agentleFS
MicrosoftKnown publishermicrosoft/Tandem/development/tandem/skills/use-case-designer/SKILL.md

use-case-designer

Skill8 starsChanged 14 days agoMITView on GitHub

Design the PM-level Use case tab and selectable user journeys.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 the user's language and assume the reviewer has no software-development background.

    line 32

≈ “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

Use-Case Designer

Design the PM-level product overview before considering internal architecture.

Identify two to seven major use cases that together cover the core product experience. A use case is a user goal with an observable outcome—not an API endpoint, screen, command, or internal operation. Do not enumerate minor edge cases.

For each use case provide:

  • a stable ID and short goal-oriented title;
  • the user or external actor;
  • the observable outcome;
  • a representative journey of one to six steps.

Each step follows:

{ id, userAction, systemResponse, interactionId }

Implementation state belongs only to the containing Use case. Do not put implementationState on journey steps; they remain fine-grained design and Attention anchors while the host initializes and preserves coarse Use case progress.

Use the user's language and assume the reviewer has no software-development background. Titles, actions, and responses must describe recognizable goals and visible behavior without API, framework, or architecture jargon. A reviewer should understand the complete experience map by reading only its visible labels. interactionId must exactly match a stable contract-set/v1 interaction ID, not its display name. Together the use cases form an experience map; selecting one reveals its journey. Keep the primary experience clear while leaving detailed error branches to the Contract or Flow subviews.

Attach zero to three Attention items directly to the relevant Use case or journey step, only for consequential ambiguity in a user goal or observable outcome. Each item has id, impact, question, whyItMatters, and two or three { option, implication } alternatives.

Persist { useCases } through submit_use_case_block. On revision, use the inherited block, including its embedded Attention, as the baseline and submit only when this perspective changes.

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.