okhp3-elicitation-interviews
Skill3 starsChanged 2 months agoMITView on GitHub
Plan and facilitate structured elicitation sessions using BABOK v3 interview and workshop techniques. Use this skill when you need to gather process knowledge from subject matter experts; when the user wants a question plan before an interview or workshop; when elicitation is incomplete and gaps need targeted follow-up; when they say "help me interview the process owner", "prepare questions for the workshop", or "what should I ask to fill in the missing steps". Produces a question plan and elicitation notes template.
In this repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/vercel-react-best-practices/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architecture-decision-recordsSkill
- catalog-integritySkill
- frontend-designSkill
- okhp3-artifact-validationSkill
- okhp3-as-is-process-captureSkill
- okhp3-brand-style-registrySkill
- okhp3-capture-intakeSkill
- okhp3-chatgpt-project-migrationSkill
- okhp3-custom-gpt-builderSkill
- okhp3-custom-gpt-readinessSkill
- okhp3-decision-model-authoringSkill
- okhp3-equilibrium-reviewSkill
- okhp3-evidence-standardSkill
- okhp3-future-state-strategySkill
- okhp3-gpt-skill-conversion-planSkill
- okhp3-graduation-gateSkill
- okhp3-handoff-packagingSkill
- okhp3-notion-capture-routerSkill
- okhp3-outcome-modeling-coreSkill
- okhp3-overkill-hill-brandSkill
- okhp3-process-captureSkill
- okhp3-process-gap-analysisSkill
- okhp3-process-intake-and-scopeSkill
- okhp3-project-promotionSkill
- okhp3-replit-build-in-publicSkill
- okhp3-replit-canvas-boardSkill
- okhp3-replit-design-pipelineSkill
- okhp3-replit-free-mode-autonomySkill
- okhp3-replit-github-syncSkill
- okhp3-replit-multi-artifactSkill
- okhp3-replit-repl-janitorSkill
- okhp3-replit-repository-janitorSkill
- okhp3-replit-task-executorSkill
- okhp3-repository-janitorSkill
- okhp3-repository-organizerSkill
- okhp3-session-handoffSkill
- okhp3-skill-catalogerSkill
- okhp3-skill-discoverySkill
- okhp3-skill-foundrySkill
- okhp3-source-backed-researchSkill
- okhp3-thread-context-extractionSkill
- okhp3-thread-extract-chatgptSkill
- okhp3-thread-extract-claudeSkill
- okhp3-triage-and-fileSkill
- okhp3-vite-github-pagesSkill
- production-build-verificationSkill
- published-keyboard-recovery-checkSkill
- publish-health-checkSkill
- publishing-trigger-checkSkill
- static-route-validationSkill
- validation-smokeSkill
- vercel-react-best-practicesSkill
- web-design-guidelinesSkill
- okhp3-skill-promotionSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 61
Do not fabricate answers from the question plan — only record what participants confirm
- Very specific: line 85
If trigger.event_type is absent → lead with Stage 1 trigger questions
- Very specific: line 86
If actors has no approver → probe approval chain: *"Who has the authority to stop or reject this?"*
- Very specific: line 87
If exceptions is empty → probe with historical incident: *"What was the hardest version of this you've dealt with?"*
- Very specific: line 88
If business_rules is empty → probe obligation: *"Are there any rules you must follow that an outsider wouldn't know?"*
- Very specific: line 117
After elicitation, update pir.yaml and re-run process-intake-and-scope scoring.
≈ “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.
Files
okhp3-elicitation-interviews
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Purpose
Generate a structured elicitation question plan and facilitate evidence-based process interviews using BABOK v3 §10.25 and §10.50 techniques. The plan targets known gaps in the PIR and provides sequenced, open-ended questions mapped to each PIR section.
When to use this skill
- PIR exists but has
completeness_score < 70or open_questions that need targeted follow-up - User needs to interview a subject matter expert and wants a prepared question set
- User is planning a process discovery workshop and needs a facilitator guide
- You need to fill elicitation gaps before proceeding to
process-narrative-authoring
When NOT to use this skill
- PIR is already complete (score ≥ 70, no open_questions) — proceed directly to
process-narrative-authoring - User has no access to process owners — document the gap and proceed with assumptions flagged
- Do not fabricate answers from the question plan — only record what participants confirm
Question Plan Generation
scripts/generate-question-plan.mjs reads the PIR and generates targeted questions for each incomplete section.
Question categories
| PIR section | Question type | Sample opening |
trigger | Context | "What makes you realise the process needs to start today?" |
actors | Role | "Who else touches this beyond the people we've named?" |
inputs | Artefact | "What document or data do you need before you can begin?" |
outputs | Artefact | "What does the person receiving your output actually do with it?" |
steps | Sequence | "Walk me through what you do on a typical day this runs." |
business_rules | Constraint | "Is there a policy or procedure that forces you to do it this way?" |
exceptions | Edge case | "Tell me about the last time this went wrong. What happened?" |
systems | Tool | "Which systems do you open, update, or check during this process?" |
controls | Governance | "How do you know when the process has been done correctly?" |
Branching logic
- If
trigger.event_typeis absent → lead with Stage 1 trigger questions - If
actorshas noapprover→ probe approval chain: "Who has the authority to stop or reject this?" - If
exceptionsis empty → probe with historical incident: "What was the hardest version of this you've dealt with?" - If
business_rulesis empty → probe obligation: "Are there any rules you must follow that an outsider wouldn't know?"
Facilitation Guidelines
- Open with context — read back the process name and one-sentence scope; confirm it is correct
- Use the question plan in order — complete highest-gap sections first
- Probe with "tell me more" — do not accept one-word answers for steps or rules
- Record verbatim — capture exact wording of rules and exceptions; paraphrase only for clarity
- Flag uncertainty — mark any answer prefaced with "I think" or "usually" as
confidence: low - Close with open invitation — "Is there anything else you think I should know to document this correctly?"
- Write up within 24 hours — update the PIR before memory fades
Elicitation Notes Template
The elicitation-notes.md output contains:
- Session metadata (date, participants, facilitator, method)
- Answers mapped to PIR sections
- Verbatim quotes for business rules
- Confidence flags for uncertain answers
- Outstanding items that need follow-up
Handoff Instruction
After elicitation, update pir.yaml and re-run process-intake-and-scope scoring. When score ≥ 70, pass pir.yaml to stakeholder-and-role-mapping and then process-narrative-authoring.
References
Load on demand:
references/babok-elicitation-techniques.md— BABOK v3 §4, §10.14, §10.25, §10.50 technique summaries and question frameworks
Scripts
scripts/generate-question-plan.mjs— generates elicitation question plan from PIR scope and open_questions
Assets
assets/fixtures/question-plan-example.yaml— canonical question plan for purchase-approval intake
About
Built by Jamie Hill · OverKill Hill P³ Published at github.com/OKHP3 Part of the OKHP3/skillz Agent Skill library. MIT License -- free to use, fork, and adapt. A nod to the source is appreciated.
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
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.

