ericrisco/rsc-harness / skills/game-storytelling
game-storytelling
VerifiedUse when a game's story is the work: premise and pillars, branching topology, meaningful choice, dialogue state, quests, environmental storytelling, ludonarrative harmony. Author portable — engine wiring is `godot`/`unity`/`unreal`. NOT the mechanics and economy the story serves (that is `game-design`), NOT level layout (that is `level-design`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.2 KB |
| evals/README.md | markdown | 1.6 KB |
| evals/cases.yaml | config | 5.9 KB |
| references/branching-and-state.md | markdown | 7.8 KB |
| references/dialogue-tools.md | markdown | 7.1 KB |
| references/environmental-storytelling.md | markdown | 7.2 KB |
evals/README.md
View on GitHub# Eval harness — `game-storytelling`
Agent-run eval, not a shell script. A human or judge-agent drives a Claude Code
agent and scores its behaviour against `cases.yaml`. There is no automated grader.
`cases.yaml` has three blocks: `should_trigger` (7), `should_not_trigger` (5),
and `capability` (2 scenarios with `must_include` rubrics).
## A. Triggering accuracy
Assert the skill fires on real narrative-design work (premise/pillars, branching
and choice, dialogue-tool authoring, quests, environmental storytelling,
ludonarrative harmony) and stays quiet on near-misses that belong to `game-design`
(mechanics/balance), `level-design` (spatial layout), the engine skill (dialogue
runner + save wiring), `marketing` (store/trailer copy), or plain prose fiction.
Load only this skill, run each prompt in a fresh session for 3–5 trials, and score
`should_trigger` as fire / `should_not_trigger` as don't-fire (bonus: routes to the
named `route_to`). Pass bar: ≥90% correct decisions across all trials.
## B. Capability uplift
Run each `capability` scenario WITH vs WITHOUT the skill and score against its
`must_include` rubric. The branching scenario checks the containment kit (2^N
framing, foldback/reconvergence, gates, state-over-structure, real-vs-illusory
choice) and engine-agnostic hand-off; the dissonance scenario checks the verb/
reward audit and cheaper-piece fix. Pass bar: WITH the skill covers ≥80% of rubric
points and clearly beats the baseline (which typically skips the explosion math,
conflates fake stakes with real choice, and writes engine code instead of a graph).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |