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

audit-data-contamination

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Audit train/test leakage, memorization artifacts, temporal leakage, and disclosure pathways that can invalidate evaluation.

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:

    Test suspected leakage pathways and compare affected with unaffected cases.

    line 24
  2. Distinctive:

    Do not call lexical overlap contamination without a disclosure pathway, and do not infer clean separation from missing metadata.

    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-data-contamination

Purpose

Audit train/test leakage, memorization artifacts, temporal leakage, and disclosure pathways that can invalidate evaluation.

Input contract

required: [dataset_partitions, training_sources, evaluation_records]
optional: [release_history, deduplication_keys, access_logs]
constraints: [each contamination claim requires a matched record, pathway, and comparison basis]

Procedure

  1. Define partition, temporal, entity, and disclosure boundaries.
  2. Match evaluation items against training and public-source records using declared keys.
  3. Test suspected leakage pathways and compare affected with unaffected cases.
  4. Classify confirmed, plausible, and unassessed contamination with impact notes.

Output contract

produces: [contamination_matches, pathway_map, affected_case_set, impact_assessment, audit_uncertainties]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]

Quality gates

  • Matching keys and time boundaries are recorded.
  • False-positive matches are sampled and documented.

Failure and counterexamples

Do not call lexical overlap contamination without a disclosure pathway, and do not infer clean separation from missing metadata.

Provenance map

  • resolved: knowledge-acquisition-contamination-audit

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