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-validategit 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-validate)<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-validate"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-validate/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-validate"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-validate.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 | $0.00042 | $0.04079 |
| Opus 5 | $0.00021 | $0.02039 |
| Sonnet 5 | $0.00008 | $0.00816 |
| Haiku 4.5 | $0.00004 | $0.00408 |
Grade A, and why
sdrf-validate 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 2d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDRF Validation Workflow
You are validating an SDRF file. Perform systematic checks in order.
Step 0: Check parse_sdrf availability
Verify that parse_sdrf is available (run parse_sdrf --version or which parse_sdrf). If it is not installed:
- Inform the user that programmatic validation with parse_sdrf will be skipped
- Suggest
/sdrf-skills:sdrf-setuporconda env create -f environment.yml && conda activate sdrf-skills(orpip install -r requirements.txt) - Continue with structural and ontology checks; manual validation is still valuable
Step 0.5: Protect the Machine During Validation
Validation can be expensive because parse_sdrf may trigger ontology lookups,
template loading, and large file parsing.
Use these resource guards:
- Default to serial validation for autonomous loops unless there is a clear reason to parallelize
- If validating multiple SDRFs in parallel, keep the concurrency small: at most
2parse_sdrfjobs at a time - If
techsdrf, raw-file conversion, or other heavy IO/CPU work is running, validate only1SDRF at a time - Validate changed datasets first, not the whole collection by default
- Prefer batch manifests or representative smoke checks before full-sandbox sweeps
- For large SDRFs, validate unique values once rather than re-checking repeated ontology terms row by row
If the machine looks stressed or validation becomes unresponsive, reduce concurrency before continuing.
Step 1: Parse the SDRF
- Read the SDRF content (from file path or pasted content)
- Count rows (samples/runs) and columns
- Check for SDRF metadata:
comment[sdrf version],comment[sdrf template]
Step 2: Detect Templates
- If
comment[sdrf template]exists → extract template names and versions Format:NT=ms-proteomics;VV=v1.1.0orms-proteomics v1.1.0 - If not → auto-detect from content using these rules:
| Detection Signal | Template |
|---|---|
technology type = "proteomic profiling by mass spectrometry" |
ms-proteomics |
technology type = "protein expression profiling by aptamer array" |
somascan |
technology type = "protein expression profiling by antibody array" |
olink |
characteristics[organism] = Homo sapiens |
human |
characteristics[organism] = Mus musculus / Rattus / Danio |
vertebrates |
characteristics[organism] = Drosophila / C. elegans |
invertebrates |
characteristics[organism] = Arabidopsis / Oryza |
plants |
| DIA acquisition method | dia-acquisition |
characteristics[cell line] present |
cell-lines |
characteristics[mhc protein complex] present |
immunopeptidomics |
comment[cross-linker] present |
crosslinking |
characteristics[single cell isolation protocol] present |
single-cell |
characteristics[environmental sample type] present |
metaproteomics |
characteristics[tumor grading] or characteristics[tumor stage] |
oncology-metadata |
comment[panel name] or comment[olink panel] present |
olink |
comment[somascan menu] present |
somascan |
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.
- 2d ago Changed 83eac8143a77
- 8d ago First seen · 305 lines · 42 tokens per session scan A 486dedd7d050
sdrf-validate is a skill published in the GitHub repository bigbio/sdrf-skills (18 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 4,079 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
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.
proteomics-data-import
Load when ingesting a MaxQuant proteinGroups.txt, FragPipe combinedprotein.tsv, DIA-NN report, or generic CSV / TSV protein-quantification table — normalises columns to a standard schema, emits tables/proteins.csv. Skip when raw spectra are the input (run the search engine first); the file is already OmicsClaw schema.
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.
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.
proteomics-identification
Load when summarising peptide identifications (PSM count, unique peptide count, distinct protein count, score / charge distributions) from a peptide-level CSV produced by MaxQuant / FragPipe / DIA-NN. Skip when raw spectra are the input (run a search engine first); working with protein-quantification tables (use…
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…