agentleFS
CodeCaroSCodeCaroS/MythOs_Aegis/.agents/skills/visual-flow-storyboard/SKILL.md

visual-flow-storyboard

Skill0 starsChanged 3 months agoApache-2.0View on GitHub

Reconstruct complete user journeys from actual code and turn them into visual storyboards. Use when analyzing multi-step flows, hidden branches, roles, feature flags, failure paths, or planning a better target flow from the codebase.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Start from the real codebase.

    line 31
  2. Distinctive:

    If asked for a future-state storyboard, describe the target flow and the changes needed to get there.

    line 37
  3. Distinctive:

    If asked for a change recap, compare before vs after and call out removed, added, or changed states.

    line 38
  4. Distinctive:

    Prefer a compact, structured storyboard:

    line 49
  5. Distinctive:

    Do not invent screens that are not supported by code or evidence.

    line 62
  6. Distinctive:

    Do not analyze screens in isolation when the real issue is the full flow.

    line 63
  7. Distinctive:

    Do not assume a framework implies the rendering or navigation model.

    line 64
  8. Distinctive:

    Keep every journey frame tied to state, action, transition, evidence, and any inferred gap.

    line 70

≈ “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

Visual Flow Storyboard

Use this skill to map what the product actually does, not what the docs say it should do. This owns the journey/storyboard artifact. For a persistent testable story matrix plus a fix loop, use ux-logic-loop (it should reuse this skill's output rather than re-deriving flows). For a pre-implementation plan inside a PR review, visual-pr-review should also reuse this output rather than re-mapping flows.

What to analyze

  • Entry points, exits, and interrupted resumes
  • Screens, states, branches, and transitions
  • Roles, permissions, tenant states, and feature flags
  • Hidden, legacy, or unreachable paths
  • Error, empty, loading, cancellation, and recovery states
  • UX friction across the full journey

Required approach

  1. Start from the real codebase.
  2. Identify the flow boundary: start point, end point, user role, and relevant flags or data states.
  3. Trace the actual path through routes, guards, loaders, actions, APIs, redirects, and state transitions.
  4. Build a state matrix for the meaningful variants.
  5. Convert the states into a storyboard with numbered steps.
  6. Mark uncertainty when a screen or branch is inferred rather than proven.
  7. If asked for a future-state storyboard, describe the target flow and the changes needed to get there.
  8. If asked for a change recap, compare before vs after and call out removed, added, or changed states.

What to inspect

  • Routes, pages, views, forms, dialogs, navigation, and responsive variants
  • Guards, middleware, permissions, feature flags, redirects, and validation rules
  • Loading, error, empty, and recovery behavior
  • Tests, analytics events, and screenshots or design artifacts when present

Output shape

Prefer a compact, structured storyboard:

  • Flow summary
  • Boundaries and roles
  • State matrix
  • Storyboard steps
  • Branch diagram or table
  • UX issues and friction points
  • Target flow if requested
  • Open questions or uncertain branches

Rules

  • Do not invent screens that are not supported by code or evidence.
  • Do not analyze screens in isolation when the real issue is the full flow.
  • Do not assume a framework implies the rendering or navigation model.
  • Focus on the actual user journey and how the system responds at each step.

Shared output profile

Compose the plan profile from output-templates. Keep every journey frame tied to state, action, transition, evidence, and any inferred gap. Preserve stricter domain rules above, omit empty components, and never fill a component with invented evidence.

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.