Skip to content

ericrisco/rsc-harness / skills/unreal

unreal

Verified

Use when building, scripting or debugging a game in Unreal Engine 5 with Blueprint or C++ — the gameplay framework (Actor, Pawn, Character, GameMode, PlayerController), Actor lifecycle and tick, the reflection macros and garbage collection, Enhanced Input, multicast delegates, UMG widgets, Paper2D, and Blueprint-to-C++ parity in both directions. NOT Godot (that is `godot`), NOT Unity or MonoBehaviour (that is `unity`), NOT language-only C++ memory and RAII questions with no Unreal types (that is `cpp`).

FileKindSize
SKILL.mdskill md15.6 KB
evals/README.mdmarkdown916 B
evals/cases.yamlconfig4.1 KB
references/blueprint-cpp-parity.mdmarkdown5.9 KB
references/gameplay-framework.mdmarkdown4.8 KB
references/packaging.mdmarkdown3.8 KB

evals/README.md

View on GitHub
# Eval harness — `unreal` skill

These cases are run by the rsc skill-eval harness (a Claude agent with the full catalog loaded)
or read manually. **Triggering**: the `unreal` description must fire on real UE5 Blueprint/C++
requests — including symptom-only ones (a garbage-collected UObject) — while staying quiet on
near-misses that belong to `godot`, `unity`, `cpp`, `game-design`, or `gamedev-shipping`, routing
each to that sibling. **Capability**: with `SKILL.md` + references loaded, the generated UE5 code
must satisfy the `must_include` rubric — Enhanced Input (never legacy mappings), GC-safe
`UPROPERTY() TObjectPtr<T>` refs, `GENERATED_BODY()`, no logic in the constructor, correct
Blueprint exposure, a dynamic multicast delegate, and the right `.Build.cs` module — and beat the
no-skill baseline. Run 3–5 trials per prompt (LLM routing is non-deterministic); a prompt passes
on a majority.
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall