Name: app-builder
Rating: 50.4 (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

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

53%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 lean and well-organized as an overview, with a clear content map and template index, but it is undermined by references to bundle files that do not actually exist and by the absence of explicit validation checkpoints in its multi-step scaffolding workflow. Progressive disclosure and workflow clarity are the limiting dimensions.

Suggestions

Ship the referenced bundle files (project-detection.md, tech-stack.md, agent-coordination.md, scaffolding.md, feature-building.md, and the 13 templates/*/TEMPLATE.md) so the content-map links resolve — without them the skill's navigation is broken.

Add an explicit validation/verification checkpoint to the workflow (e.g. 'After scaffolding, run the project's build/lint and confirm it starts before reporting done') so the batch scaffolding operation has a feedback loop.

Either inline a minimal executable snippet per template row or ensure each TEMPLATE.md contains copy-paste-ready scaffolding commands, so the body's actionability does not depend entirely on missing files.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely compact tables (content map, 13 templates, related agents) with no padding or explanation of concepts Claude already knows, fitting 'efficient; minor instances of over-explanation'; the opening blockquote lightly restates the description, keeping it just below the lean 5.	4 / 5
Actionability	It gives concrete direction (a when-to-read map, a template selection table, a worked Instagram-clone example) but no executable code or commands — the real executable detail lives in referenced files that are not present in the bundle, leaving key gaps that fit the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	The Usage Example lays out a clear 6-step sequence (project type → tech stack → plan → coordinate agents → report → preview), but there is no explicit validation/verification checkpoint for a large batch scaffolding operation, and the rubric caps such workflows at 3.	3 / 5
Progressive Disclosure	Navigation is well-signaled (a content map and template table pointing to project-detection.md, tech-stack.md, templates/*/TEMPLATE.md), but none of those referenced files exist in references/, scripts/, or assets/ — the bundle is empty, so the one-level-deep references are dangling and navigation is non-functional, fitting the 'references are buried / minimal structure' anchor better than the 3.	2 / 5
	Total	12 / 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 is third-person, concrete, and names a clear niche, but it omits any explicit 'Use when...' trigger guidance (delegated to when_to_use) and lacks common user phrasings like 'build an app' or 'scaffold a project'. Specificity and distinctiveness are solid; trigger-term quality and completeness are the weak spots.

Suggestions

Fold the when_to_use trigger phrasing into the description so it explicitly answers 'when should Claude use it' (e.g. append 'Use when creating a new full-stack app from scratch, picking a tech stack, or scaffolding project structure').

Add natural user phrasings and synonyms — 'build a web app', 'create an app', 'scaffold a project', 'full-stack'/'web app' — so the description matches terms users actually say.

Keep the third-person voice but consider naming one or two more concrete actions (e.g. 'scaffolds project structure', 'plans feature breakdown') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (full-stack applications) and several concrete actions — 'Creates full-stack applications from natural language requests', 'Determines project type', 'selects tech stack', 'coordinates agents' — with only minor coverage gaps, matching the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	The description field gives a clear 'what' but contains no 'Use when...' / trigger guidance — the when-clause lives only in the separate when_to_use field — so per the rubric a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ('full-stack applications', 'natural language requests', 'tech stack') but common natural phrasings users actually say ('build a web app', 'create an app', 'scaffold a project') and synonyms are missing, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Main application building orchestrator... Creates full-stack applications from natural language requests' carves a clear niche with minimal overlap risk, matching the 'mostly distinct; minor overlap risk' anchor; not a 5 because the triggers are not as sharply distinguished as the PDF-style example.	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: 549ba3d

Reviewed: 2 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.