app-builder
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
32
27%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 conveys the high-level purpose of the skill — orchestrating full-stack app creation — but lacks explicit trigger guidance ('Use when...'), concrete action details, and natural user-facing keywords. It reads more like an internal system description than a skill selector description, making it harder for Claude to reliably choose this skill at the right time.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user asks to build an app, create a project, scaffold a web application, or generate a full-stack codebase from scratch.'
Include more natural user-facing keywords such as 'build an app', 'create a website', 'new project', 'web app', 'API', 'frontend and backend'.
List more specific concrete actions, e.g., 'Generates project structure, configures build tools, sets up database schemas, creates API endpoints, and scaffolds frontend components.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (full-stack application building) and some actions (determines project type, selects tech stack, coordinates agents), but these are somewhat high-level and not deeply concrete — e.g., what kinds of applications, what tech stacks, what agents? | 2 / 3 |
Completeness | Describes what it does (creates full-stack applications, determines project type, etc.) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'when' is entirely absent, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'full-stack applications', 'natural language requests', 'tech stack', and 'project type', but misses many natural user phrases like 'build an app', 'create a website', 'scaffold a project', 'web app', 'backend', 'frontend', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'orchestrator' and 'coordinates agents' provide some distinctiveness, but 'creates full-stack applications' is broad enough to overlap with many coding, scaffolding, or project-generation skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions primarily as a table of contents rather than an actionable orchestration guide. While the navigation structure and template organization are well-presented, the skill lacks any concrete decision logic, executable steps, or validation checkpoints that an orchestrator skill critically needs. The usage example illustrates the concept but doesn't teach Claude how to actually perform the orchestration.
Suggestions
Add concrete decision logic for project type detection inline (e.g., keyword → project type mapping rules) rather than deferring everything to sub-files, so Claude has actionable guidance even without reading all references.
Include an explicit multi-step workflow with validation checkpoints, such as: detect project type → confirm with user → select template → scaffold → validate structure → coordinate agents, with clear criteria for each decision point.
Replace the vague usage example with a concrete, step-by-step walkthrough showing actual commands or tool calls Claude should make during orchestration.
Remove the generic 'When to Use' and 'Limitations' boilerplate sections that add no skill-specific value and waste tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good use of tables for navigation, but includes some unnecessary sections like 'When to Use' and 'Limitations' that are generic boilerplate adding no skill-specific value. The selective reading rule header is useful but slightly over-formatted. | 2 / 3 |
Actionability | The skill provides no executable code, no concrete commands, and no specific instructions for how to actually build an application. The usage example is a high-level description of a process rather than actionable steps. It's essentially a table of contents pointing to other files without giving Claude anything concrete to execute directly. | 1 / 3 |
Workflow Clarity | The usage example shows a numbered list but lacks any real workflow detail—no validation checkpoints, no error handling, no decision criteria for choosing project types or tech stacks, and no feedback loops. For an orchestrator that coordinates destructive/generative operations across multiple agents, the workflow is dangerously vague. | 1 / 3 |
Progressive Disclosure | The content has good structure with clear tables pointing to supporting files and templates with one-level-deep references. However, since no bundle files were provided, we cannot verify that referenced files exist. The SKILL.md itself is almost entirely navigation with very little substantive content at the top level, making it overly dependent on external files. | 2 / 3 |
Total | 6 / 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
cfced3a
- 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.