agentleFS
jiayuewangjavyjiayuewangjavy/product-designer-skills-os/skills/conceptual-model-design/SKILL.md

conceptual-model-design

Skill4 starsChanged 20 days agoMITView on GitHub

Build or review a product conceptual model when entities, roles, relationships, states, permissions, or lifecycle choices determine how the product should work. Use for product briefs, IA, prototypes, and data-model alignment. Do not invent a single correct model from missing policy.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Use an object when it has independent identity, lifecycle, or relationships.

    line 14
  2. Distinctive:

    Use an attribute when it only describes another object.

    line 15
  3. Distinctive:

    When the answer depends on an unstated product choice, show alternatives and request or record the decision.

    line 16
  4. Distinctive:

    Add relationships and cardinality only when supported.

    line 18
  5. Distinctive:

    Do not turn every noun into an object.

    line 36
  6. Distinctive:

    Do not silently invent policy, permissions, cardinality, or business rules.

    line 37
  7. Distinctive:

    When updating a model, state what changed and which evidence or decision caused the change.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Conceptual Model Design

Turn product evidence into an inspectable model that product, design, and engineering can discuss together.

Model the product

  1. Extract candidate actors, concepts, actions, state words, lifecycle clues, and governing rules from the supplied evidence.
  2. Decide whether each concept is an object or an attribute:
    • Use an object when it has independent identity, lifecycle, or relationships.
    • Use an attribute when it only describes another object.
    • When the answer depends on an unstated product choice, show alternatives and request or record the decision.
  3. Identify roles and permitted actions. Separate current evidence from proposed policy.
  4. Add relationships and cardinality only when supported; mark unknowns explicitly.
  5. Describe meaningful state transitions, including failure, expiry, cancellation, reversal, and recovery when relevant.
  6. Translate the model into product implications: what information, actions, permissions, states, and boundaries the experience must reveal.
  7. Identify which unresolved model decision creates the greatest downstream design or engineering risk.

Output

  1. Roles
  2. Objects and attributes, including non-obvious rationale
  3. Relationships
  4. Lifecycle and state transitions
  5. Rules and permissions
  6. Assumptions requiring human review
  7. Product implications
  8. Highest-risk model decision and next evidence

Boundaries

  • Do not turn every noun into an object.
  • Do not silently invent policy, permissions, cardinality, or business rules.
  • A polished diagram is not proof that the model is correct.
  • Preserve vocabulary users already understand unless evidence supports changing it.
  • When updating a model, state what changed and which evidence or decision caused the change.

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.