Name: app-builder
Rating: 54.400000000000006 (1 reviews)
Author: sickn33

app-builder

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/app-builder/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and token-efficient as an orchestrator index, but its value collapses because all referenced detail files are missing from the bundle and the workflow lacks validation checkpoints. Supplying the referenced files and adding verification steps would raise the weaker dimensions.

Suggestions

Add the missing bundle files (project-detection.md, tech-stack.md, agent-coordination.md, scaffolding.md, feature-building.md, and the 12 template TEMPLATE.md files) so the well-signaled references actually resolve.

Insert explicit validation checkpoints into the workflow (e.g. verify the scaffold builds / runs lint / passes a smoke test after scaffolding, and re-validate before starting the preview).

Replace the generic 'When to Use' filler with concrete routing guidance, or fold it into the existing content map to keep every section actionable.

Dimension	Reasoning	Score
Conciseness	The body is lean and table-driven (content map, templates, related agents) and does not explain concepts Claude already knows; only minor generic boilerplate in 'When to Use'/'Limitations' keeps it from being a clear 3-and-above concern, fitting the lean/efficient anchor.	3 / 3
Actionability	Routing tables are concrete ('Starting new project → read project-detection.md') but every actionable detail is delegated to referenced files that do not exist in the bundle, leaving the guidance incomplete and missing key details.	2 / 3
Workflow Clarity	The usage example gives a clear 6-step sequence, but there are no validation checkpoints or feedback loops for a batch file-generating operation, so per the destructive/batch guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	The overview/index structure with one-level-deep references is well designed, but scoring against the actual bundle shows it is empty — none of the ~18 referenced files (content-map files and 12 templates) exist, so the disclosure does not function.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 states concrete capabilities clearly but omits any explicit 'Use when…' trigger guidance, weakening trigger-term quality, completeness, and distinctiveness. Adding natural-language triggers would lift three of the four dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to build, scaffold, or generate a full-stack app, web service, SaaS, or mobile/desktop app from a natural-language request.'

Add natural user-facing terms ('build me an app', 'make a SaaS', 'scaffold a project', 'create a web/mobile app') alongside the technical vocabulary to improve trigger-term quality.

Sharpen distinctiveness by naming the coordination/orchestration scope so it does not collide with generic coding skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creates full-stack applications', 'Determines project type, selects tech stack, coordinates agents' — matching the anchor for several specific concrete actions rather than the single-domain anchor below.	3 / 3
Completeness	It clearly states what the skill does but provides no explicit when/trigger guidance, so per the missing-'Use when' guideline completeness is capped at 2 rather than reaching the explicit-trigger anchor.	2 / 3
Trigger Term Quality	Terms like 'full-stack applications' and 'natural language requests' are relevant but technical, with no 'Use when…' clause or natural user phrasing such as 'build me an app' or 'make a SaaS', so coverage of natural terms is partial.	2 / 3
Distinctiveness Conflict Risk	The 'full-stack applications from natural language requests' niche is fairly specific but lacks distinct trigger language and could still overlap with general coding or app-generation skills.	2 / 3
	Total	9 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 12 missing, 12 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/app-builder/SKILL.md
Commit: b7f833d

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.