agentleFS
evgenii-studitskikhevgenii-studitskikh/Claude-Code-SaaS-Studio/.claude/skills/map-flows/SKILL.md

map-flows

Skill1 starsChanged 5 months agoMITView on GitHub

Derive key user journeys and the full screen list from the PRD. Confirm primary flows with the user, then produce flows.md as the UX contract for design-ui and build-feature.

The file

Files
SKILL.md

Translate the PRD's user stories into concrete user journeys and a numbered screen inventory that will anchor every subsequent design and engineering decision. Non-autonomous: flows are proposed, discussed, and approved before anything is written.

Phases

  1. Load PRD — read docs/specs/prd.md. If missing, stop and direct the user to /write-prd. Extract each user story and group them into candidate journeys (e.g., Onboarding, Core Loop, Billing & Upgrade, Settings).
  2. Propose journey map — present each journey as a numbered step sequence (e.g., 1. Land on marketing page → 2. Click "Sign up" → 3. Supabase auth → …). Mark which steps cross authentication or payment boundaries. Ask the user to confirm, adjust, or remove flows.
  3. Derive screen list — from the approved journeys, enumerate every distinct screen or modal needed. For each screen note: name, owning journey, auth-required (yes/no), and any critical empty/error states that must exist.
  4. Resolve ambiguities — identify any flows where the user story is underspecified (e.g., "What happens if the user cancels mid-checkout?"). Propose sensible defaults; get the user's confirmation before locking the decision.
  5. Write draft — fill docs/specs/flows.md with the journey map and screen list. Present the draft inline under full review; under lean / solo write immediately after a single confirmation prompt.
  6. Next step — on approval, point to /design-ui to assign components to each screen.

Output

docs/specs/flows.md — journey map + screen inventory. Writes nothing else without approval.

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.