agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/audit-structural-equivalence/SKILL.md

audit-structural-equivalence

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Audit a claimed isomorphism/equivalence by constructing an explicit mapping, testing which structures/operations/invariants are preserved, searching counterexamples, and downgrading the claim to the strongest defensible relation when full isomorphism fails.

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

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    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 22
  2. Very specific:

    All required relations, operations, and invariants must have pass/fail/unknown status.

    line 40
  3. Distinctive:

    Do not infer equivalence from surface similarity.

    line 43

≈ “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

audit-structural-equivalence

Purpose

Audit a claimed isomorphism or equivalence and downgrade it to the strongest defensible relation when preservation fails.

Input contract

mode_contracts:
  isomorphism: &structural_audit_input
    required: [source_structure, target_structure, equivalence_claim]
    optional: [required_invariants, operations, constraints]
    constraints: [mapping_domains_and_preservation_obligations_must_be_explicit]
  substructure: *structural_audit_input
  homomorphism: *structural_audit_input
  shared-invariant: *structural_audit_input
  analogy: *structural_audit_input

Execution protocol

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

  1. You MUST load skill extract-structural-mapping to construct the object, relation, operation, and invariant mapping.
  2. You MUST load skill test-structure-preservation to test preservation. You MUST load skill generate-counterexample to search minimal counterexamples.
  3. You MUST load skill downgrade-equivalence-claim to downgrade the claim and record lost invariants. Deviation: if the claim is only analogy by scope, run the analogy branch and do not report isomorphism.

Output contract

mode_contracts:
  isomorphism: &structural_audit_output
    produces: [claimed_sides, maps_attempted, monsters_found, dimension_count_result, highest_defended_rung, required_wording_change]
    delta_fields: [findings, evidence_updates, uncertainties, decisions]
  substructure: *structural_audit_output
  homomorphism: *structural_audit_output
  shared-invariant: *structural_audit_output
  analogy: *structural_audit_output

Thresholds and quality gates

  • All required relations, operations, and invariants must have pass/fail/unknown status.
  • A full equivalence claim fails on one unprincipled preservation counterexample.

Failure and counterexamples

Do not infer equivalence from surface similarity. Exclusions introduced only after a counterexample are ad hoc unless independently justified.

Provenance map

  • resolved: isomorphism-falsification

Preserved source criteria ledger

sourcesource linekindsource criterion
v4 architecturenode desctextualPreserve structures/operations/invariants; downgrade when full equivalence fails.

Context checkpoint / Delta notes

Append mapping, tested invariants, counterexamples, and final relation.

Mode branches

  • isomorphism: all declared structures and operations must preserve.
  • substructure: test inclusion only.
  • homomorphism: test operation-preserving mapping with relaxed structure.
  • shared-invariant: test named invariant subset.
  • analogy: report transferable relation without equivalence claim.

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