typescript-expert

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

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/typescript-expert/SKILL.md

Quality

Content

52%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 highly actionable with concrete commands, code, and decision matrices organized under a clear validation-gated workflow, but it is verbose with textbook TS explanations Claude already knows and fails to use the provided bundle files, inlining reference material that should live one level deep.

Suggestions

Replace inlined textbook patterns (branded types, DeepReadonly, conditional types, satisfies) with a one-line pointer to references/typescript-cheatsheet.md and references/utility-types.ts; keep only the genuinely non-obvious bits inline.

Link the existing bundle files from the body — e.g. reference references/tsconfig-strict.json from the 'Strict by Default' section and scripts/ts_diagnostic.py from the debugging section — instead of duplicating their content inline.

Make the fix-and-revalidate feedback loop explicit in step 4 ('If typecheck fails, fix and re-run until clean before proceeding') and trim the generic code-review checklist and AI-assisted-development section, which restate knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The body extensively explains textbook TypeScript Claude already knows (branded types, DeepReadonly, conditional types, satisfies, const assertions, custom error classes with captureStackTrace) plus a generic code-review checklist and an AI-assisted-development section, making it noticeably verbose with several padded sections.	2 / 5
Actionability	Concrete, copy-paste-ready commands and code abound (tsc diagnostics, migration shell snippets, tsconfig JSON, decision matrices), with only minor gaps where examples are illustrative rather than fully executable.	4 / 5
Workflow Clarity	The 'When invoked' section gives a clear numbered 0–4 sequence with an explicit validation step (typecheck/test/build) and a safety note, but steps 2–3 are vague and the fix-and-revalidate feedback loop is implicit rather than spelled out.	4 / 5
Progressive Disclosure	Bundle files exist (typescript-cheatsheet.md, utility-types.ts, tsconfig-strict.json, ts_diagnostic.py) but none are referenced from the body, and their content is instead inlined as a monolithic reference wall — classic 'content that belongs in separate files is inlined' with references effectively buried.	2 / 5
	Total	12 / 20 Passed

Description

57%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 clearly conveys the TypeScript/JavaScript expertise domain and includes natural trigger terms, but it omits any explicit 'Use when...' guidance and its broad scope creates overlap risk with closely related sibling skills.

Suggestions

Add an explicit 'Use when...' clause listing concrete triggers, e.g. 'Use when the user needs TypeScript type-level help, performance tuning, monorepo config, or JS-to-TS migration.'

Narrow the niche or add a boundary line distinguishing this skill from typescript-build-expert, typescript-module-expert, and typescript-type-expert to reduce conflict risk.

Reframe capability areas as concrete actions (e.g. 'Optimizes type-checking performance', 'Migrates JS codebases to TypeScript') instead of 'deep knowledge of' noun phrases.

Dimension	Reasoning	Score
Specificity	Names the domain (TypeScript/JavaScript) and several capability areas (type-level programming, performance optimization, monorepo management, migration strategies, modern tooling), but they are framed as 'deep knowledge of' rather than concrete actions, so it sits above score 2 yet lacks true action verbs.	3 / 5
Completeness	The 'what' is clear (a TS/JS expert across five stated domains), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Natural terms a user would say are well covered — 'TypeScript', 'JavaScript', 'monorepo', 'migration', 'performance' — with only minor synonyms missing, placing it above score 3 but short of comprehensive score 5.	4 / 5
Distinctiveness Conflict Risk	It is TypeScript-specific (distinct from non-TS skills) but the broad scope — type-level, performance, monorepo, migration, tooling — overlaps heavily with the sibling TS skills (typescript-build/module/type-expert) referenced in the body, so it is not a clear niche.	3 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fathah/hermes-desktop
Path: .agents/skills/typescript-expert/SKILL.md
Commit: 3aaadb0

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.