typescript

Type-safe development patterns for JARVIS AI Assistant

Install with Tessl CLI

npx tessl i github:martinholovsky/claude-skills-generator --skill typescript

What are skills?

Review — 46%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 16 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is severely underdeveloped and would perform poorly in skill selection. It lacks concrete actions, natural trigger terms, and any guidance on when to use it. The only distinguishing element is the project name 'JARVIS', but this alone is insufficient for effective skill matching.

Suggestions

Add specific concrete actions this skill enables, e.g., 'Enforces TypeScript type safety, generates typed interfaces, validates API contracts, implements error handling patterns'

Include a 'Use when...' clause with natural trigger terms, e.g., 'Use when working on JARVIS codebase, implementing TypeScript types, or when the user mentions type safety, interfaces, or JARVIS development'

Add common user-facing keywords like 'TypeScript', 'types', 'interfaces', 'type checking', 'strongly typed' that users would naturally mention

Dimension	Reasoning	Score
Specificity	The description uses vague language ('Type-safe development patterns') without listing any concrete actions. It doesn't specify what actions Claude can perform - no verbs describing capabilities like 'validates', 'generates', or 'enforces'.	1 / 3
Completeness	Missing both 'what' and 'when'. The description doesn't explain what specific tasks this skill performs, nor does it include any 'Use when...' clause or trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Contains technical jargon ('Type-safe development patterns') and a project-specific name ('JARVIS AI Assistant') that users are unlikely to naturally say. Missing common terms users might use like 'TypeScript', 'types', 'coding', or specific development tasks.	1 / 3
Distinctiveness Conflict Risk	The mention of 'JARVIS AI Assistant' provides some specificity to a particular project, which reduces conflict with generic coding skills. However, 'development patterns' is still vague enough to potentially overlap with other coding or architecture skills.	2 / 3
	Total	5 / 12 Passed

Implementation

85%

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

This is a strong, well-structured TypeScript skill with excellent actionability through complete, executable code examples and clear TDD workflows with validation checkpoints. The main weakness is verbosity - some sections explain concepts Claude already knows (branded types, discriminated unions basics) rather than just showing the patterns. The progressive disclosure and workflow clarity are excellent.

Suggestions

Remove explanatory prose like 'Type-safe state machine' comments and section introductions - let the code examples speak for themselves

Consolidate the 'Common Mistakes' section by showing only the ✅ patterns with brief inline comments, rather than ❌/✅ pairs with explanations

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but includes some unnecessary explanations Claude would already know (e.g., explaining what branded types are, basic TypeScript concepts). The content could be tightened by removing explanatory prose and keeping only the patterns and code examples.	2 / 3
Actionability	Excellent executable code examples throughout - branded types, Zod schemas, type guards, and utility types are all copy-paste ready. The TDD workflow includes specific commands and complete test examples.	3 / 3
Workflow Clarity	Clear multi-step TDD workflow with explicit verification commands. The pre-deployment checklist provides excellent validation checkpoints across three phases. Step 4 includes specific verification commands for tests, linting, and type checking.	3 / 3
Progressive Disclosure	Well-organized with clear sections progressing from overview to implementation patterns to checklists. References to advanced-patterns.md and security-examples.md are clearly signaled at the end, maintaining one-level-deep navigation.	3 / 3
	Total	11 / 12 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (501 lines); consider splitting into references/ and linking	Warning
description_trigger_hint	Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...')	Warning
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	11 / 16 Passed

Reviewed: 22 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.