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 bigbio/sdrf-skills --skill sdrf-techrefinegit clone --depth 1 https://github.com/bigbio/sdrf-skillsWrote 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/bigbio/sdrf-skills/sdrf-techrefine)<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-techrefine"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-techrefine/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/bigbio/sdrf-skills/sdrf-techrefine"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-techrefine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 324 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00044 | $0.03702 |
| Opus 5 | $0.00022 | $0.01851 |
| Sonnet 5 | $0.00009 | $0.00740 |
| Haiku 4.5 | $0.00004 | $0.00370 |
Grade A, and why
sdrf-techrefine 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 3d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDRF Technical Metadata Refinement Workflow
You are guiding the user through refining SDRF technical metadata using techsdrf — a CLI tool that downloads raw MS files, analyzes them with pyopenms, and auto-detects instrument parameters, mass tolerances, PTMs, and DDA/DIA mode.
This workflow verifies and corrects technical columns that are often filled manually from PRIDE metadata or publications, which may be incomplete or inaccurate.
Step 1: Check Prerequisites
1.1 Verify techsdrf is installed
techsdrf --version
# If not installed:
pip install techsdrf
1.2 Verify raw file converters (as needed)
- Thermo .raw files: ThermoRawFileParser is required
conda install -c bioconda thermorawfileparser - Bruker .d / SCIEX .wiff files: msconvert (ProteoWizard) is required
For Bruker DIA isolation windows specifically, no converter and no download are needed —# Check availability: msconvert --helppython -m tools bruker-diarange-readsanalysis.tdfout of the archive. See the Bruker section below.
If converters are missing, inform the user which file types cannot be processed and suggest installation commands. techsdrf will skip files it cannot convert.
Step 2: Choose Refinement Mode
Present the three modes and help the user choose:
Mode A — Refine from PRIDE (recommended for PXD datasets)
Downloads raw files from PRIDE, analyzes them, and refines the SDRF.
techsdrf refine -p PXD###### -s input.sdrf.tsv -o refined.sdrf.tsv -v
Use when: The user has a PXD accession and an SDRF file to refine.
Mode B — Refine from local files
Points to a local directory of raw files instead of downloading from PRIDE.
techsdrf refine -d /path/to/raw/files -s input.sdrf.tsv -o refined.sdrf.tsv -v
Use when: The user already has raw files locally.
Mode C — Info only (inspect without refining)
Inspects the current SDRF technical metadata without downloading or analyzing files.
techsdrf info -s input.sdrf.tsv
Use when: The user wants a quick check of what technical metadata is declared.
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.
- 3d ago Changed · -1 tokens per session 897e76047a85
- 9d ago First seen · 329 lines · 45 tokens per session scan A 6560af68f074
sdrf-techrefine is a skill published in the GitHub repository bigbio/sdrf-skills (18 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 3,702 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 2026-08-30.
Other skills, from other repositories
interpreting-biological-results
Interpret biological results from omics analyses. Use when (1) performing overrepresentation analysis (ORA) on significant gene/protein lists, (2) running gene set enrichment analysis (GSEA) on ranked features, (3) querying STRING/UniProt for protein function, or (4) annotating clusters with pathway information.
applying-code-standards
Apply code quality standards for scientific data analysis. ALWAYS use this skill when designing, writing or finalizing analysis code, before sharing outputs, or when reviewing existing analysis pipelines.
imputing-proteomics-data
Impute missing values in protein-level proteomics data matrices. Use when (1) preparing proteomics data for downstream analyses requiring complete matrices (PCA, batch correction), (2) evaluating whether imputation is needed, (3) selecting appropriate imputation methods, or (4) assessing imputation quality. Does NOT…
reading-proteomics-data
Read proteomics search engine outputs (PSM tables, protein matrices) from search engines like DIA-NN, MaxQuant, Spectronaut, AlphaDIA, MSFragger, Sage. Use for ingesting data, mapping columns to standard names, and initial filtering.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.