failures before modifying product code. It emphasizes separating observed symptoms from inferred causes, tracing inputs, state transitions, ownership boundaries, and failure output, and ranking hypotheses by evidence and cheap falsification value. Do not edit until one credible mechanism explains the evidence; stop exploration when evidence is sufficient to name the cause or exact blocker. Report the cause and proof, and make no fix unless the task authorizes implementation.

Installations · 1 236Voir la source

Installation

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

Fichiers du skill

SKILL.md

Dernière synchronisation · 22 oct. 2026

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.