Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.
80
Quality
70%
Does it follow best practices?
Impact
100%
1.35xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-app-builder/templates/SKILL.mdQuality
Discovery
67%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 has good structure with an explicit 'Use when' clause and covers the basics of what the skill does. However, it lacks specificity about the concrete actions and the 12 templates mentioned, and could benefit from more natural trigger terms users would actually say when needing project scaffolding.
Suggestions
List specific tech stacks covered (e.g., 'React, Node.js, Python Flask, Django') to improve specificity and distinctiveness
Add more natural trigger terms users would say, such as 'bootstrap', 'starter project', 'boilerplate', 'init', or 'setup new app'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (project scaffolding) and mentions templates, but doesn't list specific concrete actions beyond 'creating new projects'. The mention of '12 templates for various tech stacks' hints at capabilities but doesn't specify what those stacks are. | 2 / 3 |
Completeness | Clearly answers both what (project scaffolding templates for new applications, contains 12 templates) and when (Use when creating new projects from scratch) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'scaffolding', 'templates', 'new projects', 'new applications', and 'tech stacks', but misses common variations users might say like 'bootstrap', 'starter', 'boilerplate', 'init', or specific stack names. | 2 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to project scaffolding/templates, but 'various tech stacks' is vague and could overlap with other code generation or project setup skills. Specifying which stacks would improve distinctiveness. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at token efficiency and progressive disclosure with a well-organized routing table to 12 templates. However, it lacks concrete actionable guidance beyond template selection—no example commands, no validation steps, and the 'When to Use' section is a meaningless placeholder that adds no value.
Suggestions
Add a concrete example showing the full workflow: user request → template selection → actual scaffolding commands to run
Include validation steps like 'verify dependencies installed' or 'run initial build to confirm setup'
Remove or replace the 'When to Use' section which currently contains no useful information
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations, just a clear table mapping project types to templates with minimal but sufficient context. | 3 / 3 |
Actionability | Provides clear template selection guidance but lacks concrete examples of what to do after selecting a template. The 4-step usage is high-level without showing actual commands or code. | 2 / 3 |
Workflow Clarity | The 4-step workflow is present but minimal. No validation checkpoints or error handling guidance. For a scaffolding skill, missing steps like 'verify project structure' or 'run initial setup commands'. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear one-level-deep references to 12 template files. The selective reading rule explicitly tells Claude to read only the relevant template, preventing unnecessary context loading. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
5c5ae21
Table of Contents
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.