classify-research-gap

SkillDev tools

Lets your agent classify a research gap by type and record what actions to take next.

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 classify-research-gap skill

About this skill

Classify a candidate research gap by type (evidence, method, mechanism, population, theory, measurement, contradiction, boundary, translation, etc.) and record implications for next actions.

What this skill tells your AI

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

Purpose

Classify a candidate research gap by type and record implications for the next research action.

Input contract

required: [gap_statement, supporting_evidence]
optional: [domain_scope, candidate_gap_types]
constraints: [gap type must be supported by evidence and distinguished from absence of search]

Procedure

  1. Compare the gap claim with the declared evidence and scope.
  2. Test evidence, method, mechanism, population, theory, measurement, contradiction, boundary, and translation categories.
  3. Assign one or more justified types and map each to a next action.

Output contract

produces: [typed_gap, classification_rationale, action_implications]
delta_fields: [findings, evidence_updates, uncertainties, decisions, recommended_jumps]

Quality gates

  • Classification names the evidence boundary and does not treat unsearched space as a confirmed gap.

Failure and counterexamples

Return unsubstantiated_gap when the claimed absence is caused by inadequate retrieval or incompatible scope.

Provenance map

  • deep-insight/gap-classification: resolved.

Signals

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