Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HolobiomicsLab/asb-skill-collections --skill fragment-file-validationgit clone --depth 1 https://github.com/HolobiomicsLab/asb-skill-collectionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/holobiomicslab/asb-skill-collections/fragment-file-validation)<a href="https://agentmods.dev/skills/holobiomicslab/asb-skill-collections/fragment-file-validation"><img src="https://agentmods.dev/badge/skills/holobiomicslab/asb-skill-collections/fragment-file-validation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/holobiomicslab/asb-skill-collections/fragment-file-validation"><img src="https://agentmods.dev/badge/skills/holobiomicslab/asb-skill-collections/fragment-file-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01518 |
| Opus 5 | $0.00020 | $0.00759 |
| Sonnet 5 | $0.00008 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
fragment-file-validation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fragment-file-validation
Summary
Validate that BAM-to-fragment file conversion produced a correctly formatted, non-empty compressed fragment file (BED.gz or .zst) with all required fields and QC metrics. This skill ensures data integrity before downstream analysis in SnapATAC2 single-cell ATAC-seq pipelines.
When to use
After invoking pp.make_fragment_file to convert a coordinate-sorted BAM file (e.g., from 10X ATAC or standard alignment) into a compressed fragment file. Use this skill to confirm the output file exists, is non-empty, contains valid BED format fields, and has computable QC metrics (duplication rate, read counts) before proceeding to matrix generation or downstream clustering.
When NOT to use
- Input is already a count matrix or peak-by-cell matrix (use directly for clustering/embedding, not fragment validation)
- Fragment file was generated by an external tool without BAM input (validation logic may differ; consult that tool's QC standards)
- Input is uncoordinate-sorted or contains unmapped reads (pre-filter or re-sort BAM before calling pp.make_fragment_file)
Inputs
- coordinate-sorted BAM file (e.g., from 10X ATAC sequencing or standard genomic alignment)
- SnapATAC2 AnnData object or file path for output destination
Outputs
- compressed fragment file (BED.gz or .zst format)
- fragment file with columns: chrom, start, end, barcode, count
- QC metrics: duplication rate per barcode, read count per barcode
How to apply
Decompress and inspect the output fragment file (BED.gz or .zst format) to verify it contains the expected four or five columns: chrom (chromosome), start (0-based start coordinate), end (end coordinate), barcode (cell barcode), and count (fragment count or quality metric). Check that the file is non-empty (contains at least header or data rows) and that all chromosomes and barcodes are valid. Compute or retrieve QC metrics including duplication rate (fraction of duplicate fragments per barcode) and total read counts per cell barcode, and confirm these values are reasonable (typically duplication rates < 50% for high-quality ATAC libraries). Validate that coordinates are sorted and non-overlapping within expected genomic ranges. If using 10X BAM input, confirm source='10x' parameter was set during pp.make_fragment_file invocation to ensure correct barcode extraction.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 97 lines · 40 tokens per session scan A 19452d84da42
fragment-file-validation is a skill published in the GitHub repository HolobiomicsLab/asb-skill-collections (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 1,518 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
gsva-analysis-and-visualization
Use this skill to run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file, then generate a heatmap from the saved GSVA result object. Trigger keywords: GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB. NOT for: gene-level differential expression…
medical-research-literature-reader-pro
A medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental backgrounds. Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper — whether they provide a PDF, abstract, DOI, PMID, or just a title.…
adverse-event-narrative
Generates CIOMS I-compliant ICSR narratives from adverse event case data for FDA and EMA regulatory submission. Includes temporal analysis, MedDRA coding, causality assessment using WHO-UMC or Naranjo criteria, and multi-format output.
anatomy-quiz-master
Generate interactive anatomy quizzes for medical education with multiple.
decision-curve-analysis
Use when evaluating the clinical utility of a binary prediction model from a single clinical CSV file by fitting a logistic decision-curve model, plotting decision and clinical-impact curves, and exporting summary outputs. NOT for: survival calibration, ROC-only discrimination analysis, nomogram construction, or…
elastic-net-feature-selection
Use when selecting predictive genes or other molecular features from bulk expression matrices for binary case-vs-control classification with elastic net logistic regression, including coefficient path and cross-validation plots. Trigger keywords: elastic net, glmnet, feature selection, binary classification…