agentleFS
nesnilnehcnesnilnehc/ai-cortex/skills/clarify-product-requirement/SKILL.md

clarify-product-requirement

Skill8 starsChanged 2 months agoMITView on GitHub

Resolve business choices that materially affect a product requirement's objective, scope, rules, or acceptance. Use for ambiguous feature requests or drafts with unresolved product decisions.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Read the project conventions, existing item, and relevant evidence.

    line 14
  2. Distinctive:

    Ask about decisions whose prerequisites are settled.

    line 19

≈ “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

Clarify Product Requirement

Take the user's request or existing draft and its available sources. Use this skill when a material business choice remains open. For settled requests, hand off directly to the project's requirement authoring workflow.

  1. Read the project conventions, existing item, and relevant evidence. Use rules/requirement-intake-triage.md from the AI Cortex asset root to classify raw intake. Route defects and technical work according to their kind.
  2. Resolve factual gaps from available evidence. List the choices that still need a person and identify which choices depend on other answers.
  3. Ask about decisions whose prerequisites are settled. Group independent questions when helpful. Give the practical consequence of each option and recommend one when supported. If an answer changes a premise, revisit the affected decisions.
  4. Return the confirmed objective, scope, exclusions, and observable acceptance to the extent supported. Cite the decision sources and list what remains open. If an open choice would change a material part of the requirement, name the question and pause the affected drafting or splitting until it is resolved. When the remaining questions do not prevent drafting, hand off to the runtime using specs/requirement-modeling.md. Suggest split-product-delivery if the scope is clear and too broad for one delivery.

For an automatic approval request, settle which application types are in scope before asking which exceptions need manual review. An existing approval policy may already answer the second question.

Self-check

Each question changes a material decision and has settled prerequisites. Confirmed answers have a source. Open decisions remain visible. The handoff does not imply approval or authorize changes to an existing requirement.

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.