CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

typescript-best-practices

Write idiomatic TypeScript patterns for clean, maintainable code. Use when writing or refactoring TypeScript classes, functions, modules, or async logic.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/typescript/typescript-best-practices/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, actionable TypeScript conventions list with a clean one-level reference to examples.md, weakened by a stray 'Priority' heading, no inline code examples, no verification step, and an orphaned REFERENCE.md containing links to files that do not exist. Core guidance quality is solid; the bundle structure is the main liability.

Suggestions

Link references/REFERENCE.md from the SKILL.md References section (or remove it) so its project-structure and tsconfig content is discoverable, and delete or create the dangling project-structure.md and configuration.md links inside it.

Inline one or two short code snippets for the highest-impact rules (e.g., never-based exhaustiveness or constructor injection) so common cases are covered without opening the reference file.

Add a brief verification step, such as running eslint with the configured import order and tsc with noUnusedLocals to confirm the code conforms before finishing.

DimensionReasoningScore

Conciseness

The body is a terse, dense rule list that assumes TypeScript competence and explains no basic concepts, so it is largely efficient. It falls short of anchor 5 due to minor noise: the leftover '## **Priority: P1 (HIGH)**' heading carries no guidance, and pervasive bold/backtick emphasis adds tokens without adding information.

4 / 5

Actionability

Guidance names concrete tools and flags ('eslint-plugin-import', 'noUnusedLocals', 'jest.Mocked<T>', 'Zod', 'Tsoa', 'import type'), so most instructions are executable as written. It does not reach anchor 5 because the body contains no inline copy-paste code or commands covering common cases — all examples are deferred to references/examples.md.

4 / 5

Workflow Clarity

As a simple single-purpose conventions skill, its single action (apply these rules when writing/refactoring TypeScript) is clear and the guidelines/anti-patterns split is coherent, fitting the simple-skill exception. It stays at 4 rather than 5 because there is no verification guidance (e.g., run eslint/tsc to confirm conformance) and the stray 'Priority: P1' heading adds slight ambiguity about how the sections relate.

4 / 5

Progressive Disclosure

The body's link to references/examples.md is real, one level deep, and clearly signaled with its topics, but the bundle's other file, references/REFERENCE.md, is never referenced from SKILL.md, making its content undiscoverable; worse, REFERENCE.md itself links to nonexistent files (project-structure.md, configuration.md). This mix of a good signaled reference with an orphaned, broken-link file fits anchor 3 rather than the well-organized anchor 4.

3 / 5

Total

15

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-formed description that clearly states both capability and an explicit, concrete 'Use when' trigger clause scoped to TypeScript. Its main weakness is that the 'what' is stated as one general action rather than several specific capabilities, and it lacks file-extension synonyms in the description text itself.

DimensionReasoningScore

Specificity

The description names the domain ('TypeScript') and a single general action ('Write idiomatic TypeScript patterns for clean, maintainable code'), but does not enumerate several specific concrete actions; the classes/functions/modules/async items appear as trigger contexts rather than capabilities. It matches the anchor for naming the domain with 1-2 actions, not the level above which requires a list of several specific actions.

3 / 5

Completeness

It explicitly answers both questions: 'Write idiomatic TypeScript patterns for clean, maintainable code' (what) and 'Use when writing or refactoring TypeScript classes, functions, modules, or async logic' (when) with concrete trigger phrases. The 'when' clause is explicit and specific, matching the top anchor rather than the 'could be more explicit' anchor below it.

5 / 5

Trigger Term Quality

Natural terms like 'TypeScript', 'refactoring', 'classes', 'functions', 'modules', and 'async logic' are words users would actually say, giving good keyword coverage. It is not a 5 because the description text omits file extensions (.ts, .tsx) and common synonyms like 'types' or 'interfaces'.

4 / 5

Distinctiveness Conflict Risk

The TypeScript scope establishes a clear niche with mostly distinct triggers, but generic programming terms ('classes', 'functions', 'modules') and the phrase 'clean, maintainable code' create minor overlap risk with general code-style or linting skills. It is more distinct than anchor 3 but does not fully meet the minimal-conflict bar of anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

HoangNguyen0403/agent-skills-standard

Path

.github/skills/typescript/typescript-best-practices/SKILL.md

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.