agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/de-anthropocentric-research-engine/skills/audit-convergence-independence/SKILL.md

audit-convergence-independence

Skill505 starsChanged 50 days agoApache-2.0View on GitHub

Audit claims of independent convergence by tracing shared priors, data, framing, models, prompts, assumptions, or upstream evidence; estimate an effective independent evidence count rather than treating nominal N paths as independent.

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

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 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 21
  2. Distinctive:

    Do not call repeated use of the same dataset, model, prompt, or source independent.

    line 41

≈ “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-convergence-independence

Purpose

Estimate how much nominally independent convergence remains after shared priors, data, models, prompts, framings, assumptions, and upstream evidence are discounted.

Input contract

mode_contracts:
  evidence-paths: &convergence_audit_input
    required: [evidence_paths, claims, provenance_records]
    optional: [dependency_schema, correlation_estimates]
    constraints: [each_path_must_be_traceable_to_its_inputs_and_assumptions]
  agents: *convergence_audit_input
  models: *convergence_audit_input
  methods: *convergence_audit_input

Execution protocol

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

  1. You MUST load skill identify-shared-priors to enumerate paths, provenance, and shared priors.
  2. You MUST load skill verify-evidence-independence to verify independence and mark shared dependencies.
  3. You MUST load skill estimate-effective-evidence-count to estimate the effective evidence count. You MUST load skill assess-sensitivity to perturb dependence assumptions. Deviation: use qualitative dependence classes when numeric correlation is unavailable; never count nominal paths as independent by default.

Output contract

mode_contracts:
  evidence-paths: &convergence_audit_output
    produces: [independence_ledger, effective_evidence_count, common_cause_framing, independent_path_result_or_design, correlated_errors, corrected_confidence_statement]
    delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
  agents: *convergence_audit_output
  models: *convergence_audit_output
  methods: *convergence_audit_output

Thresholds and quality gates

  • A-class sufficiency: declared universe = all claimed evidence/reasoning paths; numerator = paths with complete provenance and independence assessment; batch increment = one newly traced path; stopping reason = effective count stabilizes or remaining paths are dependent/irrelevant; source references = path IDs, source IDs, model/prompt IDs; direction/threshold reason = lower effective count when shared dependencies increase.
  • Report nominal N and N_eff separately.

Failure and counterexamples

Do not call repeated use of the same dataset, model, prompt, or source independent. Mark N_eff uncertain when dependence cannot be resolved.

Provenance map

  • resolved: independent-convergence-audit

Preserved source criteria ledger

sourcesource linekindsource criterion
v4 architecturenode desctextualTrace shared priors and estimate effective independent evidence count.

Context checkpoint / Delta notes

Append path provenance, shared dependencies, N, N_eff, uncertainty, and sensitivity assumptions.

Mode branches

  • evidence-paths: compare source and reasoning paths.
  • agents: compare agent-level dependence.
  • models: compare model/prior dependence.
  • methods: compare methodological dependence.

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