菜单
Create or update an LLM harness that connects a language model to a kaggle-environments game (prompt generation, response parsing, and tests)
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Kaggle/kaggle-environments --skill create-harness命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Audit a game environment's README.md and AGENTS.md against its engine implementation. Use when the user asks to "review", "audit", "check", or "fact-check" environment docs, when players report doc/engine discrepancies, or before a competition launch. Also use proactively after changing an environment's engine (`kaggle_environments/envs/<game>/<game>.py`) when a sibling README.md or AGENTS.md exists — rebalances and mechanic changes routinely leave those docs stale. The engine is always the source of truth — docs get fixed, not the engine.
Audit a game environment's README.md and AGENTS.md against its engine implementation (stale constants, unreachable caps, undocumented preconditions, wrong observation fields). Also use proactively after changing an environment engine that has sibling docs. The engine is the source of truth.
Create or update an LLM harness that lets a language model play a kaggle-environments game. Use this skill whenever the user wants to write a harness, LLM agent, or game-playing prompt for any kaggle-environments game — including OpenSpiel games, word games, or custom environments. Also use it when the user mentions core_harness.py, GameHarness, ParseResult, or asks how to connect an LLM to a game.
基于 SOC 职业分类
| name | create-harness |
| description | Create or update an LLM harness that connects a language model to a kaggle-environments game (prompt generation, response parsing, and tests) |
Follow the instructions in .agents/skills/create-harness/SKILL.md.
Use $ARGUMENTS as the game name if provided.
