CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

typescript-best-practices

TypeScript best practices. Use when reading or editing any .ts or .tsx file.

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary lean skill file: a dense, opinionated rule table with concrete type-level syntax, an explicit ordering pre-step, and a verified one-level-deep reference holding the executable examples. Nothing is padded, and nothing that belongs in the reference is inlined.

DimensionReasoningScore

Conciseness

The 16-rule table is dense, opinionated, and free of padding — it never explains concepts Claude already knows (what TypeScript is, how libraries work); every summary adds non-obvious project-specific guidance (e.g., 'A brand comes from a verifying type guard... never from `as`'). This matches anchor 5: lean, assumes competence, every token earns its place.

5 / 5

Actionability

The guidance is concrete and directly executable despite being instruction-style: exact type syntax (`[T, ...T[]]`, `& { readonly __brand: "X" }`, `const _exhaustive: never = x;`), library specifics (`z.infer`, `Pick`/`Omit`/`Parameters`/`ReturnType`), naming conventions (`isX`/`hasX`), and an ordered narrowing hierarchy, with full copy-paste examples in the verified one-level reference. Per the rubric's code-vs-instruction note, absence of inline code blocks is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

This is a single-purpose skill (apply these rules when touching TypeScript files) whose single action is unambiguous, and it even states an explicit pre-step ordering ('Apply the **type-system-discipline** principle skill first'). Per the rubric's simple-skill exception, a clear single action scores 5; no destructive or batch operations exist that would require validation checkpoints.

5 / 5

Progressive Disclosure

The body is a clear overview (the rules table) with content appropriately split: executable examples live in `references/patterns.md`, which exists, is one level deep (it points only to external principle skills, not nested bundle files), and is clearly signaled ('Examples: `references/patterns.md`.'). This matches anchor 5: clear overview, well-signaled one-level-deep references, easy navigation.

5 / 5

Total

20

/

20

Passed

Description

65%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.

The description has an explicit, concrete trigger clause (when to use it, with file extensions) and a clearly distinct TypeScript niche, but the capability side is a bare topic label with no concrete actions, which keeps specificity low. It reads as a well-triggered but under-described skill.

Suggestions

List 2-3 concrete capabilities after the topic label, e.g., 'Applies type-safety rules — discriminated unions, branded types, boundary validation, exhaustiveness checks — when writing or reviewing TypeScript.'

Add natural trigger synonyms such as 'TS', 'type safety', or 'type annotations' so the description matches more phrasings a user would naturally say.

State what the skill does on invocation (e.g., 'enforces these rules when editing TypeScript code'), not just when it applies.

DimensionReasoningScore

Specificity

"TypeScript best practices." names the domain clearly but states zero concrete capability actions — it is a topic label, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 1 because the domain is concrete rather than pure abstraction, and not a 3 because no 1-2 concrete actions are listed (the 'reading or editing' phrase is a trigger, not a capability).

2 / 5

Completeness

Both parts are present: a 'what' ("TypeScript best practices") and an explicit 'when' clause with concrete file extensions. It falls short of anchor 5 because the 'what' is a vague label that never says what the skill actually does (apply type-safety rules such as discriminated unions, branded types, boundary validation).

4 / 5

Trigger Term Quality

"Use when reading or editing any .ts or .tsx file" provides good natural keyword coverage including both file extensions plus 'TypeScript' itself. A few natural terms are missing (e.g., 'TS', 'type safety', 'type annotations'), so it matches anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The TypeScript niche is clear with distinct extension-based triggers (.ts/.tsx), giving minimal conflict risk overall. Minor overlap remains with closely related skills (JavaScript best practices, linting/style guides, and React skills that would also trigger on .tsx), matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

14

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

geut/factory-skills

Path

.agents/skills/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.