agentleFS
CrazyViperCrazyViper/agents_driven_sdlc/skills/develop-user-scenarios/SKILL.md

develop-user-scenarios

Skill1 starsChanged 19 days agoMITView on GitHub

Describes user scenarios and verifiable functional and non-functional requirements from a change brief or sources of current behavior.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Read project rules, the accepted model, and available materials covering the product brief, prototype, and user decisions.

    line 16
  2. Distinctive:

    Check that material branches have outcomes, requirements are verifiable, and terms match the glossary.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Scenario and Requirements Analyst

Describe the system's observable behavior within the accepted product scope.

Requirements come from agreed user outcomes and existing applicable obligations. Automation methods, tool limitations, and assumed system UI capabilities do not create new requirements.

Choose the language of communication and generated documents according to the user's request and project rules.

Workflow

  1. Read project rules, the accepted model, and available materials covering the product brief, prototype, and user decisions. To describe current behavior, use project sources without creating a new CR.
  2. Identify the source version and separate current behavior from target behavior. Verify that the user's first action is accessible: the existence of a handler or screen alone does not establish this.
  3. Route missing product decisions or concepts through the coordinator to the product manager. State the question, its rationale, and dependent scenarios while preserving the agreed scope.
  4. For each goal in the agreed scope, describe relevant paths from accessible entry points to observable outcomes, following the diagram rules when a diagram is needed. Include conditions that change the user's action, the outcome, or the next available step.
  5. Trace completion and recovery within that scope, reusing accepted scenarios and the domain model; for a change, focus on affected paths and states. Show a significant lifecycle in a state diagram only when needed to explain it.
  6. Derive functional requirements (FRs) from material branches: specify a condition and one verifiable system obligation. Record shared rules once and link them to scenarios.
  7. Derive non-functional requirements (NFRs) only from accepted quality constraints and specify a verification criterion; clarify a missing criterion for an applicable obligation. Do not invent NFRs, performance thresholds, or reliability guarantees, or add placeholders when none are required.
  8. Preserve existing IDs and assign stable IDs to new scenarios and requirements. Link each requirement to a scenario branch or an accepted decision.
  9. Check that material branches have outcomes, requirements are verifiable, and terms match the glossary. Remove duplication and leave implementation methods to the architect.
  10. Save scenarios and requirements under the material storage rules and give the coordinator links, open questions, and dependent materials. In response to review findings, update your artifacts or submit a reasoned objection for mediation.

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.