sdrf-techrefine

sdrf-techrefine is a skill for Claude Code from bigbio/sdrf-skills. It costs 44 tokens per session (3,702 once invoked), scanned A, original, MIT.

A workflow for checking and correcting technical metadata in SDRF files using analysis of raw mass-spectrometry data. SDRF is a tabular format that describes how proteomics experiments were run.

In plain words
What is it for?
Use it to download and inspect raw MS files, refine instrument and method fields, detect DDA or DIA acquisition, and identify supported or unsupported file-conversion requirements.
Why use it?
Manually entered experiment details can be incomplete or wrong, so raw-file analysis provides evidence for values such as instruments, mass tolerances, modifications, and acquisition mode.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the sdrf-skills plugin — 16 skills, 2 hooks, 1 MCP server shipped together

Good fit Use it to download and inspect raw MS files, refine instrument and method fields, detect DDA or DIA acquisition, and identify supported or unsupported file-conversion requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bigbio/sdrf-skills/sdrf-techrefine
Install

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.

Any agent
npx skills add bigbio/sdrf-skills --skill sdrf-techrefine
Clone the repo
git clone --depth 1 https://github.com/bigbio/sdrf-skills

Made for: Claude Code.

Or install sdrf-skills, the plugin that ships this one along with the rest of its 16 skills, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for sdrf-techrefine

README.md
[![agentmods](https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-techrefine/github.svg)](https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-techrefine)
Your own site
<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.

agentmods 80×15 button for sdrf-techrefine

Your own site · 80×15
<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>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,702 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 897e76047a85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/sdrf-techrefine/SKILL.md · 329 lines

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
    # Check availability:
    msconvert --help
    
    For Bruker DIA isolation windows specifically, no converter and no download are needed — python -m tools bruker-dia range-reads analysis.tdf out 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.

Read the full file on GitHub · 329 lines

Changes

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.

  1. 3d ago Changed · -1 tokens per session 897e76047a85
  2. 9d ago First seen · 329 lines · 45 tokens per session scan A 6560af68f074

Subscribe to this mod's changes

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.

Related

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.

MannLabs/proteomics-agent-skills · 75 tokens

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.

MannLabs/proteomics-agent-skills · 41 tokens

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…

MannLabs/proteomics-agent-skills · 78 tokens

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.

MannLabs/proteomics-agent-skills · 61 tokens

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…

K-Dense-AI/scientific-agent-skills · 66 tokens

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.

K-Dense-AI/scientific-agent-skills · 61 tokens