assess-question-quality

SkillDev tools

Lets your agent audit a research question for clarity, focus, and scope, then suggest targeted wording fixes.

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

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the assess-question-quality skill

About this skill

Audit a research question for scope and FINER-style quality; return targeted repairs.

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/assess-question-quality/SKILL.md and read by ahel’s review.

Purpose

Assess whether a research question is clear, focused, answerable, relevant, and appropriately scoped.

Input contract

required: [research_question, intended_use]
optional: [constraints, evidence_context, stakeholder_needs]
constraints: [each quality judgment requires a criterion and textual evidence]

Procedure

  1. Evaluate clarity, focus, answerability, relevance, and scope fit.
  2. Identify ambiguity, hidden assumptions, and unbounded terms.
  3. Propose the smallest wording changes that resolve material defects.
  4. Return a scored or categorical assessment with unresolved issues.

Output contract

produces: [quality_assessment, criterion_evidence, revision_candidates, unresolved_issues]
delta_fields: [findings, decisions, uncertainties, open_questions]

Quality gates

  • Judgments cite exact question terms.
  • Revision candidates preserve the intended decision or outcome.

Failure and counterexamples

Do not reward complexity as rigor or call a question answerable when its outcome cannot be observed.

Provenance map

  • resolved: assess-question-quality

Signals

GitHub stars
501
Forks
41
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
assess-question-quality
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine