javascript-typescript-typescript-scaffold

You are a TypeScript project architecture expert specializing in scaffolding production-ready Node.js and frontend applications. Generate complete project structures with modern tooling (pnpm, Vite, N

Quality

59%

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 ./skills/javascript-typescript-typescript-scaffold/SKILL.md

Quality

Content

65%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, executable scaffolding commands and complete configs, but it is weighed down by inlined template dumps that belong in reference files, a repeated intro paragraph, and a total absence of validation checkpoints in its generation workflow.

Suggestions

Move the per-project-type package.json/tsconfig/vite templates into reference files (e.g. references/nextjs.md, references/nodejs-api.md) and link to them one level deep, keeping only a concise overview in SKILL.md.

Add validation checkpoints to the workflow, e.g. run `pnpm type-check` and `pnpm test` after generation and only report success when they pass.

Remove the verbatim repeat of the frontmatter description at the top of the body to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basic concepts, but it repeats the frontmatter description paragraph verbatim at the top and inlines four full package.json/tsconfig/vite config dumps, which pads the context budget; not a level above because it is largely actionable rather than explanatory.	3 / 5
Actionability	It provides fully executable, copy-paste-ready commands ("pnpm create next-app@latest . --typescript --tailwind --app --src-dir"), complete config files, directory trees, and sample app code covering the common project types.	5 / 5
Workflow Clarity	A clear numbered sequence exists (Analyze → Initialize → Generate structure → Configure tools) but there are no validation or verification checkpoints for what is effectively a batch file-generation operation, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections are well organized with clear headers, but the skill is ~360 lines with full per-project-type config templates inlined directly in SKILL.md and no bundle files or one-level-deep references to split that material out, fitting the "content that should be separate is inline" anchor.	3 / 5
	Total	14 / 20 Passed

Description

53%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, specific niche and concrete actions but is truncated mid-sentence, uses second-person voice against the rubric, and lacks any explicit "Use when..." trigger. Fixing the truncation, switching to third person, and adding a trigger clause would lift the completeness and specificity caps.

Suggestions

Complete the truncated description ("Vite, N..." → "Vite, Next.js), ...") so the tooling list and any trigger clause are not cut off.

Rewrite in third person (e.g. "Scaffolds production-ready TypeScript projects...") instead of "You are a..." to avoid the specificity penalty.

Add an explicit "Use when..." clause naming concrete triggers (e.g. "Use when scaffolding a new TypeScript project, initializing a Node.js API, or creating a React+Vite app").

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete actions plus specific tooling ("scaffolding production-ready Node.js and frontend applications", "Generate complete project structures with modern tooling (pnpm, Vite"), which would anchor at 4, but it is written in second person ("You are a TypeScript project architecture expert") and is truncated mid-word ("Vite, N"), reducing specificity by one per the voice penalty.	3 / 5
Completeness	It has a clear "what" (scaffolds production-ready TS projects with modern tooling) but no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	It includes some natural terms users would say ("TypeScript project", "scaffolding", "Node.js", "frontend") but misses common variations and synonyms ("set up", "initialize", "boilerplate", "starter template") and the keyword list is cut off by the truncation.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct ("TypeScript project architecture expert specializing in scaffolding production-ready Node.js and frontend applications") with only minor overlap risk against generic scaffolding or per-framework setup skills.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/javascript-typescript-typescript-scaffold/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.