Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generates standardized quality control reports by aggregating metrics from FastQC, alignment, and other tools using MultiQC. Use when summarizing QC metrics across samples, creating shareable quality reports, or building automated QC pipelines.
.claude/skills/bio-reporting-automated-qc-reports/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-15 | ✓→✓ | = Same ✓ | -35% | 0% |
| case-08 | ✓→✓ | = Same ✓ | -34% | 0% |
| case-09 | ✓→✓ | = Same ✓ | -17% | 0% |
| case-02 | ✓→✓ | = Same ✓ | -12% | 0% |
<!--
#
#
-->
bash# Aggregate all QC outputs in directory multiqc results/ -o qc_report/ # Specify output name multiqc results/ -n my_project_qc # Include specific tools only multiqc results/ --module fastqc --module star
MultiQC recognizes outputs from 100+ bioinformatics tools:
| Category | Tools | |----------|-------| | Read QC | FastQC, fastp, Cutadapt | | Alignment | STAR, HISAT2, BWA, Bowtie2 | | Quantification | featureCounts, Salmon, kallisto | | Variant Calling | bcftools, GATK | | Single-cell | CellRanger, STARsolo |
Create multiqc_config.yaml:
yamltitle: "RNA-seq QC Report" subtitle: "Project XYZ" intro_text: "QC metrics for all samples" # Custom sample name cleaning extra_fn_clean_exts: - '.sorted' - '.dedup' # Report sections to include module_order: - fastqc - star - featurecounts # Highlight samples table_cond_formatting_rules: pct_mapped: fail: [{lt: 50}] warn: [{lt: 70}]
bash# Add custom data file # File format: sample\tmetric1\tmetric2 multiqc results/ --data-format tsv --custom-data-file custom_metrics.tsv
pythonfrom multiqc import run as multiqc_run # Run programmatically multiqc_run(analysis_dir='results/', outdir='qc_report/')
<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | pass→pass | 10,486 | 4,357 | -58% | 1 | 1 | 0% | 1,814 | 1,173 | -35% | 0 | 0 | — |
case-08 | pass→pass | 11,139 | 3,894 | -65% | 1 | 1 | 0% | 1,966 | 1,289 | -34% | 0 | 0 | — |
case-09 | pass→pass | 6,094 | 2,170 | -64% | 1 | 1 | 0% | 1,144 | 954 | -17% | 0 | 0 | — |
case-10 | fail→fail | 10,534 | 8,839 | -16% | 1 | 1 | 0% | 1,965 | 2,213 | +13% | 0 | 0 | — |
case-01 | fail→fail | 16,762 | 13,364 | -20% | 1 | 1 | 0% | 3,335 | 3,258 | -2% | 0 | 0 | — |
case-02 | pass→pass | 7,703 | 3,952 | -49% | 1 | 1 | 0% | 1,428 | 1,263 | -12% | 0 | 0 | — |
case-07 | pass→pass | 8,601 | 5,448 | -37% | 1 | 1 | 0% | 1,579 | 1,612 | +2% | 0 | 0 | — |
case-03 | pass→pass | 2,968 | 1,854 | -38% | 1 | 1 | 0% | 502 | 915 | +82% | 0 | 0 | — |
case-04 | pass→pass | 7,547 | 2,792 | -63% | 1 | 1 | 0% | 1,377 | 1,083 | -21% | 0 | 0 | — |
case-05 | pass→pass | 3,796 | 2,040 | -46% | 1 | 1 | 0% | 711 | 951 | +34% | 0 | 0 | — |
case-06 | pass→pass | 9,146 | 5,592 | -39% | 1 | 1 | 0% | 1,767 | 1,661 | -6% | 0 | 0 | — |
case-11 | fail→pass | 9,001 | 3,588 | -60% | 1 | 1 | 0% | 1,698 | 1,314 | -23% | 0 | 0 | — |
case-12 | pass→pass | 8,266 | 2,998 | -64% | 1 | 1 | 0% | 1,498 | 1,151 | -23% | 0 | 0 | — |
case-13 | pass→pass | 10,524 | 1,787 | -83% | 1 | 1 | 0% | 1,841 | 848 | -54% | 0 | 0 | — |
case-14 | pass→pass | 11,584 | 9,077 | -22% | 1 | 1 | 0% | 2,055 | 2,221 | +8% | 0 | 0 | — |
case-16 | pass→pass | 25,861 | 10,638 | -59% | 1 | 1 | 0% | 2,314 | 2,463 | +6% | 0 | 0 | — |
case-17 | pass→pass | 13,959 | 2,008 | -86% | 1 | 1 | 0% | 2,427 | 903 | -63% | 0 | 0 | — |
case-18 | pass→pass | 2,149 | 1,986 | -8% | 1 | 1 | 0% | 400 | 929 | +132% | 0 | 0 | — |
case-19 | pass→pass | 6,555 | 4,939 | -25% | 1 | 1 | 0% | 1,223 | 1,494 | +22% | 0 | 0 | — |
case-20 | pass→pass | 7,336 | 5,179 | -29% | 1 | 1 | 0% | 1,364 | 1,641 | +20% | 0 | 0 | — |
case-21 | pass→pass | 11,028 | 9,485 | -14% | 1 | 1 | 0% | 2,115 | 1,791 | -15% | 0 | 0 | — |
case-22 | pass→pass | 13,450 | 13,653 | +2% | 1 | 1 | 0% | 2,771 | 3,360 | +21% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/24/2026 | +9% |
Other measured skills in the registry, with their headline benchmark lift.