Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Cellfree Rna Agent · FreedomIntelligence | DecimalAI

Cellfree Rna Agent

SkillScore73Maintained

cellfree-rna-agent

AI-powered cell-free RNA analysis from liquid biopsy for cancer detection, tissue-of-origin identification, and non-invasive transcriptomic profiling.

scienceby FreedomIntelligence

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/cellfree-rna-agent/SKILL.md

decimalai skills pull cellfree-rna-agent --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cellfree-rna-agent/SKILL.md https://app.decimal.ai/s/cellfree-rna-agent/SKILL.md

Raw file: /s/cellfree-rna-agent/SKILL.md ↗ · machine-readable summary at /s/cellfree-rna-agent.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 50d ago

Yes — +14% lift · at higher cost+57% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-06	✗→✓	▲ Improved	29%	0%
case-20	✗→✓	▲ Improved	-19%	0%
case-22	✗→✓	▲ Improved	-28%	0%
case-08	✓→✓	＝ Same ✓	37%	0%
case-09	✓→✓	＝ Same ✓	29%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

FreedomIntelligence / OpenClaw-Medical-Skills

skills/cellfree-rna-agent/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v2

Skill contents

SKILL.md

<!--

COPYRIGHT NOTICE

This file is part of the "Universal Biomedical Skills" project.

Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>

All Rights Reserved.

This code is proprietary and confidential.

Unauthorized copying of this file, via any medium is strictly prohibited.

Provenance: Authenticated by MD BABU MIA

-->

Cell-Free RNA Analysis Agent

The Cell-Free RNA Analysis Agent provides comprehensive analysis of circulating cell-free RNA (cfRNA) from plasma and other biofluids for cancer detection, tissue-of-origin identification, and non-invasive transcriptomic profiling.

When to Use This Skill

When analyzing plasma cfRNA for cancer detection and monitoring.
To identify tissue-of-origin from circulating transcripts.
For non-invasive transcriptomic profiling of tumors.
When integrating cfRNA with cfDNA for comprehensive liquid biopsy.
To discover RNA-based biomarkers from accessible biofluids.

Core Capabilities

cfRNA Profiling: Quantify mRNA, lncRNA, and small RNA from plasma.

Tissue Deconvolution: Identify tissue sources contributing to cfRNA pool.

Cancer Detection: ML models detecting cancer from cfRNA profiles.

Tumor Transcriptomics: Infer tumor gene expression non-invasively.

Integration with cfDNA: Combine RNA and DNA liquid biopsy analytes.

Biomarker Discovery: Identify diagnostic and prognostic RNA markers.

cfRNA Biology

Sources:

Cell death (apoptosis, necrosis)
Active secretion (EVs, RNA-binding proteins)
Cell surface-associated RNA

Protection Mechanisms:

Extracellular vesicles
Protein complexes (AGO2, NPM1)
Lipoproteins

Half-life: Minutes to hours (shorter than cfDNA)

Workflow

Input: Plasma cfRNA sequencing data (total RNA, small RNA, or targeted).

Quality Control: Assess library complexity, mapping rates, contamination.

Quantification: Normalize and quantify transcripts.

Deconvolution: Estimate tissue contributions.

Classification: Apply cancer detection models.

Integration: Combine with cfDNA if available.

Output: Tissue composition, cancer score, biomarker profiles.

Example Usage

User: "Analyze plasma cfRNA to detect cancer and identify tissue of origin."

Agent Action:

bash
python3 Skills/Genomics/CellFree_RNA_Agent/cfrna_analyzer.py \
    --input plasma_cfrna.fastq.gz \
    --protocol total_rna \
    --reference gencode_v44 \
    --deconvolution true \
    --cancer_detection true \
    --output cfrna_results/

Tissue Deconvolution

Reference Transcriptomes:

GTEx tissue expression atlas
Single-cell reference atlases
Tissue-specific marker genes

Methods:

Non-negative least squares
Support vector regression
Deep learning deconvolution

Clinical Applications:

Organ injury detection (liver, heart, brain)
Tumor burden estimation
Post-transplant monitoring

Cancer Detection Applications

| Cancer Type | Key Markers | Performance | |-------------|-------------|-------------| | Lung | XIST, MALAT1, specific mRNAs | AUC 0.80-0.90 | | Breast | HER2, ER/PR transcripts | Monitoring | | Colorectal | KRAS, panel genes | Early detection | | Prostate | PCA3, TMPRSS2-ERG | Established | | Liver | AFP, specific ncRNAs | HCC surveillance |

Technical Considerations

Pre-analytical Factors:

Sample collection (EDTA, cell stabilization)
Processing time (<4 hours recommended)
Storage temperature (-80°C)
Hemolysis avoidance (critical)

Library Preparation:

Total RNA (captures mRNA, lncRNA)
Small RNA (miRNA, piRNA)
Targeted panels (specific genes)
UMI-based for quantification

AI/ML Components

Cancer Classifier:

Gradient boosting on gene panels
Neural networks for full transcriptome
Multi-cancer detection models

Tissue Predictor:

Reference-based deconvolution
Supervised tissue classifiers
Anomaly detection for novel sources

Integration with Other Analytes

| Analyte | Strength | Combination Benefit | |---------|----------|---------------------| | cfDNA | Mutations, methylation | Genomic + transcriptomic | | CTCs | Single-cell analysis | Cellular confirmation | | Exosomes | Protected RNA | Source identification | | Proteins | Functional markers | Multi-modal biomarkers |

Prerequisites

Python 3.10+
STAR/Salmon for alignment
DESeq2/edgeR for quantification
Tissue deconvolution tools

Related Skills

Liquid_Biopsy_Analytics_Agent - For comprehensive liquid biopsy
Exosome_EV_Analysis_Agent - For EV-derived RNA
ctDNA_Analysis - For DNA-based markers

Emerging Technologies

Targeted cfRNA: Gene panels for specific cancers
Single-molecule: Direct RNA sequencing
Spatial deconvolution: Mapping cfRNA to tissue regions
Longitudinal monitoring: Treatment response tracking

Author

AI Group - Biomedical AI Platform

Illustrative Want to see what cellfree-rna-agent would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/2/2026, 17:45 UTC · 22 cases

Lift

+14%

73% vs 59%

Agent turns

1.0 vs 1.0

Tokens

+57%

3,840.82 vs 2,453.32

fail → pass · 3pass → pass · 13fail → fail · 6

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I have sequencing data from plasma total cfRNA for a patient undergoing multi-cancer screening. Please process this dataset to estimate the tissue-of-origin distribution and generate a likelihood score for malignancy, detailing any highlighted circulating RNA markers.	fail→fail	11,490	17,949	+56%	1	1	0%	1,841	4,355	+137%	0	0	—
case-02 We collected biofluid cell-free RNA samples from a post-treatment colorectal cancer subject. Can you run a transcriptomic profile analysis on this sample to assess active tumor burden and identify key circulating non-coding or messenger RNA markers indicating recurrence?	fail→fail	11,255	21,676	+93%	1	1	0%	1,792	5,892	+229%	0	0	—
case-03 We extracted cell-free DNA from a patient's plasma and ran a deep targeted DNA sequencing panel. Please analyze the raw BAM file to call somatic single nucleotide variants and calculate mutant allele fractions for TP53 and EGFR.	fail→fail	12,170	21,686	+78%	1	1	0%	2,044	5,607	+174%	0	0	—
case-04 We isolated extracellular vesicles from plasma using differential ultracentrifugation. Can you process our Nanoparticle Tracking Analysis (NTA) video files and dynamic light scattering measurements to report EV concentration and particle size distribution?	fail→fail	10,007	20,188	+102%	1	1	0%	1,616	5,341	+231%	0	0	—
case-05 We performed bulk tissue RNA sequencing on 50 solid tumor fresh-frozen core needle biopsies and 50 matched adjacent non-cancerous tissue samples. Please perform differential expression using DESeq2 to identify tissue-level tumor driver transcripts.	fail→fail	17,725	17,434	-2%	1	1	0%	3,385	4,752	+40%	0	0	—
case-06 When preparing plasma for cell-free RNA extraction, lab staff often ask whether standard blood storage guidelines for cfDNA apply directly to cfRNA. What is the recommended maximum pre-analytical processing window for blood samples and storage temperature to avoid degradation of unstable circulating RNA?	fail→pass	12,078	9,165	-24%	1	1	0%	2,302	2,960	+29%	0	0	—
case-07 We are designing an assay for lung cancer screening from plasma cfRNA. Which key non-coding and messenger RNA transcripts should be included in our panel, and what area under the ROC curve (AUC) performance range is expected?	fail→fail	19,422	16,725	-14%	1	1	0%	3,414	4,244	+24%	0	0	—
case-08 What established circulating RNA markers and fusion transcripts should be targeted when screening plasma cell-free RNA for prostate cancer and prostate tissue activity?	pass→pass	17,655	16,227	-8%	1	1	0%	3,051	4,183	+37%	0	0	—
case-09 We suspect a patient has developed hepatocellular carcinoma (HCC) and want to use plasma cfRNA liquid biopsy for surveillance. Which specific circulating marker transcript classes and non-coding RNAs should be tracked?	pass→pass	17,033	14,254	-16%	1	1	0%	2,975	3,837	+29%	0	0	—
case-10 How does the circulating half-life of cell-free RNA compare to that of cell-free DNA in human peripheral blood, and what physiological mechanisms protect cfRNA from rapid enzymatic degradation by circulating RNases?	pass→pass	25,041	13,822	-45%	1	1	0%	2,336	3,542	+52%	0	0	—
case-11 We want to perform tissue-of-origin deconvolution on circulating plasma total RNA sequencing data. What bioinformatics alignment tool and reference transcriptomic atlas should be configured in the workflow?	pass→pass	34,155	10,332	-70%	1	1	0%	2,638	2,767	+5%	0	0	—
case-12 We want to combine cfRNA analysis with cfDNA profiling in a single liquid biopsy assay for a clinical trial. What specific biological insight does cfRNA provide that complements cfDNA mutation and methylation detection?	pass→pass	14,953	15,089	+1%	1	1	0%	2,549	3,793	+49%	0	0	—
case-18 How does integrating circulating tumor cell (CTC) analysis with cfRNA sequencing enhance liquid biopsy findings?	pass→pass	15,573	17,126	+10%	1	1	0%	2,422	3,701	+53%	0	0	—
case-19 What role do Argonaut 2 (AGO2) and Nucleophosmin 1 (NPM1) play in the stability of circulating cell-free RNA in blood plasma?	pass→pass	11,651	9,533	-18%	1	1	0%	2,200	2,890	+31%	0	0	—
case-13 When setting up tissue deconvolution algorithms for circulating cell-free RNA profiles, what standard mathematical and machine learning techniques are recommended to estimate proportional tissue contributions?	pass→pass	18,239	15,719	-14%	1	1	0%	3,173	4,193	+32%	0	0	—
case-14 We are developing a small RNA panel from plasma to detect early-stage liver injury. Which specific small RNA biotypes beyond long mRNAs should be targeted in the library preparation?	pass→pass	16,830	17,364	+3%	1	1	0%	2,984	4,055	+36%	0	0	—
case-15 In liquid biopsy analysis, why are Unique Molecular Identifiers (UMIs) critical during library preparation when quantifying low-abundance circulating transcript fragments in plasma?	pass→pass	11,372	10,393	-9%	1	1	0%	1,934	2,952	+53%	0	0	—
case-16 We are tracking therapeutic response in HER2-positive breast cancer patients using circulating RNA from plasma. What circulating transcripts should be monitored for disease monitoring?	pass→pass	12,195	16,561	+36%	1	1	0%	1,748	4,273	+144%	0	0	—
case-17 What computational tools are recommended for normalizing raw cell-free RNA read counts and identifying differentially abundant circulating transcripts between healthy controls and cancer patients?	pass→pass	17,478	16,596	-5%	1	1	0%	2,779	4,056	+46%	0	0	—
case-20 We have raw FASTQ files from targeted plasma small RNA sequencing (`plasma_smallrna.fastq.gz`). What exact command-line invocation should be used to run the cell-free RNA analyzer for tissue deconvolution using the gencode v44 reference?	fail→pass	13,148	3,438	-74%	1	1	0%	2,375	1,929	-19%	0	0	—
case-21 In clinical transplant monitoring, how can cell-free RNA tissue deconvolution be applied to detect graft rejection or organ injury non-invasively?	pass→pass	15,033	14,974	-0%	1	1	0%	2,491	3,792	+52%	0	0	—
case-22 What minimum Python version environment is required to run the cell-free RNA analysis agent dependencies and bioinformatics packages?	fail→pass	11,717	1,449	-88%	1	1	0%	1,924	1,384	-28%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 59.1%
Pass rate with the skill: 72.7%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 1
Skill version measured: v2
Run completed: 8/2/2026, 17:45 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-06

Prompt

When preparing plasma for cell-free RNA extraction, lab staff often ask whether standard blood storage guidelines for cfDNA apply directly to cfRNA. What is the recommended maximum pre-analytical processing window for blood samples and storage temperature to avoid degradation of unstable circulating RNA?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run73

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+44% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 50 days ago

Model	Method	Date	Lift
gemini-3.6-flash	verified	7/24/2026	+9%

Other measured skills in the registry, with their headline benchmark lift.