templates
Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.
80
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.
The description has a solid structure with an explicit 'Use when' clause and communicates the general purpose well. However, it lacks specificity about which tech stacks or frameworks are supported and misses common trigger terms users would naturally use like 'boilerplate,' 'bootstrap,' or 'starter project.' Adding concrete stack names and more natural trigger keywords would significantly improve skill selection accuracy.
Suggestions
List specific tech stacks or frameworks covered (e.g., 'React, Node.js, Python Flask, Django') instead of saying 'various tech stacks' to improve specificity and trigger term coverage.
Add common user trigger terms like 'bootstrap,' 'boilerplate,' 'starter project,' 'init,' or 'setup' to the description to improve matching with natural user language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (project scaffolding) and mentions '12 templates for various tech stacks,' but does not list specific concrete actions or name which tech stacks are covered. The phrase 'various tech stacks' is vague. | 2 / 3 |
Completeness | Clearly answers both 'what' (project scaffolding templates for new applications, 12 templates for various tech stacks) and 'when' (Use when creating new projects from scratch) with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'scaffolding,' 'templates,' 'new projects,' and 'new applications,' but misses common user phrases like 'bootstrap,' 'starter,' 'boilerplate,' 'init,' or specific stack names (e.g., React, Node, Python) that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The concept of 'project scaffolding' is fairly distinct, but 'various tech stacks' and 'new applications' are broad enough that it could overlap with code generation skills or individual framework-specific skills. Naming specific stacks would sharpen 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 is a well-structured routing/index skill that excels at progressive disclosure and conciseness. Its main weakness is that the skill itself contains almost no actionable content—it's entirely a pointer to other files—and the workflow lacks validation steps or fallback guidance. The 'When to Use' section at the bottom is a meaningless tautology that should be removed or replaced with actual criteria.
Suggestions
Add a brief validation/verification step to the workflow, e.g., 'After scaffolding, verify the project runs with the template's specified dev command'
Add fallback guidance for when no template matches the user's request (e.g., 'If no template matches, ask the user to clarify or scaffold manually')
Remove or replace the vacuous 'When to Use' section with meaningful trigger criteria or delete it entirely
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. The table format is an excellent use of tokens, providing maximum information density. The selective reading rule prevents unnecessary context loading. The only minor issue is the 'When to Use' section at the bottom which is a vacuous tautology, but it's only one line. | 3 / 3 |
Actionability | The skill provides clear navigation to templates and a simple 4-step usage flow, but the actual actionable content is entirely delegated to the TEMPLATE.md files. The skill itself doesn't contain any executable code or concrete scaffolding commands—it's purely a routing layer. The usage steps are somewhat vague ('Follow its tech stack and structure'). | 2 / 3 |
Workflow Clarity | The 4-step workflow is listed but lacks validation checkpoints. There's no guidance on what to do if no template matches, no verification step after scaffolding, and no error handling. For a scaffolding skill that creates entire project structures (a somewhat destructive/batch operation), some validation would be expected. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure. The skill is a clean overview with a well-organized table pointing to 12 separate template files, all one level deep. The selective reading rule explicitly instructs to load only the relevant template, which is ideal for token efficiency and navigation. | 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 | |
- Repository
- boisenoise/skills-collections
- Commit
636b862
- Reviewed
Table of Contents
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.