Name: app-builder
Rating: 51.2 (1 reviews)
Author: vudovn

app-builder

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

Quality

58%

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 ./.agents/skills/app-builder/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

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

The body is a well-organized, token-efficient overview that clearly maps files, templates, and agents, but it functions as a navigation hub whose referenced bundle files are missing, and its worked workflow lacks any validation checkpoints for a batch scaffolding operation.

Suggestions

Ship the referenced bundle files (project-detection.md, tech-stack.md, templates/*/TEMPLATE.md, etc.) so the progressive-disclosure structure resolves to real content, or inline the essential guidance directly.

Add explicit validation/verification checkpoints to the usage workflow (e.g., verify scaffold compiles, confirm dependencies installed) to lift workflow_clarity above the batch-operation cap of 3.

Replace the non-executable process outline with at least one concrete, runnable command or file-creation step to improve actionability.

Dimension	Reasoning	Score
Conciseness	The body is lean — dense tables for the content map, templates, and agents plus a compact worked example, with no padding or explanation of concepts Claude already knows; not a 5 only because emoji headers and the verbose 'Selective Reading Rule' framing add minor non-essential tokens.	4 / 5
Actionability	Guidance is mostly 'read file X when Y' plus an illustrative process outline rather than executable code or commands, and the referenced files that would carry the actual how-to do not exist in the bundle; fits 'some concrete guidance but incomplete'; not a 4 because nothing is copy-paste executable.	3 / 5
Workflow Clarity	The usage example gives a clear 6-step sequence (detect type → stack → plan → coordinate → report → preview), but there are no validation or verification checkpoints for what is a batch scaffolding operation, so per the destructive/batch cap it cannot exceed 3; not a 4 because checkpoints are entirely absent.	3 / 5
Progressive Disclosure	The content map is well signaled (File \| Description \| When to Read) with one-level-deep references, but none of the referenced bundle files (project-detection.md, tech-stack.md, agent-coordination.md, scaffolding.md, feature-building.md, templates/*/TEMPLATE.md) actually exist in the skill bundle, so the disclosure structure does not resolve to real content; sits between good-structure (4) and broken navigation.	3 / 5
	Total	13 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 a clear, third-person 'what' with several concrete actions, but omits any explicit 'when to use' trigger guidance in the description field, capping completeness and leaving natural user-facing trigger terms thin.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g., 'Use when a user asks to build, scaffold, or create a new full-stack app from scratch') to lift completeness above 3.

Include natural user phrasings as triggers ('build an app', 'make a web application', 'scaffold a project') rather than only technical terms like 'natural language requests'.

Tighten 'coordinates agents' to a concrete deliverable to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Quotes several concrete actions — "Creates full-stack applications from natural language requests", "Determines project type, selects tech stack, coordinates agents" — matching the 'lists several specific actions; minor gaps' anchor; not a 5 because the actions stay somewhat high-level (no concrete artifacts or mechanisms).	4 / 5
Completeness	The 'what' is clear but the description field has no explicit 'Use when...' clause, so per the missing-trigger-guidance cap it sits at the 'clear what, when missing or weakly implied' anchor; not a 4 because trigger guidance is entirely absent from the description.	3 / 5
Trigger Term Quality	Terms like "full-stack applications", "natural language requests", and "tech stack" are relevant but skew technical and miss the natural phrasings a user would actually say ("build me an app", "make a web app"), fitting 'some relevant keywords but missing common variations'; not a 4 due to thin natural-term coverage.	3 / 5
Distinctiveness Conflict Risk	The app-building-orchestrator niche with "selects tech stack, coordinates agents" is mostly distinct from other skills with only minor overlap risk against general coding skills; not a 5 because "full-stack applications" still overlaps somewhat with broader build/code skills.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 13 missing, 13 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/app-builder/SKILL.md
Commit: 211561c

Reviewed: 15 days 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.