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

requirements-gap-auditor

Skill28 starsChanged 8 months agoMITView on GitHub

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Before sign-off, estimation, architecture, or build.

    line 16
  2. Distinctive:

    After a large edit or merge of multiple requirement sources.

    line 17
  3. Distinctive:

    Check for normal completeness categories: actors, triggers, preconditions, postconditions, data, validation, permissions, error handling, …

    line 32
  4. Distinctive:

    Prefer short, testable statements over long prose.

    line 48
  5. Distinctive:

    Do not invent stakeholder intent.

    line 53
  6. Distinctive:

    Do not convert preferences into mandatory requirements without evidence.

    line 54
  7. Distinctive:

    Do not hide unresolved ambiguity behind polished wording.

    line 55
  8. Distinctive:

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

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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-gap-auditor

Purpose

Audit a requirement set for what is missing relative to common engineering needs: actors, flows, data, validation, security, operations, and lifecycle.

Trigger this skill when

  • A draft spec feels thin but the exact gaps are unclear.
  • Before sign-off, estimation, architecture, or build.
  • After a large edit or merge of multiple requirement sources.

Expected inputs

  • requirements
  • problem statement
  • constraints
  • assumptions
  • acceptance criteria if any

Deliverables

  • gap audit report
  • missing topic checklist
  • remediation suggestions

Operating procedure

  1. Check for normal completeness categories: actors, triggers, preconditions, postconditions, data, validation, permissions, error handling, NFRs, support/ops, reporting, auditability, rollout, and maintenance.
  2. Flag absent or weak areas.
  3. Suggest the next best artifact or question to close each major gap.

Quality gates

  • Gaps are categorized and evidence-based.
  • Findings distinguish absent, weak, and deferred.
  • Suggestions are actionable.

Handoff targets

  • requirements-interrogator
  • constraint-detector
  • definition-of-done-drafter

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.