sdrf-design

sdrf-design is a skill for Claude Code from bigbio/sdrf-skills. It costs 35 tokens per session (1,380 once invoked), scanned A, original, MIT.

A design-checking guide for SDRF files, which describe how biological samples were arranged and measured in an experiment.

In plain words
What is it for?
Use it to summarize experimental conditions, biological and technical replicates, fractions, labels, instruments, and files per sample.
Why use it?
It helps find batch effects, hidden confounding factors, and replication mistakes before they weaken the analysis.

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 summarize experimental conditions, biological and technical replicates, fractions, labels, instruments, and files per sample.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-design/github.svg)](https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-design)
Your own site
<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-design"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-design/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-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-design"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,380 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 pass 7 Sept 2026
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 $0.00035 $0.01380
Opus 5 $0.00017 $0.00690
Sonnet 5 $0.00007 $0.00276
Haiku 4.5 $0.00003 $0.00138

Measured 4d ago against content hash 50de4513718a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sdrf-design 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 4d 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-design/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDRF Experimental Design Analysis

You are analyzing the experimental design captured in an SDRF file to detect statistical and methodological issues.

Step 1: Parse the Design

Extract from the SDRF:

  • Conditions: Unique values in factor value columns
  • Samples per condition: Count of unique source names per condition
  • Biological replicates: From characteristics[biological replicate]
  • Technical replicates: From comment[technical replicate]
  • Fractions: From comment[fraction identifier]
  • Labels: From comment[label]
  • Instruments: From comment[instrument]
  • Files per sample: Count of rows per source name

Exclude non-biological channels before counting replicates or testing balance. Drop rows that are reference / carrier / bridge / empty / pooled / control — characteristics[sample type] in {reference, bridge, carrier, empty, pooled, ...-control}, or rows carrying comment[carrier channel] (PRIDE:0000901) / comment[reference channel] (PRIDE:0000899). Counting them inflates n and corrupts the TMT/label cross-tabs. Replication = unique source name per condition, not raw row count.

Step 2: Design Summary

Present a clear summary:

Experimental Design Summary:
  Type: Two-group comparison
  Factor: disease (breast carcinoma vs normal)

  Group 1 "breast carcinoma": 10 biological replicates
  Group 2 "normal": 10 biological replicates

  Technical setup:
    Label: TMT10plex (10 channels per plex)
    Fractions: 12 per TMT set
    Technical replicates: 1 per sample
    Instrument: Q Exactive HF

  File math:
    2 TMT sets × 12 fractions = 24 raw files
    Each file → 10 rows (one per TMT channel)
    Total SDRF rows: 240

  Statistical power:
    n=10 per group — adequate for detecting medium effect sizes

Step 3: Batch Effect Detection

Cross-tabulate factor values against technical variables:

Instrument Confounding

Check: Is "condition" confounded with "instrument"?
  Cross-tab factor value × comment[instrument]

  BAD:  All "disease" on Instrument A, all "control" on Instrument B
        → Cannot separate biology from instrument effect

  GOOD: Both conditions measured on both instruments (balanced)

Read the full file on GitHub · 173 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. 4d ago Changed · -1 tokens per session 50de4513718a
  2. 10d ago First seen · 173 lines · 36 tokens per session scan A 84228efd3dec

Subscribe to this mod's changes

sdrf-design is a skill published in the GitHub repository bigbio/sdrf-skills (18 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 1,380 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

uniprot-query

Query UniProt database for protein sequences, metadata, and search by criteria. Use this skill when: (1) Looking up protein information by UniProt accession ID, (2) Searching proteins by gene name, organism, function, or disease, (3) Retrieving comprehensive protein metadata including domains, PTMs, and annotations.

PharMolix/OpenBioMed · 71 tokens

proteomics-de

Load when computing two-group differential protein abundance (group2 vs group1, log2FC + p-value + BH-adjusted FDR) via Welch t-test, equal-variance t-test, or Mann-Whitney on a wide protein × sample CSV. Skip when you need multi-condition DE (run pairwise contrasts manually); label-based TMT linear-mixed models.

TianGzlab/OmicsClaw · 79 tokens

proteomics-enrichment

Load when running over-representation analysis (ORA) on a list of proteins via Fisher's exact test against a built-in 8-pathway DEMO dictionary, with BH-FDR correction. Skip when needing a real pathway database (this skill is demo-only) (use bulkrna-enrichment); rank-based GSEA.

TianGzlab/OmicsClaw · 70 tokens

proteomics-ptm

Load when summarising PTM sites (phosphorylation, acetylation, ubiquitination, etc.) from a per-site CSV — site-class assignment (Olsen et al. Class I/II/III by localizationprobability), per-PTM-type counts, amino-acid distribution, sites-per-protein. Skip when raw spectra are the input; you only need protein-level…

TianGzlab/OmicsClaw · 95 tokens

proteomics-quantification

Load when computing per-protein abundance from a peptide / PSM table via LFQ (intensity summation), iBAQ (intensity / tryptic peptide count), or spectral counting (PSMs per protein). Skip when the input is already protein-level (use proteomics-ms-qc); label-based TMT / iTRAQ workflows (search upstream first).

TianGzlab/OmicsClaw · 80 tokens

proteomics-structural

Load when summarising cross-linking MS (XL-MS) results — intra/inter-protein link split, optional FDR filtering, distance-constraint validation against a per-crosslinker (DSS / BS3 / EDC / DSSO / DSBU) max distance. Skip when raw spectra are the input (run XlinkX / pLink / xiSEARCH first); no XL-MS experiment was…

TianGzlab/OmicsClaw · 88 tokens