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
Review the base questions and identify where generic answers are likely.
Generate probes for examples, exceptions, timings, frequency, triggers, approval rules, data, handoffs, and failure cases.
Tailor probes to stakeholder vocabulary and likely blind spots.
Tag each probe with what it is trying to uncover.
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
1---2name: probe-question-generator3description: probe-question-generator4---5# probe-question-generator67## Purpose8Generate follow-up probe questions that push past generic answers into evidence, examples, rules, edge cases, and pain points.910## Trigger this skill when11- Base questions are too shallow.12- Stakeholders are likely to answer with generic or overly polished statements.13- You need evidence-oriented follow-ups.1415## Expected inputs16- base questions17- analysis theme18- stakeholder type19- current answers if any2021## Deliverables22- probe question set23- probe rationale24- likely signal targets2526## Operating procedure271. Review the base questions and identify where generic answers are likely.282. Generate probes for examples, exceptions, timings, frequency, triggers, approval rules, data, handoffs, and failure cases.293. Tailor probes to stakeholder vocabulary and likely blind spots.304. Tag each probe with what it is trying to uncover.315. Sequence probes from least to most challenging.3233## Quality gates34- Probes seek observable detail.35- Probes do not become hostile or leading.36- Each probe is tied to a signal target.3738## Handoff targets39- interview-plan-designer40- business-rule-extractor41- as-is-process-investigator4243## Output style44- Be explicit about uncertainty.45- Prefer structured outputs over loose prose.46- Separate confirmed findings, inferred findings, and open questions.47- Preserve source context where practical.4849## Failure modes to avoid50- Do not pretend weak evidence is confirmed fact.51- Do not confuse stakeholder opinion with validated rule or process truth.52- Do not hide missing coverage behind polished wording.53- Do not flatten politically different stakeholders into one generic audience.5455## Minimum output skeleton56```md57## Summary58## Findings59## Structured outputs60## Risks or tensions61## Open questions62## Recommended next skill63```
Run npx skillmds@latest add 45ck/probe-question-generator in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
probe-question-generator It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
45ck (@45ck) published this skill. Their other Agent Skills are listed on their SkillMD profile.