# Fusion Perf

> Compare performance optimization options and choose the most effective; use when tuning or speeding up a system.

- Skill: `majiayu000/fusion-perf` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add majiayu000/fusion-perf`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/fusion-perf/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: majiayu000 (https://skillmd.com/u/majiayu000)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/majiayu000/fusion-perf

---


# Fusion Performance

## Overview

Use an F-thread: three workers implement different optimizations in separate worktrees. The queen compares results.

## Inputs

- Performance problem and metrics

## Workflow

1. Verify `git` and `mprocs`.
2. Create session variables and worktrees.
3. Write `tasks.json`, worker prompts, and queen prompt.
4. Launch mprocs.

## Worktree Commands

```bash
git worktree add "{WORKTREE_ROOT}/impl-a" -b fusion/{SESSION_ID}/impl-a
git worktree add "{WORKTREE_ROOT}/impl-b" -b fusion/{SESSION_ID}/impl-b
git worktree add "{WORKTREE_ROOT}/impl-c" -b fusion/{SESSION_ID}/impl-c
```

## Worker Prompt Outline

- Worker A: algorithmic improvements
- Worker B: caching or batching
- Worker C: concurrency or IO tuning

## Queen Prompt Outline

- Compare benchmarks, complexity, and regression risk

## mprocs Launch

```bash
mprocs --config .hive/mprocs.yaml
```

## Output

- Selected optimization strategy with benchmarks