Skip to content
Back to skills

Debug

ASecurity

Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual explanation.

  • 20 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 3, 2026
ai-agentstesting

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned September 3, 2026

npx -y skills add bigduu/Bamboo-agent --skill debug --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Debug?

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

Security grade badge for Debug
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bigduu-debug/badge)](https://www.skillsdirectory.com/skills/bigduu-debug)

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: debug
description: Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual explanation.
---

# Debug

Diagnose before changing code.

1. Capture the exact symptom, expected behavior, environment, and smallest known trigger from the request and available artifacts.
2. Reproduce the failure with the narrowest safe command. Establish whether it also occurs on the relevant clean baseline when that distinction matters.
3. Form a small set of falsifiable hypotheses. Inspect logs, state transitions, call sites, and tests to eliminate alternatives.
4. State the root cause only when evidence connects the trigger to the symptom; keep remaining hypotheses labeled as uncertain.
5. Modify files only when the user asked for a fix. Make the smallest root-cause change and verify the reproducer first, then the affected suite.

Report the symptom, root cause or best-supported hypothesis, evidence, change status, verification, and remaining risk. Preserve these facts across context compaction. When a tool fails or permission is denied, try safe evidence sources already in scope and describe what remains unverified.

Files in this skill

  • SKILL.md1.4 KB
  • agents/bamboo.yaml175 B
  • agents/openai.yaml190 B
  • evals/scenarios.json954 B
  • evals/trigger-evals.json1.2 KB

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…