# Review Harness

> Review an existing LLM harness for correctness and gameplay-impacting bugs (prompt accuracy, parser robustness, replay-archive scanning, cross-harness sweeps)

- Skill: `kaggle/review-harness-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add kaggle/review-harness-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kaggle/review-harness-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: kaggle (https://skillmd.com/u/kaggle)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/kaggle/review-harness-2

---


Follow the instructions in [.agents/skills/review-harness/SKILL.md](../../../.agents/skills/review-harness/SKILL.md).

Use `$ARGUMENTS` as the game name if provided.