agentleFS
link7373link7373/agentic-pmo/.claude/skills/elicit-requirements/SKILL.md

elicit-requirements

Skill1 starsChanged 3 months agoMITView on GitHub

Elicit and analyze requirements for a problem or feature — frame the need, choose elicitation techniques, model current vs. future state, classify and specify requirements (including non-functional), keep them traceable, and verify/validate. Use when the problem is unclear, stakeholders disagree, or requirements are ambiguous, before a PRD is locked. Dispatches the business-analyst.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start from templates/requirements-package.md.

    line 37

≈ “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

/elicit-requirements — Understand the need before building

When to use

The problem is fuzzy, stakeholders disagree, the process is complex, or requirements are ambiguous — and you need a rigorous, traceable requirements package before (or to strengthen) a PRD.

Dispatches

business-analyst (lead). Pull evidence from discovery-researcher; hand analyzed requirements to product-manager for the PRD and to product-owner for backlog detailing; partner with project-manager on scope/change impact.

Inputs

knowledge/product-context.md, knowledge/stakeholder-map.md, knowledge/intake.md, any existing PRD/notes.

Steps

  1. Frame the six core concepts — name the need, value, stakeholders, and context before any solution.
  2. Plan and run elicitation — choose techniques that fit the goal (interviews, workshops, observation, surveys, document analysis, prototyping); probe the why; confirm findings back with stakeholders.
  3. Model current state → future state → gap; run root-cause analysis (5 Whys, cause-and-effect) on the real pain so the change targets causes, not symptoms.
  4. Classify requirements (business / stakeholder / solution [functional + non-functional] / transition); specify non-functional attributes with measurable targets.
  5. Establish traceability (need → requirement → design/test); verify each requirement is well-formed and validate it delivers value; prioritize by value, risk, dependency, and constraint.
  6. Compare solution options against explicit criteria; state assumptions, open questions, and confidence.

Methods

knowledge/methods/business-analysis.md, knowledge/methods/requirements-and-stories.md, knowledge/methods/discovery-and-validation.md, knowledge/methods/prioritization-frameworks.md.

Output

Start from templates/requirements-package.md. Save the package at knowledge/prds/<YYYY-MM-DD>-<feature>-analysis.md (or as a section feeding /write-prd); log scope/solution decisions to knowledge/decision-log.md. Follow standards/document-standards.md — classify requirements, make non-functional targets measurable, and keep everything traceable to a need.


Created by Colin Beck<br> LinkedIn: https://www.linkedin.com/in/beckcolin/<br> GitHub: https://github.com/link7373

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.