CtrlK
BlogDocsLog inGet started
Tessl Logo

typescript-expert

TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.

50

Quality

55%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/typescript-expert/SKILL.md

The canonical home for this skill is typescript-expert in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 code-forward, actionable TS reference with a clear validation-backed workflow, but it is padded with concepts Claude already knows and fails to use its own bundle files, inlining their content instead of linking to them.

Suggestions

Replace the inlined tsconfig and branded-type/utility-type examples with one-line pointers to references/tsconfig-strict.json and references/utility-types.ts to fix progressive disclosure and reduce duplication.

Cut explanatory padding Claude already knows (branded-type rationale, satisfies/const-assertion tutorials) and the filler AI-Assisted Development and "When to Use" boilerplate to improve conciseness.

Reference scripts/ts_diagnostic.py and references/typescript-cheatsheet.md from the relevant debugging and quick-reference sections so the bundle is actually navigable.

DimensionReasoningScore

Conciseness

Mostly compact code blocks, tables, and decision trees, but it re-teaches well-known TS patterns (branded types, DeepReadonly, satisfies), duplicates content already in the references bundle, and includes filler like the AI-Assisted Development section and the boilerplate "When to Use" line.

3 / 5

Actionability

Rich executable guidance throughout — concrete commands (npx tsc --extendedDiagnostics, tsc --generateTrace, npm run typecheck) and complete TypeScript snippets — with only minor gaps such as conditional command -v guards and pseudocode-style decision trees.

4 / 5

Workflow Clarity

The "When invoked" section gives a clear numbered sequence with an explicit validation step (typecheck/test/build) and a safety note about avoiding watch processes, but the validate->fix->retry feedback loop is only implicit rather than spelled out.

4 / 5

Progressive Disclosure

Bundle files exist (references/tsconfig-strict.json, utility-types.ts, typescript-cheatsheet.md, scripts/ts_diagnostic.py) yet the body never references them and instead inlines their duplicated content, fitting the anchor where content that belongs in separate files is inlined and references are absent/buried.

2 / 5

Total

13

/

20

Passed

Description

50%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 conveys a clear TS/JS expertise niche and enumerates specific knowledge areas, but it states capabilities rather than actions and omits any explicit use-trigger. Adding a "Use when..." clause with natural user phrases would lift completeness and trigger quality.

Suggestions

Add an explicit "Use when..." clause naming concrete trigger scenarios (e.g., slow type checking, JS-to-TS migration, monorepo tsconfig setup).

Replace knowledge-area nouns with concrete actions users would request (e.g., "Diagnoses slow type checking", "Migrates JS files to TypeScript").

Include natural user terms and synonyms like "tsconfig", "type errors", "strict mode", and ".ts" to improve trigger matching.

DimensionReasoningScore

Specificity

Names the domain plus several specific capability areas ("type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling"), but states areas of knowledge rather than concrete actions/verbs, matching the 'names domain and 1-2 concrete actions' anchor loosely.

3 / 5

Completeness

Clearly states what the skill does (expert with deep knowledge of five areas) but provides no "Use when..." trigger clause, capping completeness at 3 per the guideline.

3 / 5

Trigger Term Quality

Includes relevant keywords ("TypeScript", "JavaScript", "monorepo", "migration") but leans on jargon like "type-level programming" and omits natural user phrases such as tsconfig, type errors, or strict mode.

3 / 5

Distinctiveness Conflict Risk

The TypeScript/JavaScript niche is identifiable, but the broad five-area scope overlaps with closely related sibling experts (build, module, type), so it could still trigger for the wrong specialist.

3 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.