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, validat
npx skills add wondelai/skills --skill create-app --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Instructs the agent to lead a user through ten sequential phases to turn a raw app idea into a validated MVP, recording decisions and artifacts in docs/ and resuming across sessions. It orchestrates multiple phase-specific skills (lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way, software-design-philosophy) and manages phase gates, trackers, and artifacts per phase.
How it works
- Resumes an existing journey by reading docs/CREATE-APP-PLAN.md and artifacts in the Journey Map, summarizing state, and selecting an entry point.
- On first run, performs Intake and creates docs/CREATE-APP-PLAN.md with phased statuses (pending, in-progress, awaiting-evidence, done, deferred, skipped).
- For each phase, announces the phase purpose, the decision it forces, the artifact produced, and rough effort; offers proceed, skip, or defer; marks the phase as in-progress when proceeding.
- Invokes the phase's skill by its slug (e.g., lean-startup, design-sprint, clean-architecture). If unavailable, suggests installing via
npx skills add wondelai/skills/<slug> --global. - Records decisions under "Decide with the user" and updates the tracker with Key Decisions.
- Presents a draft artifact for sign-off before extending docs/ files and updating the tracker to done upon approval.
- Ensures artifacts live in docs/ as UPPERCASE files, created from full templates and extended as phases progress.
When to use it
- Use when the user wants to build a new app, validate an idea before coding, architect an MVP for sustainable cadence, or when the user says they want to build the right way. It also notes alternative journeys for related tasks (improve-app, grow-app, create-website, design-code-architecture).
What it can touch
- Invokes phase-specific skills by slug and reads/writes docs/CREATE-APP-PLAN.md and phase artifacts under docs/ (e.g., PRODUCT.md, ARCHITECTURE.md, DESIGN.md, EXPERIMENTS.md, TESTING.md, etc.).
Caveats
- The journey emphasizes recording decisions and artifacts; it may produce phases with no code in early steps. It defers to user validation before progressing to implementation.
- The workflow relies on the availability of phase skills; if a phase skill is unavailable, a fallback method is used and noted.
# Create an App Take a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence — without over-building for scale you have not earned, or writing a prototype that calcifies into a rewrite. This journey runs ten phases: it asks before every decision and records each choice in `docs/` so you can stop and resume across sessions. The early phases often produce no code at all; once an experiment greenlights building, the engineering phases build the real thing well. ## Core Principle **Validate fast while keeping options open: make the expensive-to-reverse decisions early and defer everything cheap.** Spend scarce early effort on the few things that compound — the riskiest assumption, the dependency boundaries, the domain language — and aggressively avoid waste everywhere else. This skill sequences the phases, asks the questions, and records the decisions; the constituent skills carry the method. Invoke them rather than improvising their frameworks. ## Journey Map | Phase | Skill | Question it answers | Artifact | |---|---|---|---| | 1 | lean-startup | Is the riskiest assumption true, and what is the MVP? | Creates docs/PRODUCT.md + docs/EXPERIM
- Core Principle
- Journey Map
- Operating Rules
- Intake
- Phases
- Phase 1 — Validate the riskiest assumption (lean-startup)
- Phase 2 — De-risk the core experience (design-sprint)
- Phase 3 — Draw the boundaries (clean-architecture)
- Phase 4 — Model the domain (domain-driven-design)
- Phase 5 — Write code to be read (clean-code)
- Phase 6 — Install the meta-disciplines (pragmatic-programmer)
- Phase 7 — Size it honestly (system-design)
- Phase 8 — Make it feel native (ios-hig-design) — iOS only
- Phase 9 — Ship on a cadence (37signals-way)
What does the create-app skill do?
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, validat
How do I install it?
Run `npx skills add wondelai/skills --skill create-app --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From wondelai/skills, a repository with 1,835 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.