Identify Shared Priors

Trace supposedly independent evidence/reasoning paths to shared priors, datasets, models, prompts, framings, assumptions, or upstream sources that induce correlated errors.

yogsoth-ai Updated 512 repo stars
No DARE runtime: 271 SKILL.md files executed by any capable agent, instead of a seven-layer framework stack

File contents

identify-shared-priors

Purpose

Trace supposedly independent paths to shared priors, datasets, models, prompts, framings, assumptions, or upstream sources.

Input contract

required: [evidence_paths, provenance_records]
optional: [prompt_records, model_records, upstream_sources]
constraints: [shared dependency identity and path membership must be explicit]

Procedure

  1. Inventory each path's inputs and assumptions.
  2. Match shared priors, data, models, prompts, framing, and upstream evidence.
  3. Produce dependency clusters and unresolved provenance.

If shared priors and dependence groups are explicit, consider estimate-effective-evidence-count as the next tactic.

Output contract

produces: [shared_prior_map, dependency_clusters, unresolved_links]
delta_fields: [findings, evidence_updates, uncertainties, open_questions]

Quality gates

  • Similar conclusions alone are not evidence of shared priors; trace the dependency.

Failure and counterexamples

Mark provenance unknown rather than inferring common origin from naming similarity.

Provenance map

  • resolved: independent-convergence-audit

yogsoth-ai/de-anthropocentric-research-engine commit d21bd6e0ef

Frequently asked questions

npx get-skill add yogsoth-ai/identify-shared-priors