agentleFS
librosdeialibrosdeia/builder-method-claude-plugin/skills/idea/SKILL.md

idea

Skill0 starsChanged 5 days agoMITView on GitHub

Phase 1 of the Builder Method — turn a vague product idea into a concrete one, written to builder/01-idea.md. Use when someone has an idea for an app, website or tool and wants to shape it before building, or runs /builder:idea.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use weekly-retro, decompose and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Joshua-PalamuttamSkill

    weekly-retro

    End-of-week retrospective. Compares planned vs actual, updates calibration data, and surfaces estimation patterns. Run Friday afternoons.

    Also in 3 projects that use this

  • matt-k-wongSkill

    decompose

    Learn to decompose complex problems before building real agents. Better answers today. Ready for orchestration tomorrow. Breaks messy tasks into clear DAG structures with explicit dependencies, parallel branches, and synthesis logic. Improves Claude outputs by enforcing topological order and catching contradictions. Teaches the mental model for LangGraph, CrewAI, n8n, and Sub-Agents. Type "decompose: [goal]" or "decompose preview: [goal]" to start. Zero experience required.

    Also in 3 projects that use this

  • seongjaeryuSkill

    save

    Complete and save your current thinking to Bindly

    Also in 3 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 5 projects that use this

  • GoogleSkill

    to-issues

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

    Also in 3 projects that use this

  • GoogleSkill

    to-prd

    Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    If builder/state.json doesn't exist, set the project up first, as the start skill does (${CLAUDE_PLUGIN_ROOT}/skills/start/SKILL.md, steps …

    line 17
  2. Very specific:

    If the file already exists, follow "Existing outputs" in state-rules.md (revise it, never overwrite the user's edits).

    line 41
  3. Very specific:

    when approved (or if the user asked you to proceed with defaults): set review: reviewed, mark the step and the phase done, set currentPhase …

    line 51

“Common” is measured: kept by at least 6 in 10 of the 25 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

Phase 1 · Idea

Goal: turn a vague idea, with all the user's requirements, into a concrete idea to work with. Input: whatever the user has (the problem, notes, documents, links). Output: builder/01-idea.md.

Read and follow:

  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/tone.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/state-rules.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/idea/references/prompts.md (the method's original intent)

If builder/state.json doesn't exist, set the project up first, as the start skill does (${CLAUDE_PLUGIN_ROOT}/skills/start/SKILL.md, steps 2–3), then come back here.

Never write code or start building in this phase.

Step 1 · explore

Set phases.idea.status to in_progress.

Help the user think, don't interrogate them. Find out, a little at a time:

  • what problem they want to solve, and for whom;
  • what information they already have (documents, examples, competitors);
  • who will use it, and in what situation;
  • how they imagine it working.

Bring in what you know: similar products, typical approaches, pitfalls. Offer 2–3 possible approaches when there is a real choice, with your recommendation. If you can search the web and it helps, do so and keep the useful links for "Sources".

Mark the step done when you can describe the product in two sentences and the user agrees.

Step 2 · scope

Agree on what the first version does not do. Propose a short list (payments, accounts, multiple languages, admin panels…), and let the user move items in or out. A smaller v1 ships sooner. Say so.

Step 3 · summarize

If the file already exists, follow "Existing outputs" in state-rules.md (revise it, never overwrite the user's edits). Otherwise: write builder/01-idea.md from the template ${CLAUDE_PLUGIN_ROOT}/skills/idea/templates/01-idea.md. Translate the headings to the user's language.

Rules:

  • Use simple terms.
  • Describe the idea as the user sees it. Don't add conclusions of your own.
  • The "Not in v1" section is the list from step 2.

Then:

  • set project.hasFrontend: true if people will use it through screens (a website, an app), false for a script, API, bot or automation without screens, null if still unclear;
  • show the user the summary and ask them to approve it, or to change anything;
  • when approved (or if the user asked you to proceed with defaults): set review: reviewed, mark the step and the phase done, set currentPhase to prd, and update the progress page.

Close with one line, then suggest /builder:next (it continues with the PRD).

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.