agentleFS
Sign inStart free
dabodamjandabodamjan/app-idea-to-spec/skills/build-plan/SKILL.md

build-plan

Skill0 starsChanged 5 months agoMITView on GitHub

Turn a finished app spec into an ordered, buildable plan that Claude Code can execute. Use when the spec is solid and the user is ready to start building the actual app.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. shawnclybor/clybor-claude-tooling★ 6same name
    2. trevorbyrum/claude-skills-suite★ 1same name
    3. korcekj/skills★ 0same name
    4. myusernameiskey/Claude_skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Project setup: Create the project for the chosen platform (Swift and SwiftUI, Expo, Flutter, etc.), the folder structure, dependencies, and …

    line 18
  2. Distinctive:

    Supporting screens: Only the MVP features from the spec, in priority order.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

app-idea-to-spec: build-plan

You are turning a app-idea-to-spec spec into a build plan that Claude Code (or any capable coding agent) can execute. This is the handoff from "what to build" to "build it."

How to run this

  1. Read the spec (default app-spec.md). If it is missing, point them to /app-idea-to-spec:new-spec. If it is clearly under-specified (no data model, no screens, no platform decision), point them to /app-idea-to-spec:refine-spec first. A vague spec produces a vague plan.

  2. Produce an ordered, phased build plan. Order matters: each phase should leave the app in a runnable state. A sensible default order, adapted to the spec:

    1. Project setup. Create the project for the chosen platform (Swift and SwiftUI, Expo, Flutter, etc.), the folder structure, dependencies, and any chosen SDKs (RevenueCat, Firebase) installed but not yet wired.
    2. Data layer. The data model and storage from the spec (SwiftData, Core Data, local, or a backend), with the main entities and relationships.
    3. Core loop. The screens and navigation that deliver the one core loop, end to end, with real data. Nothing else yet.
    4. Supporting screens. Only the MVP features from the spec, in priority order.
    5. Monetization. The paywall and purchase flow, if the spec has one. Wire up StoreKit 2 or RevenueCat per the spec.
    6. Store readiness. The blockers from the spec: account deletion if there are accounts, a privacy manifest if there are third-party SDKs, a privacy policy, an app icon and screenshots, and a working demo path for review.
  3. For each phase, write: the goal, the concrete tasks, and what "done" looks like (something the user can run and see). Keep tasks specific to this app, using the real screen names, entities, and decisions from the spec. Reference ${CLAUDE_PLUGIN_ROOT}/knowledge/ docs where a phase depends on a mobile-specific detail.
  4. Keep the cut list visible. Restate what the spec deliberately left out, so the build does not quietly grow it back.
  5. Write the plan into the spec's "Build handoff" section, or to a separate build-plan.md if the user prefers. Then tell them how to start: open the plan in Claude Code and build phase by phase, checking each phase runs before moving on.

Tone

Practical and concrete. The output is an execution plan, not advice. Order things so the app is runnable as early and as often as possible.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free