# Debug Software with Structured Evidence

Intermittent bugs are difficult to isolate when evidence is incomplete. This skill structures hypotheses, captures diagnostic evidence, applies focused fixes, and verifies regressions.

## Install

```bash
npx skillstore add cubha/debugger
```

## Metadata

- Status: approved
- Slug: cubha-debugger
- Skillstore revision: r2
- Version status: missing
- Tree hash: 780446cbbb1884138f5cd095dd61289f46f3d986bf07bc1a09c0eaae058e1408
- Author: cubha
- GitHub username: cubha
- License: MIT
- Repository: https://github.com/cubha/claude-workflow-plugins/tree/3172e1a00f7090579f36af20c046828489983c23/plugins/debugger/skills/debugger
- Ref: c43861a65bb95efcae259cd161c9d6f4dc7eec6f
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 69
- Public page: https://skillstore.pages.dev/skills/cubha-debugger
- Manifest: https://skillstore.pages.dev/api/skills/cubha-debugger/manifest

## Capabilities

- Analyzes error messages, reproduction conditions, and related source files.
- Ranks up to five evidence-based root cause hypotheses.
- Adds marked temporary logs for JavaScript, TypeScript, Python, Java, and Kotlin.
- Uses Playwright MCP to collect browser console, network, screenshot, and DOM evidence.
- Applies scoped fixes and checks callers, contracts, and shared state.
- Runs available regression checks and removes inserted diagnostic logs.

## Use Cases

- Trace an Application Error: Analyze a stack trace, add focused diagnostics, identify the failing path, and verify the fix.
- Reproduce a Browser Defect: Use Playwright evidence to reproduce a web issue and compare behavior before and after a fix.
- Repair a Cross-Module Regression: Check callers, data contracts, and shared state before applying a durable correction.

## Prompt Templates

### Diagnose an Error

```
Diagnose this error: [paste error]. Identify likely causes, inspect relevant files, and tell me what evidence you need before changing code.
```

### Instrument an Intermittent Failure

```
Debug this intermittent failure in [feature]. Add temporary marked logs at the strongest hypotheses, then wait for my results before fixing anything.
```

### Debug a Browser Scenario

```
Use --pw on [URL] to reproduce [scenario]. Capture console, network, screenshot, and DOM evidence, then fix and rerun the scenario.
```

### Investigate a Boundary Regression

```
Investigate [bug] across [modules]. Check caller, API, data, and shared-state boundaries before applying a durable fix and running all available regression gates.
```

## Limitations

- Default mode requires the user to run the application and return diagnostic output.
- Browser mode requires a connected Playwright MCP server, a web project, a URL, and a reproduction scenario.
- Temporary log formats are defined only for JavaScript, TypeScript, Python, Java, and Kotlin.
- The workflow stops after bounded retries when available evidence cannot identify the cause.

## Best Practices

- Provide the exact error, reproduction steps, environment, and recent changes.
- Review proposed diagnostic locations before running the affected application.
- Inspect every final diff and confirm that temporary logs were removed.

## Anti Patterns

- Do not use this workflow for feature development or general code review.
- Do not run project scripts from an untrusted repository without inspection and confirmation.
- Do not include passwords, tokens, personal data, or production records in diagnostic output.

## Security Audit

- Audited at: 2026-07-23T12:57:21.919\+00:00
- Summary: Two of 38 static findings are confirmed because the workflow runs project-controlled verification scripts that may execute arbitrary repository code. The remaining static findings are Markdown, safe examples, or explicit prohibitions. A separate medium-risk finding covers direct source edits and marker-based deletion.

## Stats

- Views: 0
- Downloads: 4
- Favorites: 1
- Popularity score: 0