adjust-abstraction-scope
SkillDev toolsLets your agent shift a research object's abstraction level and scope until it becomes more explainable and testable.
Available today. Use it from your connected AI after setup.
No other account needed.
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 adjust-abstraction-scope skill
About this skill
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context, outcome, timeframe, system boundary) until the representation has useful explanatory and experimental leverage.
What this skill tells your AI
The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/adjust-abstraction-scope/SKILL.md and read by ahel’s review.
Purpose
Move a scientific object up or down in abstraction, or narrow/broaden scope dimensions, until explanatory and experimental leverage improve.
Input contract
required: [research_object, current_scope, leverage_failure]
optional: [candidate_levels, context_constraints, target_use]
constraints: [retain object identity; change representation or declared scope explicitly]
Procedure
- Record object, current level, and scope dimensions (population, mechanism, context, outcome, timeframe, boundary).
- Generate at least one upward and one downward abstraction candidate when leverage is unclear.
- For each candidate, state what is gained, lost, and newly testable.
- Select the narrowest or broadest level that supports the caller's stated use and record rationale.
Output contract
produces: [scoped_representations, selected_scope, leverage_rationale]
delta_fields: [findings, decisions, uncertainties]
Quality gates
- Object identity is invariant across representations.
- Every changed dimension is named with before/after values.
- Selected scope has an explicit explanatory or experimental leverage claim.
Parameterization
Caller supplies object schema, allowed abstraction dimensions, admissible scope bounds, target use, and selection rule.
Failure and counterexamples
Reject a level that changes the object while appearing to change only scope; reject scope changes with no stated leverage test.
Provenance map
- resolved: abstraction-laddering
- resolved: scope-assessment
- resolved: question-reformulation
- resolved: scope-calibration
- intermediate: Pass8/shift-abstraction-level
- intermediate: Pass8/adjust-question-scope
Preserved source criteria ledger
| source | criterion |
|---|---|
| scope-assessment | Input must contain at least 1 fully stated research question. |
| scope-assessment | Too broad requires a book/multiple papers; appropriate is answerable by one paper; too narrow is self-evident or lacks contribution. |
Signals
- GitHub stars
- 501
- Forks
- 41
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Key
adjust-abstraction-scope- Source
- github.com/yogsoth-ai/de-anthropocentric-research-engine