Name: create-app
Rating: 77.60000000000001 (1 reviews)
Author: wondelai

create-app

Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way, software-design-philosophy - asking the user questions at every decision point and recording results in the project docs/ folder (PRODUCT.md, ARCHITECTURE.md, EXPERIMENTS.md, CREATE-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to build a new app, validate an idea before writing code, architect an MVP that will not need a rewrite, or says 'help me build my app the right way'. App already exists: use improve-app or grow-app. Business idea not yet validated: run create-business first. Marketing site only: use create-website. Architecture-only question: design-code-architecture. For one framework in isolation, invoke that skill directly.

Quality

97%

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

The canonical home for this skill is create-app in wondelai/skills

Quality

Content

92%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.

A well-structured orchestrator body that sequences ten phases with concrete artifacts, explicit validation checkpoints, and a real one-level-deep reference for templates. Its only weakness is mild over-explanation in the per-phase methodology fallbacks.

Suggestions

Tighten the per-phase Brief fallbacks: distill each to the few non-obvious rules Claude would not already know, since the named constituent skills are expected to carry the full method.

Consider moving the longer methodology fallbacks (e.g. Phase 7 capacity math, Phase 8 HIG detail) into references/ so the SKILL.md body stays a lean overview.

Confirm the Briefs are explicitly framed as fallback-only so it is clear they are the minimum viable method, not the primary path.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no generic concept padding, but the per-phase Brief fallbacks re-summarize methodology Claude largely already knows (lean-startup, clean-architecture, DDD, HIG, 37signals) at a length that could be trimmed without losing the fallback value.	4 / 5
Actionability	Highly concrete and actionable for an instruction-only skill: every phase specifies exact docs files, section headings (e.g. "Create docs/PRODUCT.md with `## Vision` and `## MVP Definition`"), tracker statuses, decision points, and a "Done when" criterion.	5 / 5
Workflow Clarity	Clear ten-phase sequence (Journey Map table plus numbered phases) with explicit validation checkpoints — sign-off before writing artifacts, the `awaiting-evidence` feedback loop, and a closing exit checklist — providing the feedback loops the rubric rewards.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with a single well-signaled, one-level-deep reference ([references/artifact-templates.md]) that actually exists in the bundle, with content appropriately split out of the main file.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

A strong, third-person description that clearly states what the skill does, when to use it via concrete trigger phrases, and how it differs from sibling skills. It is comprehensive without padding and names specific artifacts and constituent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Orchestrates ten skills phase by phase", "asking the user questions at every decision point", "recording results in the project docs/ folder" — and names concrete artifacts (PRODUCT.md, ARCHITECTURE.md, EXPERIMENTS.md, CREATE-APP-PLAN.md), giving comprehensive coverage of what it does.	5 / 5
Completeness	Explicitly answers both what ("Guided journey from a raw app idea to a validated, cleanly architected first version", orchestrating ten skills, recording results) and when ("Use when the user wants to build a new app, validate an idea before writing code, architect an MVP...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers users would actually say — "build a new app", "validate an idea before writing code", "architect an MVP that will not need a rewrite", and the direct quote "help me build my app the right way" — plus synonym-style routing variants.	5 / 5
Distinctiveness Conflict Risk	Clear niche (new-app creation via a ten-phase journey) with explicit sibling-skill disambiguation — "App already exists: use improve-app or grow-app", "Business idea not yet validated: run create-business first", "Marketing site only: use create-website", "Architecture-only question: design-code-architecture" — minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wondelai/skills
Path: create-app/SKILL.md
Commit: c172996

Reviewed: 13 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.