Clawbio Guide

What it does

When your agent uses it

• Tasks that involve Bioinformatics

Example prompts

• “/clawbio-guide”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Genomics pipelines: Standard NGS analysis workflows
2. 2Lab integration: Natural language interface for bioinformatics
3. 3Teaching: Demonstrate analysis pipelines interactively
4. 4Rapid prototyping: Quick exploratory biological analyses
5. 5Reproducibility: Standardized, documented pipelines

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python, bash and json).

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

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • bioconductor.org
  • nf-co.re

  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

Clawbio Guide loads about 1.1k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 154 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~19

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

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

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 wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 154 words, ~1,105 tokens.

name

clawbio-guide

description

OpenClaw bioinformatics skill library for genomics pipelines

# Install as OpenClaw plugin
openclaw plugins install @clawbio/clawbio

# Or add to your OpenClaw configuration
# In openclaw.config.json:
{
  "plugins": ["@clawbio/clawbio"]
}

# Through OpenClaw conversational interface:
# "Analyze differential expression between treated and control
#  samples in the data/rnaseq/ directory"

# ClawBio executes:
# 1. Quality control (FastQC)
# 2. Trimming (Trimmomatic)
# 3. Alignment (STAR)
# 4. Quantification (featureCounts)
# 5. Differential expression (DESeq2)
# 6. Visualization (volcano plot, MA plot, heatmap)
# 7. Pathway enrichment (GSEA)

# "Call variants from the whole-genome sequencing data
#  in samples/ against hg38 reference"

# Pipeline:
# 1. Alignment: BWA-MEM2 → sorted BAM
# 2. Preprocessing: MarkDuplicates, BQSR
# 3. Variant calling: GATK HaplotypeCaller
# 4. Filtering: VQSR or hard filters
# 5. Annotation: VEP or SnpEff
# 6. Report: variant statistics, quality metrics

# "Classify the microbial communities in my 16S/shotgun
#  sequencing data and generate taxonomic plots"

# Pipeline:
# 1. Quality filtering (fastp)
# 2. Host decontamination (Bowtie2 vs human)
# 3. Classification (Kraken2 + Bracken)
# 4. Diversity analysis (alpha + beta diversity)
# 5. Differential abundance (LEfSe/ANCOM)
# 6. Visualization (stacked bar, PCoA, heatmap)

{
  "clawbio": {
    "reference_genomes": {
      "hg38": "/data/references/hg38/",
      "mm39": "/data/references/mm39/",
      "custom": "/data/references/custom/"
    },
    "tools": {
      "aligner": "bwa-mem2",
      "variant_caller": "gatk",
      "quantifier": "featurecounts",
      "de_method": "deseq2"
    },
    "resources": {
      "threads": 8,
      "memory_gb": 32,
      "gpu": false
    },
    "output": {
      "format": ["html_report", "csv", "plots"],
      "figures_dpi": 300
    }
  }
}

# Create custom bioinformatics skills
# SKILL.md template for new analysis types

"""
---
name: my-custom-analysis
description: "Custom bioinformatics analysis skill"
metadata:
  openclaw:
    category: "domains"
    subcategory: "biomedical"
---

# My Custom Analysis

## When to use
Describe when this analysis is appropriate.

## Pipeline Steps
1. Input validation
2. Processing step 1
3. Processing step 2
4. Output generation

## Example Usage
Show conversational examples.
"""

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

Files

Just SKILL.md in skills/domains/biomedical/clawbio-guide of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

• brycewang-stanford/Auto-Empirical-Research-Skillsskills/43-wentorai-research-plugins/skills/domains/biomedical/clawbio-guide