app-builder
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
54
31%
Does it follow best practices?
Impact
98%
1.55xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-app-builder/SKILL.mdQuality
Discovery
32%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 communicates the high-level purpose of the skill (building full-stack apps) but reads more like an internal system description than a skill selection guide. It lacks explicit trigger guidance ('Use when...'), misses common user-facing keywords, and uses internal jargon like 'orchestrator' and 'coordinates agents' that users wouldn't naturally say.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases like 'build an app', 'create a web application', 'new project', 'scaffold a full-stack app', 'generate an application from scratch'.
Replace internal jargon ('orchestrator', 'coordinates agents') with user-facing language describing concrete outcomes, e.g., 'generates project structure, sets up frontend and backend, configures build tools'.
Include specific technology or project type examples (e.g., 'React + Node.js apps, Next.js projects, REST API backends') to improve both trigger term quality and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (full-stack application building) and some actions (determines project type, selects tech stack, coordinates agents), but the actions are more about orchestration mechanics than concrete user-facing capabilities. 'Creates full-stack applications from natural language requests' is somewhat specific but lacks detail on what kinds of applications or what the output looks like. | 2 / 3 |
Completeness | Describes what it does (creates full-stack applications, determines project type, selects tech stack, coordinates agents) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'when' is not even implied clearly, so this scores at 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'full-stack applications', 'tech stack', and 'natural language requests', but misses many natural user phrases like 'build an app', 'create a website', 'web app', 'project scaffold', 'new project', 'generate application'. The term 'orchestrator' and 'coordinates agents' are internal/technical jargon unlikely to appear in user requests. | 2 / 3 |
Distinctiveness Conflict Risk | The 'full-stack applications' and 'orchestrator' framing provides some distinctiveness, but 'creates applications from natural language requests' is broad enough to overlap with many code generation or project scaffolding skills. Without clear boundaries on scope, it could conflict with individual frontend, backend, or code generation skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels as a navigation hub with well-structured tables and clear file references, but fails as an actionable orchestrator. It contains almost no concrete guidance on how to actually perform the app-building process—no decision logic, no executable steps, no validation checkpoints. It reads more like a table of contents than a skill.
Suggestions
Add a concrete decision workflow with specific criteria for selecting project type and tech stack (e.g., 'If request mentions auth/payments → nextjs-saas; if static content → nextjs-static')
Include the actual orchestration steps as executable instructions: how to invoke agents, in what order, with what inputs, and how to validate outputs between steps
Add validation checkpoints to the workflow (e.g., 'After scaffolding, verify directory structure matches template; after agent coordination, verify all planned endpoints exist')
Replace the illustrative usage example with a concrete step-by-step procedure that Claude can follow, including specific commands or tool invocations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with good use of tables for navigation, but includes some unnecessary elements like the 'When to Use' section at the bottom which adds nothing, and the emoji headers are decorative padding. The 'Selective Reading Rule' bold callout is reasonable but slightly verbose. | 2 / 3 |
Actionability | The skill provides no concrete, executable guidance. There are no commands, no code snippets, no specific steps to follow. The 'Usage Example' is a high-level description of a process, not actionable instructions. Everything is delegated to other files with no inline substance. | 1 / 3 |
Workflow Clarity | The usage example shows a numbered list but it's purely illustrative with no actual instructions on how to execute each step. There are no validation checkpoints, no error handling, no decision criteria for choosing between templates or tech stacks. The orchestration workflow is entirely absent from this file. | 1 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure with well-organized tables pointing to specific files, clear descriptions of when to read each file, and one-level-deep references. The content map, templates table, and related agents table provide clear navigation. | 3 / 3 |
Total | 7 / 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.