---
name: Gstack Investigate
slug: gstack-investigate
category: Quality
description: Gstack Investigate guides systematic debugging for bugs, crashes, regressions, flaky behavior, and provider issues. It emphasizes reproduction, evidence, and the smallest fix before verification.
github: "https://github.com/LING71671/Open-ClaudeCode/tree/main/plugins/gstack-workflows/skills/gstack-investigate"
language: TypeScript
stars: 945
forks: 1224
install: "npx degit https://github.com/LING71671/Open-ClaudeCode/tree/main/plugins/gstack-workflows/skills/gstack-investigate ~/.claude/skills/gstack-investigate"
installs_to: ~/.claude/skills/gstack-investigate
source_path: plugins/gstack-workflows/skills/gstack-investigate/SKILL.md
collection_size: 15
category_size: 1354
collection_url: "https://dirskills.com/collections/LING71671/Open-ClaudeCode"
added: 2026-08-21T05:15:31.654Z
last_synced: 2026-08-21T05:15:31.654Z
canonical_url: "https://dirskills.com/skills/gstack-investigate"
---

# Gstack Investigate

Gstack Investigate guides systematic debugging for bugs, crashes, regressions, flaky behavior, and provider issues. It emphasizes reproduction, evidence, and the smallest fix before verification.

**Install:**

```bash
npx degit https://github.com/LING71671/Open-ClaudeCode/tree/main/plugins/gstack-workflows/skills/gstack-investigate ~/.claude/skills/gstack-investigate
```

## README

# gstack-investigate

Use this skill to diagnose before fixing.

## Workflow

1. State the observed symptom and the expected behavior.
2. Reproduce the issue with the smallest command, UI flow, fixture, or log slice available.
3. Trace the relevant path through the code before proposing a fix.
4. Form at least three plausible causes.
5. Test the causes with targeted checks, logs, assertions, or isolated commands.
6. Pick the cause with the strongest evidence.
7. Apply the smallest fix that addresses that cause.
8. Re-run the original reproduction and one nearby regression check.

## Rules

- Do not fix before reproduction or strong evidence.
- If one attempted fix fails, record why and try a different strategy.
- Prefer direct runtime evidence: command output, logs, API responses, persisted state, or failing tests.
- Keep unrelated refactors out of the fix.

## Output

Report:

- Symptom
- Root cause
- Fix
- Verification command or manual check
- Residual risk