agentleFS
dabodamjandabodamjan/app-idea-to-spec/CLAUDE.md

app-idea-to-spec

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

Purpose: an open-source Claude Code plugin that turns a mobile app idea into a build-ready spec, which Claude Code then builds from. Spec-driven development, made for mobile. app-idea-to-spec is a plugin made of markdown and JSON. There is no build and no runtime. The commands are Skills in skills/, the spec structure is templates/spec-template.md, and the encoded mobile knowledge is in knowledge/. Users install it with /plugin marketplace add dabodamjan/app-idea-to-spec or run it locally with claude --plugin-dir ./app-idea-to-spec. Then run…

The file

We split this CLAUDE.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Cite current facts: No invented numbers, no stale advice as current.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “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
CLAUDE.md

app-idea-to-spec

Purpose: an open-source Claude Code plugin that turns a mobile app idea into a build-ready spec, which Claude Code then builds from. Spec-driven development, made for mobile.

Operating model

app-idea-to-spec is a plugin made of markdown and JSON. There is no build and no runtime. The commands are Skills in skills/, the spec structure is templates/spec-template.md, and the encoded mobile knowledge is in knowledge/. Users install it with /plugin marketplace add dabodamjan/app-idea-to-spec or run it locally with claude --plugin-dir ./app-idea-to-spec.

Read first

  • README.md: what it is and how users install and run it
  • docs/architecture.md: how the pieces fit
  • docs/decisions/: why it is built this way
  • knowledge/: the mobile playbook the skills rely on

Hard rules for this repo

  • No em dashes in any file. Use periods, commas, or restructure. House style, and it matches the author's voice.
  • No emojis in docs or knowledge, unless there is a functional reason.
  • Keep it mobile-specific. Generic spec-driven tooling already exists. app-idea-to-spec earns its place through App Store, StoreKit, SwiftData, ASO, and the rest. Do not dilute that into generic PRD advice.
  • Cut before you add. New spec sections and commands have a high bar. The tool models scope discipline, so the repo should too.
  • Cite current facts. No invented numbers, no stale advice as current. If something is unsettled, say so in the doc. The knowledge/ docs are the part most likely to go stale, so date facts and link primary sources.
  • Public repo hygiene. This is public. No personal or business content beyond the author's public brand (name, dabo.dev, shipped apps). No personal emails in manifests.

Testing locally

claude --plugin-dir .

Then run /app-idea-to-spec:new-spec and walk a sample idea through to a spec.

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.