ml-auditor
Skill10 starsChanged 6 days agoMITView on GitHub
Audits a labelled dataset for leakage and label errors with scikit-learn, and optionally takes a second opinion from cleanlab. Runs inside the process sandbox; missing dependencies degrade the gate to `UNVERIFIED`.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/chelate-shell.mdcCursor rule
- 3d-modelerSkill
- ai-trace-removerSkill
- bibtex-normalizerSkill
- capstone-labmateSkill
- conflict-detectorSkill
- data-profilerSkill
- document-evolution-trackerSkill
- formula-validatorSkill
- fulltext-extractorSkill
- latex-exporterSkill
- literature-retrieverSkill
- longitudinal-analysisSkill
- multi-dim-managerSkill
- quantitative-validatorSkill
- reference-auditorSkill
- sci-visualizerSkill
- security-guardSkill
- task-organizerSkill
- video-trackerSkill
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
- Distinctive: line 25
Run this exact form — do not read the source tree:
≈ “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.
Files
ml-auditor
Detects data leakage (a feature that encodes the target) and suspicious labels in a CSV. It audits the dataset; it does not train your final model.
- Stage:
gates· Sandbox: yes · Dependencies:scikit-learn,pandas(cleanlaboptional)
Quick Execution
Run this exact form — do not read the source tree:
python scripts/run.py --root <WS> --action gate --input data.csv --label target--labelmay be omitted; the target column is then auto-detected.--datais an alias of--input.- The gate lands in
<WS>/process/gates/ml-auditor_<ts>.json.
When to use
- A supervised dataset is about to be used for training or reporting.
- A model reports suspiciously high accuracy.
When NOT to use
- Unlabelled data — there is no target to audit.
- You want the model trained or tuned.
Actions
--action | Does | Extra arguments |
gate | Leakage + label-error audit | --input|--data <csv> [--label <col>] |
Hard constraints
- Never modify the dataset. The audit is read-only.
- Report leakage, do not silently drop the feature.
Outputs
<WS>/process/gates/ml-auditor_<ts>.json— the gate result with suspects listed.
Failure handling
- A CSV without a usable target fails the gate.
scikit-learnmissing →UNVERIFIED.
Limitations
- Heuristic leakage detection; every suspect must be reviewed.
cleanlabis optional and only refines the label report.
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
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.