Sigil: Structured Interview Kits

SkillAI & models

Use when: running one-question-at-a-time interviews with pluggable modes, evidence-backed prompts, and artifact updates after each answer.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Sigil: Structured Interview Kits skill

What this skill tells your AI

The instructions your AI receives, as published by cyberalchemyai/arcanum in .claude/skills/interrogation/SKILL.md and read by ahel’s review.

  • mode ID,
  • applicability signals,
  • question formation strategy,
  • required question fields,
  • allowed patch targets,
  • exit criteria,
  • readiness verdict rules.

Do not change the orchestrating sigil unless the mode contract itself changes.

  • ask one question at a time,
  • base each question on evidence or explicit uncertainty,
  • avoid dumping full question banks,
  • update artifacts after answers when mutation is in scope,
  • preserve decision traceability,
  • distinguish blocker ambiguity from non-blocker ambiguity,
  • stop cleanly when exit criteria are met.
  • asking broad generic questions without evidence,
  • asking multiple unrelated questions at once,
  • continuing after a blocker answer contradicts the target artifact without updating it,
  • using interview mode as hidden implementation planning,
  • inventing answers for the user,
  • treating unresolved blocker ambiguity as readiness.
## Structured Interview Result

- Target scope: <scope>
- Mode: <mode-id>
- Questions asked: <count>
- Decisions recorded: <count>
- Artifacts updated: <paths or none>
- Remaining ambiguities: <summary>
- Verdict: pass | flag | block
- Next step: <action>

Signals

GitHub stars
25
Forks
3
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
interrogation
Source
github.com/cyberalchemyai/arcanum