CtrlK
BlogDocsLog inGet started
Tessl Logo

typescript-best-practices

Provides TypeScript patterns for type-first development, making illegal states unrepresentable, exhaustive handling, and runtime validation. Must use when reading or writing TypeScript/JavaScript files.

85

1.11x
Quality

Does it follow best practices?

Impact

96%

1.11x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

The body is concise and highly actionable with executable, well-structured examples, but it is monolithic for its size and its main workflow lacks explicit validation checkpoints.

Suggestions

Add an explicit validation/feedback checkpoint to the Type-First Development workflow (e.g. 'compile after each step; resolve type errors before proceeding').

Split the larger reference-style sections (Zod runtime validation, Configuration, type-fest) into separate reference files with one-level-deep links from the overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Lean and efficient — no introductory padding about what TypeScript is or how libraries work; each section pairs a brief directive with tight, well-commented code, fitting the score-3 'lean and efficient, assumes Claude's competence' anchor.

3 / 3

Actionability

Provides numerous complete, executable TypeScript blocks (discriminated unions, branded types, Zod schemas, exhaustive switch, config validation) that are copy-paste ready, matching the score-3 anchor.

3 / 3

Workflow Clarity

The Type-First Development workflow is a clear 4-step sequence ('Define the data model' through 'Validate at boundaries') but lacks explicit validation checkpoints or error-recovery feedback loops, fitting the score-2 'sequence present but checkpoints missing or implicit' anchor.

2 / 3

Progressive Disclosure

Well-organized into clear sections with the type-fest content appropriately marked 'Optional', but for a ~265-line skill all content is monolithically inline with no references split out, fitting the score-2 'content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

77%

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 is specific, complete, and provides an explicit use-when trigger, but its trigger-term coverage lacks common variations and it risks overlapping with related code skills.

Suggestions

Broaden trigger terms to include natural variations users would say, e.g. '.ts/.tsx files', 'types', 'interfaces', or 'TypeScript errors'.

Tighten the trigger to reduce overlap with adjacent skills, e.g. 'Use when writing or reviewing TypeScript/JavaScript (.ts/.tsx/.js/.jsx) files' and defer React-specific cases to the React skill.

DimensionReasoningScore

Specificity

Lists multiple specific concrete capabilities — 'type-first development', 'making illegal states unrepresentable', 'exhaustive handling', and 'runtime validation' — matching the score-3 anchor rather than the narrower score-2 'some actions'.

3 / 3

Completeness

Clearly answers both what (the listed TypeScript patterns) and when via the explicit trigger 'Must use when reading or writing TypeScript/JavaScript files', matching the score-3 anchor with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Includes relevant natural keywords ('TypeScript/JavaScript files', 'reading or writing') but misses common variations like '.ts', 'tsx', 'types', or 'TS', fitting the score-2 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

'reading or writing TypeScript/JavaScript files' is somewhat specific but broad enough to overlap with adjacent skills (the skill itself flags react-best-practices as a co-load), fitting the score-2 'could still overlap' anchor.

2 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NeverSight/skills_feed
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.