agentsclimarketplace

Bio stats ml reporting

Skill fmschulz/omics-skills/skills/bio-stats-ml-reporting

Analyze biological results with statistics or machine learning and produce validated reports. Use when aggregating features, testing hypotheses, training models, or reporting performance.From its SKILL.md

Install
npx -y skills add fmschulz/omics-skills --skill bio-stats-ml-reporting

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 2 commands, including `scripts/validate_predictions.py` and 1 more.

SKILL.md

5.1 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

Bio Stats ML Reporting

Aggregate results, train ML models, and produce reports with validated references.

Instructions

  1. Join outputs in DuckDB v1.1+ and build feature tables. Arrow / DuckLake integration is the recommended bridge into ML pipelines for large datasets.
  2. Train baseline models and evaluate with cross-validation.
    • CPU baseline: scikit-learn v1.5+ for linear/tree/clustering baselines; XGBoost v2.1.4+ for gradient boosting.
    • GPU node available (CUDA): set device="cuda" on XGBoost (native since v2.0) by default. For sklearn-compatible estimators (random forest, k-means, PCA, UMAP), use RAPIDS cuML as a drop-in replacement and record the device in the run log.
  3. Generate reports and validate references.
    • Validate the prediction table with scripts/validate_predictions.py. Keep group identifiers and confounder labels in the table so the gate can detect sample/group leakage, class imbalance, calibration failure, batch-outcome imbalance, and performance that does not beat the majority-class null.
  4. For exploratory omics projects, aggregate discovery evidence across the literature-derived analysis playbook, annotation, phylogenomics, viromics, and comparative-genomics outputs.
  5. Comparative-axes rollup — join the per-axis comparison artifacts produced by upstream skills into a single comparative_axes_summary.tsv. The rollup must have one row per (query genome, axis) and include:
    • genome-property frontier (size, gene count, etc. — link to relative_genome_metrics.tsv and genome_size_frontier.tsv)
    • marker-gene census (link to marker_census.tsv)
    • family copy-number expansions/contractions (link to family_copy_number_comparison.tsv and family_expansion_candidates.tsv)
    • synteny / conserved neighborhoods (link to conserved_neighborhoods.tsv)
    • non-coding RNA census (link to ncRNA_census.tsv) Each row records observation, comparison baseline, literature reference, status (notable / conserved / artifact / negative), and a follow-up test.
  6. Produce an interesting-findings section that ranks candidate discoveries relative to the literature-derived baseline and separates:
    • strong candidates with multiple evidence types
    • plausible candidates needing validation
    • likely artifacts or conserved lineage features
    • explicit negative findings where nothing notable was detected
  7. Include the comparison baseline, literature context, confidence, and next discriminating analyses for each candidate.

Quick Reference

TaskAction
Run workflowFollow the steps in this skill and capture outputs.
Validate inputsConfirm required inputs and reference data exist.
Review outputsInspect reports and QC gates before proceeding.
Tool docsSee docs/README.md.
Validate predictionsuv run --no-project python scripts/validate_predictions.py predictions.tsv --report validation.json --require-beats-null

Input Requirements

Prerequisites:

  • Tools declared in the project's pinned Pixi environment. See docs/README.md for expected tools.
  • Results tables and metadata are available. Inputs:
  • results/.parquet or results/.tsv
  • metadata.tsv

Output

  • results/bio-stats-ml-reporting/models/
  • results/bio-stats-ml-reporting/metrics.tsv
  • results/bio-stats-ml-reporting/comparative_axes_summary.tsv
  • results/bio-stats-ml-reporting/discovery_summary.tsv
  • results/bio-stats-ml-reporting/report.md
  • results/bio-stats-ml-reporting/logs/
  • results/bio-stats-ml-reporting/prediction_validation.json

Quality Gates

  • Model performance sanity checks pass.
  • Reference validation passes.
  • On failure: retry with alternative parameters; if still failing, record in report and exit non-zero.
  • Verify input tables are readable and schema-consistent.
  • Discovery summary joins candidate genes/features to annotation evidence, comparison baseline, literature context, and confidence.
  • comparative_axes_summary.tsv covers all five mandatory axes (genome-property frontier, marker-gene census, family copy-number, synteny/neighborhoods, ncRNA census) for every query genome, with rows for axes that produced negative findings.
  • Final report states what is interesting, what is conserved/expected, what is likely artifact, and what should be tested next.
  • Grouped splits have no sample or group overlap, calibration is reported, confounding and imbalance are quantified, and the model is compared with a declared null baseline.

Examples

Example 1: Expected input layout

results/*.parquet or results/*.tsv
metadata.tsv

Troubleshooting

Issue: Missing inputs or reference databases Solution: Verify paths and permissions before running the workflow.

Issue: Low-quality results or failed QC gates Solution: Review reports, adjust parameters, and re-run the affected step.

What ships with it: 11 files

52.9 KB alongside SKILL.md, 1 of them executable

fixtures/

scripts/

Gives 0 of the 12 instructions most docs writing skills give in ~1.1k tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

  • Use third-person for skill descriptionsin 54 of 1951, across 35 files
  • Start descriptions with Use whenin 43 of 1951, across 29 files
  • Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
  • Use active voicein 40 of 1951, across 36 files
  • Map file responsibilities before defining tasksin 36 of 1951, across 29 files
  • Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
  • Ask one question at a timein 35 of 1951
  • Offer execution options after saving the planin 33 of 1951, across 24 files
  • Include complete code in every stepin 33 of 1951, across 27 files
  • Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
  • Announce the skill usage at the startin 30 of 1951
  • Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

  • Join outputs using DuckDB to build feature tables
  • Train baseline models using scikit-learn or XGBoost
  • Use RAPIDS cuML for GPU acceleration when available
  • Validate prediction tables using the provided script
  • Aggregate discovery evidence across omics outputs
  • Create a comparative axes summary file

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 611,919. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.