Skip to content
Back to skills

Assess Question Quality

ASecurity

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

  • 499 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
researchgo

Security analysis

A100/100

Scanned September 24, 2026

npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill assess-question-quality --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Assess Question Quality?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Assess Question Quality
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-assess-question-quality/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-assess-question-quality)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: assess-question-quality
description: "Audit a research question for scope and FINER-style quality; return targeted repairs."
---

# assess-question-quality

## Purpose

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

## Input contract

```yaml
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

```yaml
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`

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…