agentleFS
45ck45ck/business-analysis-skills/.agents/skills/requirements-interrogator/SKILL.md

requirements-interrogator

Skill28 starsChanged 8 months agoMITView on GitHub

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Run a disciplined clarification pass that pressure-tests requirements, surfaces hidden constraints, and exposes ambiguity early.

    line 12
  2. Distinctive:

    Read the current requirement set end to end.

    line 32
  3. Distinctive:

    Prefer short, testable statements over long prose.

    line 50
  4. Distinctive:

    Do not invent stakeholder intent.

    line 55
  5. Distinctive:

    Do not convert preferences into mandatory requirements without evidence.

    line 56
  6. Distinctive:

    Do not hide unresolved ambiguity behind polished wording.

    line 57
  7. Distinctive:

    Do not collapse functional, non-functional, and business rule concerns into one blob.

    line 58

≈ “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

requirements-interrogator

Purpose

Run a disciplined clarification pass that pressure-tests requirements, surfaces hidden constraints, and exposes ambiguity early.

Trigger this skill when

  • The user has given requirements but they are incomplete, optimistic, or inconsistent.
  • You are about to design, estimate, or implement from natural-language requirements.
  • A change request may affect security, compliance, UX, or operations.

Expected inputs

  • problem statement
  • existing requirements
  • stakeholders
  • project constraints

Deliverables

  • clarification question set
  • requirements issues list
  • assumptions register
  • updated requirement notes

Operating procedure

  1. Read the current requirement set end to end.
  2. Probe for actor, trigger, precondition, main flow, exception flow, data, policy, security, timing, and operational concerns.
  3. Classify ambiguities into missing information, conflict, hidden assumption, scope uncertainty, and unverifiable statement.
  4. Prioritize the highest-risk unanswered questions first.
  5. Rewrite shaky requirements into testable language where enough context exists.

Quality gates

  • Questions are risk-based, not random.
  • Distinguishes missing requirement from implementation decision.
  • Marks unverifiable language such as fast, user-friendly, secure, intuitive, scalable.

Handoff targets

  • ambiguity-hunter
  • constraint-detector
  • acceptance-criteria-writer

Output style

  • Be explicit about uncertainty.
  • Prefer short, testable statements over long prose.
  • Surface risk and ambiguity instead of guessing.
  • Separate facts, assumptions, constraints, and open questions.

Failure modes to avoid

  • Do not invent stakeholder intent.
  • Do not convert preferences into mandatory requirements without evidence.
  • Do not hide unresolved ambiguity behind polished wording.
  • Do not collapse functional, non-functional, and business rule concerns into one blob.

Minimum output skeleton

## Summary
## Findings
## Structured outputs
## Assumptions
## Constraints
## Open questions
## Recommended next skill

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.