app-builder
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
68
Quality
52%
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 orchestrating application creation but lacks the explicit trigger guidance essential for skill selection. It uses appropriate third-person voice and mentions key concepts, but remains too abstract about specific capabilities and completely omits when Claude should choose this skill over others.
Suggestions
Add an explicit 'Use when...' clause with trigger phrases like 'build an app', 'create a new project', 'scaffold application', 'full-stack project from scratch'
Include specific examples of project types or tech stacks to make capabilities concrete (e.g., 'React/Node apps, Python web services, mobile backends')
Add natural user keywords like 'new app', 'start a project', 'build me a', 'create an application' that users would actually say
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (application building) and some actions (determines project type, selects tech stack, coordinates agents), but lacks concrete specifics about what types of applications, which tech stacks, or what coordination entails. | 2 / 3 |
Completeness | Describes what it does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has no 'when' component at all. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'full-stack applications' and 'natural language requests', but misses common user phrases like 'build an app', 'create a website', 'new project', 'scaffold', or specific framework names users might mention. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'orchestrator' and 'coordinates agents' provides some distinction, but 'application building' is broad and could overlap with skills for specific frameworks, frontend-only, backend-only, or individual component generation. | 2 / 3 |
Total | 7 / 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 organization and token efficiency, serving as a clean orchestration hub with excellent progressive disclosure through its content map and template references. However, it lacks concrete executable guidance and validation checkpoints that would be critical for coordinating multi-agent application builds, particularly around error recovery and verification between pipeline stages.
Suggestions
Add concrete commands or code snippets showing how to invoke each agent and verify their output before proceeding to the next stage
Include explicit validation checkpoints in the workflow (e.g., 'Verify schema before generating API routes', 'Run type-check before frontend build')
Add error handling guidance: what to do when an agent fails, how to rollback partial builds, or how to retry specific stages
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Uses tables for quick reference, no unnecessary explanations of concepts Claude knows. Every section serves a clear purpose with minimal prose. | 3 / 3 |
Actionability | Provides good structural guidance with clear file references and template links, but lacks executable code or concrete commands. The usage example shows a process flow but not actual implementation steps or commands to run. | 2 / 3 |
Workflow Clarity | The usage example shows a numbered sequence, but lacks validation checkpoints or feedback loops. For an orchestrator coordinating multiple agents on complex builds, there's no explicit error handling, rollback procedures, or verification steps between stages. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear content map, selective reading rule, and well-organized one-level-deep references to templates and detailed docs. Navigation is intuitive with tables indicating when to read each file. | 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
5c5ae21
- 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.