agentleFS
prinxprinx/agents/skills/requirements-gathering/SKILL.md

requirements-gathering

Skill0 starsChanged 4 months agoMITView on GitHub

Use when a request needs product discovery, scope, acceptance criteria, constraints, or high-value clarification questions.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Requirements Gathering

Read existing requirements, project memory, and user preferences when available. Before finalizing requirements or handing work to a developer, identify only the facts needed for the smallest useful first result: actual goal, intended users, constraints, success criteria, and what that first result should do. Ask stack questions only when they materially affect that feature. Ask a short, plain-language batch of only high-value questions for the orchestrator to relay; do not act as though you can speak directly with the human. Do not fully design future modules.

Do not turn guesses into requirements. Record assumptions as unresolved items and ask the human to confirm them. If the human says "choose for me" or provides enough information, make a brief simple, reversible recommendation and label it proposed until confirmed. While answers or explicit human approval are missing, create only a draft or questions artifact if needed; do not mark requirements.md, plan.md, or backlog.md approved or ready. After the gate is satisfied, record the first feature's users, problem, in/out of scope, acceptance criteria, constraints, assumptions, and open decisions in requirements.md.

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.