typescript-best-practices
Write idiomatic TypeScript patterns for clean, maintainable code. Use when writing or refactoring TypeScript classes, functions, modules, or async logic.
51
57%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/typescript/typescript-best-practices/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has good structural completeness with an explicit 'Use when...' clause and identifies the TypeScript domain clearly. However, it lacks specificity in the concrete actions it performs (relying on the vague 'idiomatic patterns') and could benefit from more natural trigger terms that users would actually say. The distinctiveness is moderate—it could conflict with general code quality or JavaScript-related skills.
Suggestions
Add specific concrete actions such as 'implement generics, define type-safe interfaces, use discriminated unions, handle async/await error patterns' to improve specificity.
Expand trigger terms to include common variations like 'TS', '.ts files', 'types', 'interfaces', 'generics', 'type guards', 'enums' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (TypeScript) and mentions some actions ('writing or refactoring') with targets ('classes, functions, modules, async logic'), but the core capability 'write idiomatic TypeScript patterns for clean, maintainable code' is somewhat vague—it doesn't list specific concrete actions like 'generate type-safe interfaces, implement generics, configure strict compiler options.' | 2 / 3 |
Completeness | Clearly answers both 'what' (write idiomatic TypeScript patterns for clean, maintainable code) and 'when' (Use when writing or refactoring TypeScript classes, functions, modules, or async logic) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'TypeScript', 'classes', 'functions', 'modules', 'async logic', 'refactoring', but misses common user variations such as 'TS', '.ts files', 'types', 'interfaces', 'generics', 'type safety', or 'enums' that users would naturally mention. | 2 / 3 |
Distinctiveness Conflict Risk | While it specifies TypeScript, the description is broad enough ('clean, maintainable code', 'writing or refactoring') that it could overlap with general coding style skills, JavaScript skills, or other language-specific pattern skills. The triggers aren't narrow enough to clearly carve out a unique niche. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions as a TypeScript style guide with clear organization into guidelines and anti-patterns, but it critically lacks concrete code examples in the main body, relying entirely on a referenced file that doesn't exist in the bundle. Much of the content covers conventions Claude already knows (naming conventions, async/await preference), reducing its value. The skill would benefit significantly from inline executable examples demonstrating the non-obvious patterns like exhaustiveness checks, DI patterns, and Zod validation.
Suggestions
Add concrete, executable code examples for at least the non-obvious patterns (exhaustiveness checking with `never`, DI with constructor injection, Zod validation) directly in the SKILL.md body.
Remove or significantly trim guidance Claude already knows well (naming conventions, async/await over .then(), optional chaining) to improve token efficiency.
Provide the referenced 'references/examples.md' file in the bundle, or inline the most critical examples if the file cannot be provided.
Reduce excessive bold formatting throughout the document — the current styling adds visual noise without improving scannability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some guidance Claude already knows (e.g., PascalCase for classes, camelCase for variables, async/await over .then() chains). The bold formatting is excessive and adds visual noise without adding information. However, it avoids lengthy explanations and stays relatively compact. | 2 / 3 |
Actionability | The skill provides only abstract guidelines and rules without any concrete code examples, executable snippets, or copy-paste ready patterns. Statements like 'Use arrow functions for callbacks' and 'Favor composition over inheritance' are descriptive rather than instructive, and the referenced examples file is not provided in the bundle. | 1 / 3 |
Workflow Clarity | This is a single-purpose reference skill (coding conventions/patterns) rather than a multi-step workflow. The content is clearly organized into Implementation Guidelines, Anti-Patterns, and References sections, making it easy to follow for its intended purpose as a style guide. | 3 / 3 |
Progressive Disclosure | The skill references 'references/examples.md' for detailed patterns which is good progressive disclosure structure, but the bundle shows no such file exists. The main content is well-organized into sections, but without the referenced file actually being available, the disclosure is incomplete and the reference is a dead link. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
556618c
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.