# run-parallel-agents-feature-debug

run-parallel-agents-feature-debug is a Claude Code skill that concurrently diagnoses and fixes three or more independent failures in isolated worktrees after checking for a shared cause.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 148 installs · ★ 5 repo stars
- Author: ulpi-io
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ulpi-io/skills/tree/HEAD/run-parallel-agents-feature-debug/SKILL.md
- Updated: 2026-08-31
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/run-parallel-agents-feature-debug

## What it does

This skill organizes concurrent bug investigations on the Claude Code agent runtime. Prior to spinning up workers, it inspects traces to confirm errors do not stem from a shared database migration or dependency bump. A minimum of three independent issues is required.

Because fresh subagents inherit no conversational history, the skill drafts comprehensive briefs for each worker. Each brief includes stack traces and failing test names. All workers launch in a single turn using `Agent` tool calls configured with `run_in_background: true` and `isolation: "worktree"`.

The runner avoids polling transcripts, waiting for completion signals instead. Without Git worktree support, parallel code changes will inevitably collide.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add ulpi-io/skills --skill run-parallel-agents-feature-debug -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/run-parallel-agents-feature-debug/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/run-parallel-agents-feature-debug/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add ulpi-io/skills --skill run-parallel-agents-feature-debug -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/run-parallel-agents-feature-debug/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add ulpi-io/skills --skill run-parallel-agents-feature-debug -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/run-parallel-agents-feature-debug/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install ulpi-io/skills run-parallel-agents-feature-debug
```

2. **Manually: put the files in place**
- File: `.github/skills/run-parallel-agents-feature-debug/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add ulpi-io/skills --skill run-parallel-agents-feature-debug -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/ulpi-io/skills --path run-parallel-agents-feature-debug
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/run-parallel-agents-feature-debug/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add ulpi-io/skills --skill run-parallel-agents-feature-debug -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ulpi-io/skills/tree/HEAD/run-parallel-agents-feature-debug/SKILL.md

## When to use it
- debug three or more decoupled test suite failures concurrently
- rule out common root causes across build and runtime traces
- dispatch isolated bug investigations to specialized subagents
- isolate concurrent code patches using Git worktrees

## Example prompts
- Debug these three failing test suites in parallel
- Split these four independent bugs across background agents and fix them
- Investigate and patch the unrelated errors in auth and reporting

## Similar
- [build-run-debug](https://affpapa.org/en/nevibecode/skills/build-run-debug.md) — skill · 60 installs
- [hub-run](https://affpapa.org/en/nevibecode/skills/hub-run.md) — skill · ★ 30251 repo stars
- [orchestrate](https://affpapa.org/en/nevibecode/skills/hyperb1iss-orchestrate.md) — skill · 669 installs
- [implement](https://affpapa.org/en/nevibecode/skills/orchestkit-implement.md) — skill · 206 installs
- [distributed-task-execution](https://affpapa.org/en/nevibecode/skills/distributed-task-execution.md) — skill · 134 installs
- [fleet](https://affpapa.org/en/nevibecode/agents/fleet.md) — subagent · ★ 937 repo stars

From the same set: [ulpi-io/skills](https://affpapa.org/en/nevibecode/by/ulpi-io/skills.md) — 49 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
