agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/adjust-abstraction-scope/SKILL.md

adjust-abstraction-scope

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

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.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every changed dimension is named with before/after values.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

adjust-abstraction-scope

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

  1. Record object, current level, and scope dimensions (population, mechanism, context, outcome, timeframe, boundary).
  2. Generate at least one upward and one downward abstraction candidate when leverage is unclear.
  3. For each candidate, state what is gained, lost, and newly testable.
  4. 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

sourcecriterion
scope-assessmentInput must contain at least 1 fully stated research question.
scope-assessmentToo broad requires a book/multiple papers; appropriate is answerable by one paper; too narrow is self-evident or lacks contribution.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free