agentleFS
forsvn-labsforsvn-labs/meta-skills/skills/map-user-flow/SKILL.md

map-user-flow

Skill14 starsChanged 3 months agoMITView on GitHub

Map an in-product flow across screens, decisions, transitions, native platform surfaces, and recovery states. Use for a feature or user journey that spans multiple screens or states, before visual UI design or technical architecture.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Create the smallest complete flow that lets a product team make interface and implementation decisions without inventing missing behavior.

    line 11
  2. Distinctive:

    Read existing product requirements, shipped UI, analytics, and support evidence when available.

    line 19
  3. Distinctive:

    Keep the happy path short.

    line 32
  4. Distinctive:

    Do not add a screen merely to house information that belongs in an existing state.

    line 48
  5. Distinctive:

    Use a diagram only after the written structure is complete.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Map a product flow

Create the smallest complete flow that lets a product team make interface and implementation decisions without inventing missing behavior.

Establish the job and surfaces

State the user job, entry condition, successful end state, and explicit non-goals. Enumerate actual platforms and native surfaces; reject “cross-platform” as a sufficient specification.

Read existing product requirements, shipped UI, analytics, and support evidence when available. Separate observed behavior, approved requirement, inference, and open decision.

Write structure before diagrams

Give every screen/state a stable short identifier. For each, specify:

  • user intent and information required;
  • available actions;
  • decision or system condition;
  • destination for success, cancellation, and failure;
  • state that must persist across the transition.

Keep the happy path short. Challenge more than seven user actions and remove steps that do not create understanding, control, or required trust.

Cover the complete state space

For every relevant surface, cover:

  • empty and first-run;
  • loading and duplicate-action prevention;
  • validation and system error;
  • permission denied or revoked;
  • offline/degraded operation;
  • cancellation, retry, and safe recovery;
  • interruption, resume, and destructive confirmation where applicable;
  • accessibility and native platform behavior.

Do not add a screen merely to house information that belongs in an existing state.

Deliver

Return:

  1. outcome, assumptions, and non-goals;
  2. platforms and surfaces;
  3. numbered happy path with explicit transitions;
  4. decision branches;
  5. state and edge-case matrix;
  6. recovery behavior;
  7. validation scenarios;
  8. unresolved product decisions.

Use a diagram only after the written structure is complete. Finish with the smallest review question that would materially change the flow.

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.