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-reviewgit 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-review)<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-review"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-review/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-review"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-review.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 Agent Snooping · line 15 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00061 | $0.02653 |
| Opus 5 | $0.00030 | $0.01326 |
| Sonnet 5 | $0.00012 | $0.00531 |
| Haiku 4.5 | $0.00006 | $0.00265 |
Grade A, and why
sdrf-review 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 5d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDRF Review Workflow
You are performing a comprehensive quality review of an SDRF file — like a peer reviewer would for a PRIDE submission or a community annotation PR.
If this context created or edited the SDRF, this workflow is an advisory
self-review only. For an approval verdict, dispatch a fresh context that follows
skills/sdrf-adversarial-review/SKILL.md; never approve work produced in the
same context.
Step 1: Load Context
- Read the SDRF content
- Detect templates from metadata or content
- If PXD available → fetch project context + publication:
mcp PRIDE → get_project_details(project_accession="PXD######") Extract PMID → mcp PubMed → get_article_metadata([pmid]) - If GitHub PR → read the diff to understand what changed
Step 2: Run Full Validation (sdrf-validate workflow)
Apply the complete validation checklist from the sdrf-validate skill.
Read spec/sdrf-proteomics/TERMS.tsv for column definitions and spec/sdrf-proteomics/sdrf-templates/templates.yaml for template metadata.
Collect all errors and warnings.
Step 3: Cross-Reference with Publication
If a publication is available:
- Does the sample count in SDRF match the paper?
- Are all conditions from the paper represented?
- Do the instruments match?
- Are demographics (age, sex) consistent with the paper?
- Is
characteristics[developmental stage]supported by the cohort description even if age is reported only at group level? - Are tissue types correctly annotated?
When Europe PMC full text is available, do not inspect raw XML directly. First run:
python scripts/europepmc_fulltext.py PMC_ID --section methods --section results --section discussion --format text
or use --format json when structured links, captions, or accession detection will help the review.
Flag any discrepancies:
DISCREPANCY: Paper says "24 patients" but SDRF has 20 unique source names.
DISCREPANCY: Paper mentions "hippocampus and temporal cortex" but SDRF only has "brain".
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.
- 5d ago Changed · -1 tokens per session cfa72d4011d4
- 11d ago First seen · 270 lines · 62 tokens per session scan A 3d2ae242b60c
sdrf-review is a skill published in the GitHub repository bigbio/sdrf-skills (18 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 2,653 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
protein-expression-analysis
This skill covers a common bioinformatics task pattern: given an Excel workbook with a large proteomics dataset on one sheet and a structured task template on another, perform two-way lookups to extract expression values, compute group statistics (mean, stdev), and calculate fold changes — all while preserving the…
sf-metadata-parser
Use this skill whenever the user wants to parse, analyze, document, or export SAP SuccessFactors OData metadata ($metadata XML). Triggers include: any mention of 'metadata', '$metadata', 'OData entities', 'entity fields', 'SF metadata', 'SuccessFactors schema', 'data dictionary', or requests to understand, compare, or…
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
nature-experiment-log
A workflow for turning experiment notes, images, audio, or text into structured Markdown laboratory logs with YAML metadata. It can also organize raw attachments and optionally connect the logs to Feishu or Obsidian.
extracting-keywords
Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), --detect-language, and the standalone embed command with real flags.