agentleFS
45ck45ck/business-analysis-skills/.agents/skills/probe-question-generator/SKILL.md

probe-question-generator

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 structured outputs over loose prose.

    line 49
  2. Distinctive:

    Do not pretend weak evidence is confirmed fact.

    line 54
  3. Distinctive:

    Do not confuse stakeholder opinion with validated rule or process truth.

    line 55
  4. Distinctive:

    Do not hide missing coverage behind polished wording.

    line 56
  5. Distinctive:

    Do not flatten politically different stakeholders into one generic audience.

    line 57

≈ “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

probe-question-generator

Purpose

Generate follow-up probe questions that push past generic answers into evidence, examples, rules, edge cases, and pain points.

Trigger this skill when

  • Base questions are too shallow.
  • Stakeholders are likely to answer with generic or overly polished statements.
  • You need evidence-oriented follow-ups.

Expected inputs

  • base questions
  • analysis theme
  • stakeholder type
  • current answers if any

Deliverables

  • probe question set
  • probe rationale
  • likely signal targets

Operating procedure

  1. Review the base questions and identify where generic answers are likely.
  2. Generate probes for examples, exceptions, timings, frequency, triggers, approval rules, data, handoffs, and failure cases.
  3. Tailor probes to stakeholder vocabulary and likely blind spots.
  4. Tag each probe with what it is trying to uncover.
  5. Sequence probes from least to most challenging.

Quality gates

  • Probes seek observable detail.
  • Probes do not become hostile or leading.
  • Each probe is tied to a signal target.

Handoff targets

  • interview-plan-designer
  • business-rule-extractor
  • as-is-process-investigator

Output style

  • Be explicit about uncertainty.
  • Prefer structured outputs over loose prose.
  • Separate confirmed findings, inferred findings, and open questions.
  • Preserve source context where practical.

Failure modes to avoid

  • Do not pretend weak evidence is confirmed fact.
  • Do not confuse stakeholder opinion with validated rule or process truth.
  • Do not hide missing coverage behind polished wording.
  • Do not flatten politically different stakeholders into one generic audience.

Minimum output skeleton

## Summary
## Findings
## Structured outputs
## Risks or tensions
## 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.