agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/de-anthropocentric-research-engine/skills/analogical-discovery/SKILL.md

analogical-discovery

Skill505 starsChanged 50 days agoApache-2.0View on GitHub

Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.

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:

    Do not perform called SOP operations inline.

    line 16

≈ “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

analogical-discovery

Purpose

Transfer a validated relational structure from a source domain into a target research problem.

Input contract

required: [target_problem, source_domain]
optional: [candidate_sources, transfer_constraints]
constraints: [source and target roles must be explicit]

Execution protocol

Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.

  1. You MUST load skill abstract-structure to abstract the relational structure.
  2. You MUST load skill map-analogy to map source relations to the target.
  3. You MUST load skill instantiate-transfer to instantiate and test the transferred mechanism. If the analogy should be expanded across a typed combination space, consider explore-dimensional-space. If biological mechanisms are the relevant source domain, consider biomimetic-transfer. If several source structures must be composed, consider conceptual-blending. If the claimed mapping requires a formal preservation audit, audit-structural-equivalence may be the better next tactic. Deviation: skip source search only when a supplied source is structurally specified; never skip mapping or transfer validation.

Output contract

produces: [abstract_structure, structural_mapping, transfer_candidate]
delta_fields: [findings, hypothesis_updates, uncertainties, decisions, open_questions]

Thresholds and quality gates

  • B: every transfer records source/target correspondences, unmapped relations, and a depth check; surface similarity alone is insufficient.

Failure and counterexamples

Reject transfers whose causal/relational roles do not map, whose target constraints are violated, or whose claimed mechanism is only lexical resemblance.

Provenance map

  • creative-ideation/cross-domain-discovery, analogical-transfer, design-by-analogy, functional-analogy, analogy-extraction, bridge-validation: resolved where exact v3 node exists; campaign/strategy labels remain concept provenance.
  • Status: all six exact names resolved against the v3 source graph.

Preserved source criteria ledger

  • Preserve deep structural correspondence and transfer viability; do not collapse to keyword similarity.

Context checkpoint / Delta notes

Append source relations, mapping gaps, transfer assumptions, and validation findings.

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