New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cerna Analysis

by aipoch in aipoch/medical-research-skills

A skill your agent uses when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF…

MITAuto-check passedResearch & Science

Install Cerna Analysis

skills CLI
$ npx skills add aipoch/medical-research-skills --skill cerna-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aipoch/medical-research-skills cerna-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'awesome-med-research-skills/Data Analysis/cerna-analysis' .claude/skills/cerna-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cerna-analysis
GitHub stars
2k
Token cost
~2.4k tokens
SKILL.md length
972 words
Files
26 (incl. scripts, references)
Skills in repo
567
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF…

  • Works in 4 steps: Validate Input → Load Interaction Data → Filter the Network → …
  • Building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files
  • SKILL.md covers When to Use, Input Validation, When to Read External Files and Usage, plus 8 more sections
  • Runs R scripts from its folder

What it does

Cerna Analysis is an agent skill from aipoch/medical-research-skills. Use when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF visualization in a single output directory. NOT for: differential expression, single-cell analysis, enrichment analysis, or workflows without a key gene list.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 28 other files, including scripts and reference files (for example `eval_report_cerna-analysis_result.json`, `references/algorithm.md` and `references/cli-guide.md`).

It sits in Research & Science, covering Bioinformatics and CSV and tabular files. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

  • Building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files
  • With flat-file CSV exports and PDF visualization in a single output directory

Example prompts

  • “/cerna-analysis”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Validate Input
  2. Load Interaction Data
  3. Filter the Network
  4. Build Outputs

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 6 files in scripts/ (R, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cerna Analysis loads about 2.4k tokens when it runs, and up to ~19M if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 972 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~19M

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 972 words, ~2,401 tokens.

Download SKILL.mdSave it as .claude/skills/cerna-analysis/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.
name
cerna-analysis
description
Use when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF visualization in a single output directory. NOT for: differential expression, single-cell analysis, enrichment analysis, or workflows without a key gene list.
license
MIT
skill-author
Codex

ceRNA Analysis

When to Use

Use this skill when you need to construct a ceRNA regulatory network from a known key-gene list using the bundled miRNA-mRNA and miRNA-lncRNA reference tables.

Use it for:

  • Building a ceRNA network from one gene list and exporting flat CSV plus PDF outputs
  • Comparing supported miRNA source modes such as combined, starbase, or pairwise overlaps
  • Re-running the same local workflow with different lncRNA strictness, layout, or plotting parameters

Do not use it for:

  • Differential expression, single-cell, enrichment, or survival analysis
  • Workflows that do not start from a key gene list
  • Cases where you want a miRNA-mRNA-only graph without a retained lncRNA ceRNA layer

Input Validation

This skill accepts:

  • A key gene list as a plain-text file (one gene symbol per line) or as a comma-separated string on the CLI
  • Optional parameter overrides for dataset mode, lncRNA strictness, layout, colors, and timeout

If the user's request does not involve building a ceRNA regulatory network from a key gene list — for example, asking to run differential expression, enrichment analysis, single-cell workflows, or survival analysis — do not proceed with the workflow. Instead respond:

"ceRNA Analysis is designed to construct a ceRNA regulatory network from a key gene list using bundled miRNA-mRNA and miRNA-lncRNA reference databases. Your request appears to be outside this scope. Please provide a key gene list and specify a supported miRNA dataset mode, or use a more appropriate skill for differential expression, enrichment analysis, or single-cell workflows."

When to Read External Files

SituationFile to ReadPurpose
Need algorithm detailsreferences/algorithm.mdceRNA construction logic, dataset combinations, filtering rules. Includes worked examples of pairwise intersection network size vs combined mode.
Need to run analysisscripts/main.RExecute: Rscript scripts/main.R --key_genes ... --output_dir .... Note: --help requires igraph to be installed.
Encounter errorsreferences/troubleshooting.mdCommon errors and solutions
Need CLI examplesreferences/cli-guide.mdDetailed local run examples with measured outputs
Need test datatests/data/Sample key-gene input for testing

Usage

bash
Rscript scripts/main.R \
  --key_genes tests/data/gene.txt \
  --output_dir ./output/ \
  --mirna_dataset combined \
  --lncrna_strictness High \
  --lncrna_freq_thresh 0 \
  --timeout_seconds 600 \
  --seed 42

Dependency note: --help and all analysis modes require igraph to be installed. Install igraph before running any command. Use references/troubleshooting.md for installation guidance.

Arguments

Main Analysis: scripts/main.R
ShortLongTypeDefaultDescription
-i--key_genescharacterrequiredKey gene file path or comma-separated gene names
-o--output_dircharacter./output/Output directory
-m--mirna_datasetcharactercombinedDataset: combined, starbase, mirdb, mirtarbase, starbase+mirdb, starbase+mirtarbase, mirdb+mirtarbase
-l--lncrna_strictnesscharacterHighlncRNA interaction strictness: Low, Median, High
-f--lncrna_freq_threshinteger0Minimum retained lncRNA frequency
-r--reference_dircharacterfile.path(script_dir, "..", "references", "database")Database directory
--plot_widthdouble12PDF width in inches
--plot_heightdouble8PDF height in inches
--layout_typecharacterkkLayout: kk, fr, nicely, circle, grid, randomly
--mrna_colorcharacter#D16BA5mRNA node color
--lncrna_colorcharacter#008dcdlncRNA node color
--mirna_colorcharacter#00c9a7miRNA node color
--node_size_basedouble15Base node size
--label_sizedouble0.8Node label size
--show_legendlogicalTRUEShow legend in the PDF
-t--timeout_secondsinteger3600Elapsed timeout limit
-s--seedinteger42Random seed for reproducibility

Input Format

Key Genes (key_genes)

Plain-text input with one gene symbol per line, or a comma-separated string passed directly on the CLI.

text
TP53
BRCA1
MYC

Rules:

  • Blank lines are ignored
  • Lines starting with # are ignored
  • Duplicate genes are removed
  • At least one valid gene is required
Database Directory (reference_dir)

The bundled database directory is references/database/. Required files depend on the selected mirna_dataset plus the selected lncRNA strictness file.

  • combined: miRNA_mRNA.csv
  • starbase: starbase_miRNA_mRNA.csv
  • mirdb: miRDB_miRNA_mRNA.csv
  • mirtarbase: miRTarbase_miRNA_mRNA.csv
  • starbase+mirdb: starbase_miRNA_mRNA.csv and miRDB_miRNA_mRNA.csv
  • starbase+mirtarbase: starbase_miRNA_mRNA.csv and miRTarbase_miRNA_mRNA.csv
  • mirdb+mirtarbase: miRDB_miRNA_mRNA.csv and miRTarbase_miRNA_mRNA.csv
  • lncRNA file: one of starbase_miRNA_lncRNA_High.csv, starbase_miRNA_lncRNA_Median.csv, or starbase_miRNA_lncRNA_Low.csv
Show full SKILL.md (395 more words)Show less

Output Files

FileDescription
ceRNA_network_edges.csvEdge table with node1,node2 columns
ceRNA_network_nodes.csvNode table with node,type,degree columns
ceRNA_network.pdfceRNA network visualization
session_info.txtR session details and loaded package versions

Workflow

Step 1: Validate Input
  • Check key-gene input existence or parse comma-separated genes
  • Validate parameter choices, numeric limits, timeout, and colors
  • Verify the database directory and required files
Step 2: Load Interaction Data
  • Load the selected miRNA-mRNA dataset
  • Load the selected miRNA-lncRNA dataset by strictness level
  • Recompute pairwise intersections when requested
Step 3: Filter the Network
  • Retain miRNA-mRNA pairs linked to the provided key genes
  • Retain miRNA-lncRNA pairs connected to the retained miRNAs
  • Apply the lncRNA frequency threshold
  • Stop with SKILL_INVALID_DATA if no lncRNA interactions remain after filtering, because the ceRNA layer has collapsed
Step 4: Build Outputs
  • Construct edge and node tables
  • Save CSV, PDF, and session information in the output directory root

Methods

combined

Uses the bundled precomputed overlap across three miRNA-mRNA resources for higher-confidence interactions.

Pairwise Intersections

starbase+mirdb, starbase+mirtarbase, and mirdb+mirtarbase recompute the overlap between two bundled databases. Pairwise intersections typically yield 20–40% fewer edges than combined mode because only interactions present in both selected databases are retained. Use pairwise modes when you need higher-confidence edges at the cost of reduced network coverage.

lncRNA Strictness

High, Median, and Low select different bundled starBase evidence levels for miRNA-lncRNA interactions.

Examples

Basic Combined Analysis
bash
Rscript scripts/main.R \
  -i ./key_genes.txt \
  -o ./output \
  -m combined
Single Database Analysis
bash
Rscript scripts/main.R \
  -i ./key_genes.txt \
  -o ./output_starbase \
  -m starbase \
  -l Median \
  -f 1

Error Handling

ErrorCauseSolution
SKILL_FILE_NOT_FOUNDInput file or database file is missingCheck the file path or bundled database directory
SKILL_EMPTY_FILEA required file exists but has no contentReplace or regenerate the file
SKILL_EMPTY_DATAA required reference table has no usable rowsVerify the input content and regenerate the file if needed
SKILL_MISSING_COLUMNSAn input table lacks required columnsVerify the expected schema
SKILL_INVALID_PARAMETERAn invalid CLI value was providedUse one of the documented parameter values
SKILL_INVALID_DATAThe input data cannot build a valid ceRNA network, or lncRNA filtering removes the ceRNA layer entirelyVerify the key genes and database files, then lower --lncrna_freq_thresh or choose a different dataset / strictness
SKILL_DEPENDENCY_MISSINGA required package is not installed (igraph required for all modes including --help)Install the missing package before running any command
SKILL_TIMEOUTThe run exceeded the timeout limitIncrease --timeout_seconds
SKILL_RUNTIME_ERRORAn unexpected runtime failure occurredRe-run after checking the console error message

IF error persists, READ: references/troubleshooting.md

Testing

Test with Sample Data
bash
# Run with sample data (igraph must be installed first)
Rscript scripts/main.R \
  -i tests/data/gene.txt \
  -o tests/output/
Validation Commands
bash
# Inspect edge output
wc -l tests/output/ceRNA_network_edges.csv

# Check plot exists
ls -la tests/output/ceRNA_network.pdf

© aipoch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 25 other files (scripts, references) in awesome-med-research-skills/Data Analysis/cerna-analysis of aipoch/medical-research-skills.

  • SKILL.md
  • eval_report_cerna-analysis_result.json
  • references/algorithm.md
  • references/cli-guide.md
  • references/database/miRDB_miRNA_mRNA.csv
  • references/database/miRNA_mRNA.csv
  • references/database/miRTarbase_miRNA_mRNA.csv
  • references/database/starbase_miRNA_lncRNA_High.csv
  • references/database/starbase_miRNA_lncRNA_Low.csv
  • references/database/starbase_miRNA_lncRNA_Median.csv
  • references/database/starbase_miRNA_mRNA.csv
  • references/troubleshooting.md
  • scripts/functions.R
  • scripts/io.R
  • scripts/main.R
  • scripts/plot_functions.R
  • scripts/run_analysis.R
  • scripts/utils.R
  • … and 8 more

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Cerna Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cerna Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cerna Analysis this skillaipoch/medical-research-skills2k—~2.4kAutomated safety check: PassMIT
Spatial XeniumQING1105/ezST101—~535Automated safety check: PassMIT
Plannotate Plasmid Annotationjaechang-hits/SciAgent-Skills3701 repos~4.7kAutomated safety check: PassGPL-3.0
Proteomics Data ImportTianGzlab/OmicsClaw161—~1.1kAutomated safety check: PassMIT
Sc Perturb PrepTianGzlab/OmicsClaw161—~1.6kAutomated safety check: PassMIT
Vdjdb Extractantigenomics/vdjdb-db157—~1.2kAutomated safety check: PassCustom licence

Similar skills

  • Spatial Xenium

    QING1105/ezST

    Xenium platform branch of the spatial transcriptomics workflow — load and validate the platform's cell-level matrix for downstream analysis.

    101 GitHub stars~535 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Plannotate Plasmid Annotation

    jaechang-hits/SciAgent-Skills

    Auto-annotate plasmids with features (promoters, terminators, resistance, origins, tags, fluorescent proteins) via BLAST against curated DBs (Addgene, fpbase, SnapGene).

    370 GitHub starsUsed in 1 repo~4.7k tokens
    Research & ScienceAuto-check passed

  • Proteomics Data Import

    TianGzlab/OmicsClaw

    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…

    161 GitHub stars~1.1k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed

  • Sc Perturb Prep

    TianGzlab/OmicsClaw

    Load when attaching cell-barcode → sgRNA assignments from a mapping TSV/CSV onto a Perturb-seq expression AnnData, producing standardised perturbation / sgRNA / target-gene obs columns.

    161 GitHub stars~1.6k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed

  • Vdjdb Extract

    antigenomics/vdjdb-db

    Extract TCR:pMHC specificity records from raw submission sources - supplementary XLS/CSV tables, PDF manuscripts, 10x Genomics contig and clonotype files, AIRR Rearrangement TSVs, Adaptive ImmunoSEQ…

    157 GitHub stars~1.2k tokensUpdated today
    Documents & OfficeAuto-check passed

  • Ukb Ppp Region Fetch

    ClawBio/ClawBio

    Fetch a regional slice of plasma pQTL summary statistics from the UK Biobank Pharma Proteomics Project (UKB-PPP; Sun 2023 Nature) for a specific (protein, ancestry) measurement.

    1.2k GitHub stars~4.6k tokensUpdated yesterday
    Research & ScienceAuto-check passed

More from aipoch/medical-research-skills

All 567 skills in this repo

  • Academic Poster Generator

    aipoch/medical-research-skills

    Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…

    2k GitHub stars~2.2k tokensUpdated 20 days ago
    Auto-check passed

  • Diagnostic Study Quality Assessment Quadas

    aipoch/medical-research-skills

    Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.

    2k GitHub stars~1.4k tokensUpdated 20 days ago
    Auto-check passed

  • Exploratory Data Analysis

    aipoch/medical-research-skills

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.

    2k GitHub stars~3.7k tokensUpdated 20 days ago
    Auto-check passed

  • Iso Certification

    aipoch/medical-research-skills

    A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.

    2k GitHub stars~1.8k tokensUpdated 20 days ago
    Auto-check passed

  • Journal Skills

    aipoch/medical-research-skills

    Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…

    2k GitHub stars~1.7k tokensUpdated 20 days ago
    Auto-check passed

  • Latex Posters

    aipoch/medical-research-skills

    Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.

    2k GitHub stars~1.3k tokensUpdated 20 days ago
    Auto-check passed

Categories

Questions about Cerna Analysis

What does Cerna Analysis do?

A skill your agent uses when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF…. Cerna Analysis is an agent skill from aipoch/medical-research-skills. Use when building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files, with flat-file CSV exports and PDF visualization in a single output directory.

When should I use Cerna Analysis?

Cerna Analysis fits situations like: building a ceRNA regulatory network from a key gene list by combining bundled miRNA-mRNA and miRNA-lncRNA database files; with flat-file CSV exports and PDF visualization in a single output directory.

How do I install Cerna Analysis in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill cerna-analysis -a claude-code`. Or copy the skill folder (awesome-med-research-skills/Data Analysis/cerna-analysis in aipoch/medical-research-skills) into .claude/skills/cerna-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Cerna Analysis in Codex?

Run `npx skills add aipoch/medical-research-skills --skill cerna-analysis -a codex`. Or copy the skill folder (awesome-med-research-skills/Data Analysis/cerna-analysis in aipoch/medical-research-skills) into .agents/skills/cerna-analysis in your project. Codex loads it when a task matches its description.

Can I use Cerna Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aipoch/medical-research-skills --skill cerna-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cerna-analysis, .gemini/skills/cerna-analysis, .github/skills/cerna-analysis and .opencode/skills/cerna-analysis in your project.

What does Cerna Analysis need to run?

Going by SKILL.md and its folder, Cerna Analysis needs R for the scripts in its folder.

Does Cerna Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cerna Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cerna Analysis use?

Cerna Analysis is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cerna Analysis use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19M tokens, read only when the agent opens those files.

What are the alternatives to Cerna Analysis?

Skills that share tags, products or a category with Cerna Analysis: Spatial Xenium (QING1105/ezST, 101 stars), Plannotate Plasmid Annotation (jaechang-hits/SciAgent-Skills, 370 stars), Proteomics Data Import (TianGzlab/OmicsClaw, 161 stars) and Sc Perturb Prep (TianGzlab/OmicsClaw, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cerna Analysis?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,973 GitHub stars. The repository holds 567 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.