A collection of community game environments for the ARC-AGI-3 benchmark.
This repository also configures its own agents. See what arc-interactive tells them →
theredbluepill/arc-interactive
Skill Claude CodeCodex
Judges whether an ARC game is discoverable by play (goals/rules learned in the env); co-requires fair shared observation/actions for humans and AIs. Use when reviewing stems for discovery-through-play or remediation.
theredbluepill/arc-interactive
Skill Claude CodeCodex needs its repo
Checks mechanical per-level solvability (a winning trajectory exists under the real game rules). Use when authoring or reviewing stems, after logic changes, or when debugging “impossible” puzzles. Complements discoverability review.
theredbluepill/arc-interactive
Skill Claude CodeCodex needs its repo
This skill guides the creation of ARC-AGI-3 games based on established patterns from environmentfiles/.
theredbluepill/arc-interactive
Skill Claude CodeCodex
Use this skill when adding or refreshing 64×64 registry GIFs in assets/, or when checking whether a game’s HUD is suitable for markdown previews.
theredbluepill/arc-interactive
Skill Claude CodeCodex
Skill for playing and testing ARC-AGI-3 games using rungame.py.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: