agentleFS
UwayxtUwayxt/agent-skills/.agents/skills/stakeholder-requirement-mapping/SKILL.md

stakeholder-requirement-mapping

Skill4 starsChanged 3 months agoMITView on GitHub

Translate cross-department needs into unified requirements. Use when requirements from sales/ops/finance, cross-department needs, stakeholder alignment, or conflicting requirements.

The file

Files
SKILL.md

Stakeholder Requirement Mapping

Every department speaks a different language about the same product. This skill translates, deduplicates, and resolves conflicts before they become architecture problems.

1. Map stakeholders

Who has a stake? List every department or role that will touch the product (sales, ops, finance, customer support, legal, end users). Detail what they need from the product and why.

2. Extract requirements per stakeholder

Separate stated needs ("I want a report") from underlying needs ("I need to know which customers are at risk of churning"). Underlying needs survive requirements changes; stated needs don't.

3. Cross-reference and deduplicate

Merge duplicates where multiple stakeholders ask for the same thing in different words. Surface contradictions explicitly ("Sales wants unlimited free trials; Finance wants paid-only access").

4. Resolve conflicts

Propose resolution for each contradiction. Escalate to the user for unresolvable conflicts. Record the decision and rationale.

5. Produce unified requirement list

Map each requirement to originating stakeholder(s), priority, and resolution status.

Completion Criteria

Done when all stakeholder inputs are mapped, deduplicated, and all direct conflicts are resolved or escalated.

Output Format

Stakeholder Map and Requirements Matrix (requirement → stakeholder → priority → status).

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.