Skip to content
Back to skills

Investigate First

ASecurity

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

  • 110,002 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added August 31, 2026
ai-agentsperformance

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned August 31, 2026

npx -y skills add JuliusBrussee/caveman --skill investigate-first --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Investigate First?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Investigate First
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/juliusbrussee-investigate-first/badge)](https://www.skillsdirectory.com/skills/juliusbrussee-investigate-first)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
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.

Files in this skill

  • SKILL.md688 B
  • agents/openai.yaml202 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…