ericrisco/rsc-harness / skills/typescript
typescript
VerifiedUse when writing or fixing TypeScript type code (.ts/.tsx/.d.ts), modeling data with generics/unions/branded types, diagnosing narrowing failures, or configuring tsconfig and the build toolchain. NOT runtime code, fs/streams/http (that is `nodejs`); NOT component/route typing (that is `react`/`nextjs`); NOT ORM type-gen (that is `drizzle-orm`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.8 KB |
| evals/README.md | markdown | 1.0 KB |
| evals/cases.yaml | config | 3.1 KB |
| references/build-and-monorepo.md | markdown | 5.6 KB |
| references/type-system.md | markdown | 5.5 KB |
| scripts/verify.shexecutable | script | 1.7 KB |
evals/README.md
View on GitHub# Evals: typescript
`cases.yaml` checks two things. **Routing**: `should_trigger` lists prompts (including
non-obvious narrowing symptoms and Spanish/Catalan phrasings) that must select this skill, and
`should_not_trigger` lists adjacent prompts that must route to a named sibling (`nodejs`,
`react`, `drizzle-orm`, `python`, `testing-web`) instead. **Capability**: the scenario gives a
loosely-typed module with no tsconfig and grades the output against the `must_include` rubric
(any -> precise types, discriminated union with a literal discriminant, exhaustive `never`
guard, a strict tsconfig, `import type` usage, no error-silencing casts).
To run, feed each prompt to the skill router and confirm the trigger/route decision, then run
the capability scenario through an agent loaded with this skill and score the result by hand
against the rubric. There is no automated runner here; the rigor is the rubric plus
`scripts/verify.sh`, which independently proves the toolchain enforces strictness and
exhaustiveness on a sample project.
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 |