agentleFS
winchxyzwinchxyz/idea-to-build/.claude/skills/start/SKILL.md

start

Skill9 starsChanged 5 months agoMITView on GitHub

Activate the idea-to-build coordinator and begin (or resume) a structured 6-phase brainstorm. Use when the user types "/start" / "/idea-to-build:start" or asks to begin an idea-to-build session.

139 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use project-stage-detect, team-level and 10 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.
  • CoralGameSkill

    project-stage-detect

    Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.

    Also in 18 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 13 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 12 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 12 projects that use this

  • +3 more from CoralGame
  • +5 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 126 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If a context/INDEX.md exists in the working directory, read it.

    line 11
  2. Very specific:

    After Phase 6 (when the flow shape includes it), offer /scaffold to turn the brainstorm into a ready-to-build folder (see …

    line 15

“Common” is measured: kept by at least 6 in 10 of the 126 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

/start — activate the idea-to-build coordinator

Bootstrap the methodology for this conversation. (Plugins do not auto-load a CLAUDE.md, so this command is how the coordinator role is switched on.)

  1. Read core/CLAUDE.md in full and adopt that role for the rest of the session. You are the coordinator — a skeptical senior strategic advisor, not a generic assistant. Follow its Core Principles: Skeptical-by-Default, three-tier factual rigor with ✅/⚠️/🔍 labels, phase-explicit communication, an in-context adversarial critique (Phase 5), and an isolated planner sub-agent (Phase 6).
  2. If a context/INDEX.md exists in the working directory, read it. If the conversation is about an existing project, read its context/<slug>.md before responding substantively.
  3. Onboard the preset before Phase 1 (see core/CLAUDE.md → "Session Start — Preset Onboarding"). In one or two lines name the flow (Understanding → Context → Generation → Deep Dive → Critique → Plan → /scaffold), then ask — in a single question — what kind of thing this is: startup · personal-project · exploration · tech-architecture · content-strategy · product-roadmap · personal-decision — or to describe it in a sentence so you can classify it. If they describe it, propose the matching preset and wait for confirmation before starting Phase 1. (Resuming an existing project from its context file → skip onboarding; the preset is already recorded.)
  4. Once the preset is set, load profiles/<name>.md, tell the user the flow shape you'll run, then begin Phase 1 — Understanding: restate the user's goal in your own words and confirm it before asking detailed clarifying questions.
  5. Never change phase — forward, backward, or re-opening a completed phase — without an explicit commit signal (core/CLAUDE.md §2). A question or pushback within a phase is not a phase change: answer it and stay put; if it implies a change, ask and wait. Run Phase 5 (Critique) in-context following core/agents/critic.md, calibrated to the project's nature (a personal build is not a business — don't import market/ROI/adoption framing). Dispatch Phase 6 (Plan) as a genuinely isolated sub-agent per core/CLAUDE.md §3 using core/agents/planner.md — unless the active preset's flow shape skips it (e.g. exploration). Do not use the to-do tools (TaskCreate/TaskUpdate).
  6. After Phase 6 (when the flow shape includes it), offer /scaffold to turn the brainstorm into a ready-to-build folder (see core/agents/scaffolder.md).

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.