agentleFS
45ck45ck/business-analysis-skills/.agents/skills/edge-case-elicitor/SKILL.md

edge-case-elicitor

Skill28 starsChanged 8 months agoMITView on GitHub

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Prefer short, testable statements over long prose.

    line 47
  2. Distinctive:

    Do not invent stakeholder intent.

    line 52
  3. Distinctive:

    Do not convert preferences into mandatory requirements without evidence.

    line 53
  4. Distinctive:

    Do not hide unresolved ambiguity behind polished wording.

    line 54
  5. Distinctive:

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

    line 55

≈ “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

edge-case-elicitor

Purpose

Generate realistic boundary, invalid, exceptional, and rarely discussed cases from normal requirements.

Trigger this skill when

  • A feature looks simple and therefore risky to under-specify.
  • Validation, permissions, workflow branching, or time/state logic exists.
  • Acceptance criteria are too happy-path heavy.

Expected inputs

  • requirements
  • acceptance criteria
  • data rules
  • workflow states

Deliverables

  • edge-case catalogue
  • negative scenarios
  • follow-up questions

Operating procedure

  1. Inspect actor, data, timing, ordering, concurrency, state, limits, and environment assumptions.
  2. Generate invalid, missing, duplicated, stale, partial, unauthorized, boundary, and sequencing scenarios.
  3. Mark which cases need requirement clarification vs direct acceptance criteria.

Quality gates

  • Cases are plausible, not random.
  • Edge cases map back to a real workflow or data rule.
  • Critical failure modes are represented.

Handoff targets

  • acceptance-criteria-writer
  • verification/test packs later
  • ambiguity-hunter

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.