New: 98,000+ 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

Bulkrna Ppi Network

by TianGzlab in TianGzlab/OmicsClaw

Load when querying STRING for the protein-protein interaction neighborhood of a bulk RNA-seq DEG list and finding hub genes.

Apache-2.0Auto-check passedResearch & Science

Install Bulkrna Ppi Network

skills CLI
$ npx skills add TianGzlab/OmicsClaw --skill bulkrna-ppi-network -a claude-code

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

GitHub CLI
$ gh skill install TianGzlab/OmicsClaw bulkrna-ppi-network --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/TianGzlab/OmicsClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bulkrna/bulkrna-ppi-network .claude/skills/bulkrna-ppi-network && 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
bulkrna-ppi-network
GitHub stars
161
Token cost
~1.2k tokens
SKILL.md length
476 words
Files
11 (incl. references)
Skills in repo
88
Repo updated
First seen
Licence
Apache-2.0

At a glance

Load when querying STRING for the protein-protein interaction neighborhood of a bulk RNA-seq DEG list and finding hub genes.

  • Tasks that involve Bioinformatics
  • SKILL.md covers When to use, Use from a step, API and Methods and parameters, plus 5 more sections
  • Runs Python scripts from its folder; calls python

What it does

Bulkrna Ppi Network is an agent skill from TianGzlab/OmicsClaw. Load when querying STRING for the protein-protein interaction neighborhood of a bulk RNA-seq DEG list and finding hub genes. Skip when pathway enrichment of the same list (use bulkrna-enrichment); de novo co-expression network discovery (use bulkrna-coexpression).

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `_api.py`, `bulkrna_ppi_network.py` and `data/README.md`).

It sits in Research & Science, covering Bioinformatics. The repository describes itself as: Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Bioinformatics

Example prompts

  • “/bulkrna-ppi-network”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 90a3bec. 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 script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Bulkrna Ppi Network loads about 1.2k tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 476 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.6k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from TianGzlab/OmicsClaw at commit 90a3bec, republished under its Apache-2.0 licence (© TianGzlab). 476 words, ~1,240 tokens.

Download SKILL.mdSave it as .claude/skills/bulkrna-ppi-network/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
bulkrna-ppi-network
description
Load when querying STRING for the protein-protein interaction neighborhood of a bulk RNA-seq DEG list and finding hub genes. Skip when pathway enrichment of the same list (use bulkrna-enrichment); de novo co-expression network discovery (use bulkrna-coexpression).
trigger
PPI, protein interaction, STRING, network, hub gene, interactome
tags
bulkrna, PPI, STRING, network, hub-genes, protein-interaction

bulkrna-ppi-network

When to use

Analyze a PPI subgraph and rank hub genes from explicit interaction tables. Use bulkrna-coexpression for expression-derived networks and bulkrna-enrichment for pathways.

Use from a step

python
import pandas as pd
from skills._sdk.notebook import load_skill, read_input, write_output
library = load_skill('bulkrna-ppi-network')
data = read_input('edges.csv', reader=pd.read_csv)
result = library.analyze(data)
write_output(result, 'tables/result.csv')

examples/example_step.py runs offline and supports fresh-kernel replay. Pure computations return objects; CLI and steps own writes.

API

<!-- api:begin generated from _api.py; regenerate with run.py api <skill dir> --write -->
analyze(data, *, genes=None, induced=False)

Rank query nodes using the CLI's unweighted neighborhood convention.

:param data: Interaction DataFrame with gene_a, gene_b and score columns; scores do not weight centrality. :param genes: Optional gene list including isolates; None uses all edge endpoints. :param induced: Default False preserves external neighbors in degree/closeness; True restricts edges to genes. :returns: A node-centrality DataFrame with degree, betweenness, closeness and hub_score. :raises ValueError: Edge columns or the node list are invalid.

fetch_interactions(data, *, species=9606, score_threshold=400)

Query STRING explicitly; unavailable or malformed responses raise.

:param data: Gene identifiers sent to the public STRING service. :param species: CLI default 9606 (human); NCBI taxonomy identifier. :param score_threshold: CLI default 400; integer confidence cutoff from 0 to 1000. :returns: A DataFrame with gene_a, gene_b and scores on STRING's 0 to 1 scale. :raises ImportError: Install requests with install_skill_deps if unavailable. :raises ValueError: Parameters or response columns are invalid. :raises Exception: Network and HTTP failures propagate without demo fallback.

run_info(data, *, keep=True)

Read topology diagnostics attached to the node table.

:param data: Centrality DataFrame returned by analyze. :param keep: Default True; the CLI removes diagnostics with False. :returns: An independent summary dictionary. :raises TypeError: data is not a DataFrame.

network_figure(data, *, genes=None, random_state=42)

Draw a seeded spring layout without changing numpy's global random state.

:param data: Edge DataFrame accepted by analyze. :param genes: Optional gene list including isolates; None uses edge endpoints. :param random_state: CLI default 42; spring-layout initialization seed. :returns: A matplotlib Figure. :raises ValueError: Edges or node list are invalid.

Show full SKILL.md (185 more words)Show less
hubs_figure(data, *, top_n=20)

Plot the highest-ranked hub scores.

:param data: Centrality table returned by analyze. :param top_n: CLI default 20; maximum number of nodes shown. :returns: A matplotlib Figure. :raises KeyError: gene or hub_score is absent.

<!-- api:end -->

Methods and parameters

fetch_interactions explicitly queries STRING with a 0 to 1000 confidence threshold and returns 0 to 1 scores. analyze uses an unweighted graph and includes provided isolates. Hub scores combine normalized degree and betweenness. The CLI demo reads the fixed 364-edge STRING table described in data/README.md; it does not contact STRING.

Gotchas

  • --demo accepts only species 9606 because data/demo_string_edges.csv contains human interactions; other species require a real query.
  • fetch_interactions propagates HTTP/network errors and never substitutes demo edges. analyze defaults to the CLI neighborhood convention: degree includes external neighbors, closeness visits them, and betweenness is restricted to query nodes. Use induced=True to restrict all edges to the query set. network_figure draws query nodes only and uses seed 42 without changing the global random generator.

Inputs and outputs

tables/hub_genes.csv, tables/interaction_edges.csv, tables/node_centrality.csv, figures/hub_genes_barplot.png, figures/ppi_network.png, report.md, result.json and reproducibility/commands.sh.

CLI

bash
python skills/bulkrna/bulkrna-ppi-network/bulkrna_ppi_network.py --demo --output /tmp/bulkrna_ppi_network

See also

Dependencies

numpy, pandas, matplotlib, requests

© TianGzlab, Apache-2.0. 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 10 other files (references) in skills/bulkrna/bulkrna-ppi-network of TianGzlab/OmicsClaw.

  • SKILL.md
  • _api.py
  • bulkrna_ppi_network.py
  • data/README.md
  • data/demo_string_edges.csv
  • examples/example_step.py
  • references/methodology.md
  • references/output_contract.md
  • references/parameters.md
  • tests/test_api.py
  • tests/test_cli.py

Open the folder on GitHubat commit 90a3bec

Compare with similar skills

Bulkrna Ppi Network 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.

Bulkrna Ppi Network compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bulkrna Ppi Network this skillTianGzlab/OmicsClaw161—~1.2kAutomated safety check: PassApache-2.0
Scanpy Single-Cell Analysisdavila7/claude-code-templates32k15 repos~2.8kAutomated safety check: PassMIT
deepTools NGS Toolkitdavila7/claude-code-templates32k12 repos~4.5kAutomated safety check: PassMIT
LaminDB Biological Data Managementdavila7/claude-code-templates32k12 repos~3.6kAutomated safety check: PassMIT
PyDESeq2 Differential Expressiondavila7/claude-code-templates32k11 repos~4kAutomated safety check: PassMIT
Gtars Genomic Interval Toolkitdavila7/claude-code-templates32k11 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Scanpy Single-Cell Analysis

    davila7/claude-code-templates

    Walks through single-cell RNA-seq analysis with Scanpy: loading .h5ad and 10X data, QC, normalization, PCA and UMAP, Leiden clustering, marker genes and cell type annotation.

    32k GitHub starsUsed in 15 repos~2.8k tokens
    Research & ScienceAuto-check passed

  • deepTools NGS Toolkit

    davila7/claude-code-templates

    Guides use of deepTools on sequencing data: BAM to bigWig conversion, QC, sample correlation, and heatmaps or profiles around TSS and peaks for ChIP-seq, RNA-seq and ATAC-seq.

    32k GitHub starsUsed in 12 repos~4.5k tokens
    Research & ScienceAuto-check passed

  • LaminDB Biological Data Management

    davila7/claude-code-templates

    Manages biological datasets with LaminDB: versioned artifacts, run lineage, ontology-based annotation, schema validation and links to workflow managers and ML tools.

    32k GitHub starsUsed in 12 repos~3.6k tokens
    Research & ScienceAuto-check passed

  • PyDESeq2 Differential Expression

    davila7/claude-code-templates

    Runs differential gene expression analysis on bulk RNA-seq counts with PyDESeq2: design formulas, Wald tests, FDR correction and volcano or MA plots.

    32k GitHub starsUsed in 11 repos~4k tokens
    Research & ScienceAuto-check passed

  • Gtars Genomic Interval Toolkit

    davila7/claude-code-templates

    Works with genomic intervals using gtars, a Rust toolkit with Python bindings: overlap detection, coverage tracks, tokenization for ML models and reference sequences.

    32k GitHub starsUsed in 11 repos~1.9k tokens
    Research & ScienceAuto-check passed

  • Single-Cell Initial Analysis

    LigphiDonk/Oh-my--paper

    Runs a seven-step quality-control and exploration pipeline on scRNA-seq, CyTOF or flow cytometry data and writes a plain-language report of what it found.

    738 GitHub starsUsed in 1 repo~1.4k tokens
    Research & ScienceAuto-check passed

More from TianGzlab/OmicsClaw

All 88 skills in this repo

  • Bulkrna Cosinor Rhythm

    TianGzlab/OmicsClaw

    Load when the user needs Deterministic fixed-period 24-hour single-component cosinor OLS rhythm analysis for a bulk RNA time-course CSV.

    161 GitHub stars~840 tokensUpdated 2 days ago
    Auto-check passed

  • Bulkrna Batch Correction

    TianGzlab/OmicsClaw

    Load when correcting batch effects in bulk expression using R sva ComBat or the legacy Python parametric approximation.

    161 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Bulkrna Coexpression

    TianGzlab/OmicsClaw

    Load when discovering bulk gene co-expression modules and hub genes with R WGCNA.

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

  • Bulkrna De

    TianGzlab/OmicsClaw

    Load when comparing gene expression between two conditions in bulk RNA-seq count data.

    161 GitHub stars~867 tokensUpdated 2 days ago
    Auto-check passed

  • Bulkrna Deconvolution

    TianGzlab/OmicsClaw

    Load when estimating cell-type proportions in bulk RNA-seq samples from a single-cell or signature-matrix reference.

    161 GitHub stars~757 tokensUpdated 2 days ago
    Auto-check passed

  • Bulkrna Enrichment

    TianGzlab/OmicsClaw

    Load when running pathway / GO term enrichment on a bulk RNA-seq DE result list.

    161 GitHub stars~860 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Bulkrna Ppi Network

What does Bulkrna Ppi Network do?

Load when querying STRING for the protein-protein interaction neighborhood of a bulk RNA-seq DEG list and finding hub genes. Bulkrna Ppi Network is an agent skill from TianGzlab/OmicsClaw. Load when querying STRING for the protein-protein interaction neighborhood of a bulk RNA-seq DEG list and finding hub genes.

When should I use Bulkrna Ppi Network?

Bulkrna Ppi Network fits situations like: tasks that involve Bioinformatics.

How do I install Bulkrna Ppi Network in Claude Code?

Run `npx skills add TianGzlab/OmicsClaw --skill bulkrna-ppi-network -a claude-code`. Or copy the skill folder (skills/bulkrna/bulkrna-ppi-network in TianGzlab/OmicsClaw) into .claude/skills/bulkrna-ppi-network in your project. Claude Code loads it when a task matches its description.

How do I install Bulkrna Ppi Network in Codex?

Run `npx skills add TianGzlab/OmicsClaw --skill bulkrna-ppi-network -a codex`. Or copy the skill folder (skills/bulkrna/bulkrna-ppi-network in TianGzlab/OmicsClaw) into .agents/skills/bulkrna-ppi-network in your project. Codex loads it when a task matches its description.

Can I use Bulkrna Ppi Network 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 TianGzlab/OmicsClaw --skill bulkrna-ppi-network -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bulkrna-ppi-network, .gemini/skills/bulkrna-ppi-network, .github/skills/bulkrna-ppi-network and .opencode/skills/bulkrna-ppi-network in your project.

What does Bulkrna Ppi Network need to run?

Going by SKILL.md and its folder, Bulkrna Ppi Network needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Bulkrna Ppi Network 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 Bulkrna Ppi Network 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. Review the folder before installing.

What licence does Bulkrna Ppi Network use?

Bulkrna Ppi Network is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bulkrna Ppi Network use?

About 1.2k tokens (SKILL.md is roughly 5k 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 397 tokens, read only when the agent opens those files.

What are the alternatives to Bulkrna Ppi Network?

Skills that share tags, products or a category with Bulkrna Ppi Network: Scanpy Single-Cell Analysis (davila7/claude-code-templates, 32k stars), deepTools NGS Toolkit (davila7/claude-code-templates, 32k stars), LaminDB Biological Data Management (davila7/claude-code-templates, 32k stars) and PyDESeq2 Differential Expression (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bulkrna Ppi Network?

TianGzlab (a GitHub organization) maintains it in TianGzlab/OmicsClaw, which has 161 GitHub stars. The repository holds 88 skills in this directory. The repository was last updated on October 7, 2026.

Source: TianGzlab/OmicsClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.