typescript-expert

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

Quality

63%

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

77%

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 executable code, commands, decision tables, and a validated workflow, and it is well-organized. Its weaknesses are token efficiency (padded checklist/AI sections and a vacuous closer) and progressive disclosure: provided reference/script bundle files are never linked from the body while their content sits inline.

Suggestions

Link the existing bundles from the relevant sections (e.g. 'See references/tsconfig-strict.json', 'See references/typescript-cheatsheet.md', 'See scripts/ts_diagnostic.py') and move the inlined tsconfig JSON and type-pattern catalog into those files.

Trim the generic Code Review Checklist and the 'AI-Assisted Development' section, and remove the vacuous 'When to Use' closer to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	Most content is concrete and specific, but padding remains: the generic Code Review Checklist restates TS best practices Claude already knows, the 'AI-Assisted Development' section is off-scope filler, 'TypeScript paths only work at compile time, not runtime' states a known fact, and the trailing 'When to Use' line is vacuous; leaner than a 1 but not a tight 3.	2 / 3
Actionability	The body is rich with fully executable, copy-paste-ready material: bash diagnostics (npx tsc --extendedDiagnostics), valid TypeScript snippets (Branded Types, DeepReadonly, satisfies), concrete tsconfig JSON, and a migration decision table; it is well above the pseudocode/incomplete bar of 2.	3 / 3
Workflow Clarity	The numbered 'When invoked' sequence (route -> analyze -> identify -> apply -> validate) includes an explicit validation step with concrete commands (npm run -s typecheck \|\| npx tsc --noEmit, npm test -s) plus a safety note and a final 'validate before considering resolved' checkpoint, and the error-pattern 'Fix priority' lists give recovery guidance; checkpoints are explicit, not implicit, so above 2.	3 / 3
Progressive Disclosure	Bundle files exist (references/tsconfig-strict.json, references/typescript-cheatsheet.md, references/utility-types.ts, scripts/ts_diagnostic.py) but none are referenced or signaled anywhere in the body, while the tsconfig JSON, type patterns, and cheatsheet-style content are inlined instead of split into those files; organized enough to avoid 1, but references are unsignaled and content that should be separate is inline, so not 3.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 domain focus with several named sub-areas, but it reads as a knowledge profile rather than a trigger-oriented statement of actions. It lacks any 'Use when...' guidance and does not distinguish itself from the closely related sibling skills, capping both completeness and distinctiveness.

Suggestions

Rewrite as concrete third-person actions, e.g. 'Analyzes, fixes, and optimizes TypeScript/JavaScript type systems, performance, monorepos, and migrations.'

Add an explicit trigger clause: 'Use when the user needs help with TypeScript type errors, slow type-checking, tsconfig/strict-mode setup, monorepo configuration, or JS-to-TS migration.'

Narrow the niche or add a distinct trigger so it does not collide with typescript-build-expert, typescript-module-expert, and typescript-type-expert.

Dimension	Reasoning	Score
Specificity	The phrase 'expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling' names the domain and several concrete sub-areas, but frames them as knowledge rather than actions (no verbs like 'Analyze', 'Optimize', 'Migrate'), so it is above vague/abstract (1) but lacks comprehensive concrete actions (3).	2 / 3
Completeness	It states what the skill covers (the 'what'), but there is no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it; per the rubric this caps completeness at 2.	2 / 3
Trigger Term Quality	'TypeScript' and 'JavaScript' are natural terms users say, with relevant domain keywords like 'performance optimization' and 'monorepo management', but common variations users actually say (e.g. 'type checking', 'tsconfig', 'types', 'linting', 'build') are missing and 'type-level programming' leans toward jargon, so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	'TypeScript and JavaScript expert' is a specific niche (above generic, so not 1), but it is broad and would overlap heavily with the sibling skills it itself names (typescript-build-expert, typescript-module-expert, typescript-type-expert) and lacks distinct triggers, so it is not 3.	2 / 3
	Total	8 / 12 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: 9bae718

Reviewed: 8 minutes 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.