kaggle-environments
CLAUDE.md459 starsChanged 58 days agoApache-2.0View on GitHub
See AGENTS.md for project overview, architecture, commands, and code style. See .agents/skills/ for detailed how-to guides: - create-environment -- building a game environment (Python backend) - create-harness -- writing an LLM harness (connecting a language model to a game) - review-harness -- auditing an existing harness for gameplay-impacting bugs - review-docs -- auditing an environment's README/AGENTS.md against its engine - create-visualizer -- building a web visualizer for any game (regular or OpenSpiel) - create-playable-visualizer -- building an interactive human-vs-AI visualizer…
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-environmentSkill
- create-harnessSkill
- create-playable-visualizerSkill
- create-visualizerSkill
- onboard-open-spiel-gameSkill
- review-docsSkill
- review-harnessSkill
- run-ablationSkill
- create-environmentSkill
- create-harnessSkill
- create-playable-visualizerSkill
- create-visualizerSkill
- onboard-open-spiel-gameSkill
- review-docsSkill
- review-harnessSkill
- run-ablationSkill
The file
Files
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
See AGENTS.md for project overview, architecture, commands, and code style.
See .agents/skills/ for detailed how-to guides:
create-environment-- building a game environment (Python backend)create-harness-- writing an LLM harness (connecting a language model to a game)review-harness-- auditing an existing harness for gameplay-impacting bugsreview-docs-- auditing an environment's README/AGENTS.md against its enginecreate-visualizer-- building a web visualizer for any game (regular or OpenSpiel)create-playable-visualizer-- building an interactive human-vs-AI visualizer (TS engine port + worker)onboard-open-spiel-game-- adding an OpenSpiel game (Python backend)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.