mcollina/typescript-magician
Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors. Use when the user asks about TypeScript (TS) types, generics, type inference, type guards, removing `any` types, strict typing, type errors, `infer`, `extends`, conditional types, mapped types, template literal types, branded/opaque types, or utility types like `Partial`, `Record`, `ReturnType`, and `Awaited`.
87
95%
Does it follow best practices?
Impact
76%
1.16xAverage score across 5 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities (designing generics, refactoring `any`, creating type guards, resolving compiler errors) and provides comprehensive trigger guidance with an extensive list of natural keywords. The description is well-scoped to TypeScript's type system, making it highly distinguishable from general programming or JavaScript skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: designing complex generic types, refactoring `any` types to strict alternatives, creating type guards and utility types, and resolving TypeScript compiler errors. | 3 / 3 |
Completeness | Clearly answers both 'what does this do' (designs generic types, refactors any types, creates type guards, resolves compiler errors) AND 'when should Claude use it' with an explicit 'Use when...' clause listing extensive trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'TypeScript', 'TS', 'types', 'generics', 'type inference', 'type guards', 'removing any types', 'strict typing', 'type errors', 'infer', 'extends', 'conditional types', 'mapped types', 'template literal types', 'branded/opaque types', and specific utility types like 'Partial', 'Record', 'ReturnType', 'Awaited'. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to TypeScript's type system specifically, with distinct triggers like generics, type guards, utility types, and branded types that are unlikely to conflict with general coding or JavaScript skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured TypeScript typing skill with strong actionability, clear workflow with validation checkpoints, and excellent progressive disclosure through categorized rule file references. The main weakness is moderate verbosity in the 'Capabilities include' and 'For every TypeScript challenge' sections, which enumerate things Claude already knows or provide meta-instructions that don't add concrete value. Note: bundle files were not provided, so the referenced rule files cannot be verified to exist.
Suggestions
Remove or significantly trim the 'Capabilities include' bullet list—Claude already knows these TypeScript features and listing them wastes tokens.
Remove or condense the 'For every TypeScript challenge' meta-instructions (explain theory, show before/after, etc.)—these are generic coaching instructions that don't add actionable specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Capabilities include' bullet list and 'For every TypeScript challenge' section are somewhat redundant—Claude already knows these concepts and doesn't need to be told to 'explain the type theory behind the problem.' The examples and workflow steps are efficient, but the skill could be tightened by removing the capability enumeration and the meta-instructions about explaining theory. | 2 / 3 |
Actionability | The skill provides fully executable before/after code examples for eliminating `any` and narrowing unknown types. The workflow includes concrete commands (`tsc --noEmit`) and specific steps for diagnosing and fixing type issues. The examples are copy-paste ready and demonstrate real patterns. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation checkpoints: run `tsc --noEmit` before changes, identify root cause, craft solution, validate replacements satisfy call sites, and confirm with a second `tsc --noEmit` pass. This is a proper feedback loop for a potentially destructive refactoring operation. | 3 / 3 |
Progressive Disclosure | The skill has a clean overview with quick examples inline, then well-organized one-level-deep references to 14 rule files grouped by category (Core Patterns, Advanced Generics, Type-Level Programming, Type Safety Patterns, Debugging). Navigation is clear and references are well-signaled with descriptive labels. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents