ericrisco/rsc-harness / skills/godot
godot
VerifiedUse when writing, reviewing, or debugging Godot 4.x games in GDScript or C# — scenes, nodes, custom Resources, autoload/EventBus signals, typed GDScript, CharacterBody2D/3D movement, GUT/gdUnit4 — or porting Godot 3 APIs to 4. NOT Unity/Unreal (that is `unity`/`unreal`), NOT `.gdshader` code (`gamedev-shaders`), NOT GDExtension C++ tooling (`cpp`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.1 KB |
| evals/README.md | markdown | 1.0 KB |
| evals/cases.yaml | config | 4.6 KB |
| references/export-and-testing.md | markdown | 4.9 KB |
| references/gdscript-style.md | markdown | 3.2 KB |
| references/godot3-to-4-traps.md | markdown | 5.0 KB |
| references/nodes-scenes-resources.md | markdown | 5.0 KB |
evals/README.md
View on GitHub# Eval harness — `godot` skill
These cases are read by the rsc skill-eval harness (a Claude agent with the full skill catalog
loaded) or by hand. They assert two things. **Triggering**: the `godot` description fires on each
`should_trigger` prompt — including symptom-only and Spanish phrasings — and stays quiet on the
`should_not_trigger` near-misses, routing each to its named sibling (`unity`, `unreal`,
`gamedev-shaders`, `cpp`, `game-design`, `gamedev-multiplayer`) instead. **Capability**: with
`SKILL.md` and its references loaded, the generated Godot code satisfies every
`capability.must_include` bullet — the Godot 4 flow (`velocity` property + no-arg `move_and_slide()`),
typed GDScript, Callable signals, `@export`/`@onready`, zero Godot 3 leftovers, and a correct C#
parity block — and clearly beats the no-skill baseline. Because LLM routing is non-deterministic,
run 3–5 trials per prompt and pass on a majority. No network is required; the capability rubric is
judged by reading the output against the bullets.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |