metagenome-binning
Recover metagenome-assembled genomes (MAGs) from contigs using MetaBAT2, refine with DAS Tool, and assess quality with CheckM2.
Skill by Scientific-Tooling
Chalk Labs
Need help deploying metagenome-binning?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/scientific-tooling-metagenome-binning
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/metagenome-binning
What's inside
- Skill name
metagenome-binning- Description
- Recover metagenome-assembled genomes (MAGs) from contigs using MetaBAT2, refine with DAS Tool, and assess quality with CheckM2.
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (10)
- SKILL.md
- README.md · agents/
- claude.yaml · agents/
- openai.yaml · agents/
- .gitkeep · assets/
- config.yaml
- README.md · references/
- metabat2-dastool-checkm2.md · references/
- batch_run.sh · scripts/
- run.sh · scripts/
SKILL.md (first lines)
# Skill: metagenome-binning ## Use When - The user wants to recover individual microbial genomes from assembled metagenomic contigs. - The user needs MAG quality assessment (completeness, contamination). - The user wants to refine bins from multiple binners with DAS Tool. - The user needs MIMAG-standard quality classifications for recovered genomes. ## Inputs - Required: - Assembled contigs FASTA file. - BAM file of reads mapped back to contigs (for coverage calculation). - Optional: - `--das-tool` — Enable DAS Tool refinement using multiple binner results. - `--min-contig N` — Minimum contig length for binning in bp (default: 1500). - `--threads N` — Number of threads (default: 4). - `--outdir DIR` — Output directory (default: `binning_results`). - `--checkm2-db PATH` — Path to CheckM2 database. ## Workflow 1. Calculate contig coverage depth with MetaBAT2's `jgi_summarize_bam_contig_depths`. 2. Run MetaBAT2 for initial binning. 3. Optionally run additional binners (MaxBin2, CONCOCT) for DAS Tool refinement. 4. If multiple binners used: run DAS Tool to select the best non-redundant bin set. 5. Run CheckM2 `predict` on the final bin set for completeness and contamination estimates. 6. Classify bins by MIMAG standards: high-quality (>=90% complete, <5% contamination), medium-quality (>=50%, <10%), low-quality (below thresholds). 7. Report: number of bins, quality distribution, total high/medium/low quality MAGs. ## Output Contract - **MAG FASTA files** — One FASTA file per bin (`<outdir>/bins/<bin_id>.fa`). - **CheckM2 quality report** — Completeness and contamination per bin (`<outdir>/checkm2/quality_report.tsv`). - **Bin quality summary** — Per-bin completeness, contamination, N50, genome size, and MIMAG classification (`<outdir>/bin_summary.txt`). ## Limits - MetaBAT2 and CheckM2 must be installed and available on `$PATH`. - CheckM2 requires a pre-downloaded database (approximately 3 GB). - DAS Tool requires results from multiple binners as input; it is optional but recommended. - Assembly must have sufficient depth for binning (>10x per genome is recommended). - Contigs shorter than 1500 bp are typically excluded from binning. - MIMAG quality standards: high-quality draft (>=90% completeness, <5% contamination), medium-quality draft (>=50% completeness, <10% contamination). - Common failure cases: - BAM file not sorted or indexed, causing `jgi_summarize_bam_contig_depths` to fail. - CheckM2 database not downloaded or path not set, preventing quality assessment. - Insufficient sequencing depth (<10x per genome) producing fragmented or empty bins.
From Scientific-Tooling/structured-intelligence, MIT.
More from Scientific-Tooling/structured-intelligence
- 0.456score
download-geo
Scientific-Tooling
Download supplementary data files, series matrices, and raw FASTQ links from NCBI GEO for a given GSE series or GSM sample accession.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
metagenome-functional-profiling
Scientific-Tooling
Functional annotation of metagenomic data using HUMAnN 3 for pathway abundance, Prokka for gene prediction, and eggNOG-mapper for ortholog assignment.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
metagenome-host-removal
Scientific-Tooling
Remove host-derived reads from metagenomic samples by aligning to a host reference genome and extracting unmapped pairs.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
download-sra
Scientific-Tooling
Download raw sequencing data from NCBI SRA as FASTQ files using prefetch and fasterq-dump, with support for single accessions, batch lists, and BioProject…
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
ncbi-eutilities-assistant
Scientific-Tooling
Query NCBI Entrez databases through official E-utilities with deterministic search, summary, fetch, link, and history workflows.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
genome-alignment-qc
Scientific-Tooling
Assess alignment quality with coverage depth, mapping rates, insert size, and on-target metrics using samtools, mosdepth, and picard.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
design-thermostable-mutations
Scientific-Tooling
Decision-grade enzyme/protein mutation design for thermostability with bioactivity-preserving constraints enforced by default, plus structure-aware and…
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
genome-variant-annotation
Scientific-Tooling
Annotate variants with functional effects using SnpEff or Ensembl VEP, adding gene impact, population frequencies, and clinical significance.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
genome-variant-calling
Scientific-Tooling
Call SNVs and indels from aligned BAMs using GATK HaplotypeCaller or DeepVariant with optional GVCF output for joint genotyping.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
download-gdc
Scientific-Tooling
Download files from the NCI Genomic Data Commons (GDC) using the GDC Data Transfer Tool and REST API, supporting both open-access and controlled-access data.
SkillDFreshness: D★ 4Claude Code +9 - 0.453score
ngs-quality-control
Scientific-Tooling
Raw read quality assessment with FastQC and multi-sample report aggregation with MultiQC.
SkillDFreshness: D★ 4Claude Code +9 - 0.453score
genome-read-alignment
Scientific-Tooling
Align short reads to a reference genome with BWA-MEM2, sort and index with samtools, and mark duplicates with picard.
SkillDFreshness: D★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Mar 15, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Scientific-Tooling
- 0.456score
design-thermostable-mutations
Scientific-Tooling
Decision-grade enzyme/protein mutation design for thermostability with bioactivity-preserving constraints enforced by default, plus structure-aware and…
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
download-gdc
Scientific-Tooling
Download files from the NCI Genomic Data Commons (GDC) using the GDC Data Transfer Tool and REST API, supporting both open-access and controlled-access data.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
download-geo
Scientific-Tooling
Download supplementary data files, series matrices, and raw FASTQ links from NCBI GEO for a given GSE series or GSM sample accession.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
download-sra
Scientific-Tooling
Download raw sequencing data from NCBI SRA as FASTQ files using prefetch and fasterq-dump, with support for single accessions, batch lists, and BioProject…
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
genome-alignment-qc
Scientific-Tooling
Assess alignment quality with coverage depth, mapping rates, insert size, and on-target metrics using samtools, mosdepth, and picard.
SkillDFreshness: D★ 4Claude Code +9 - 0.456score
genome-variant-annotation
Scientific-Tooling
Annotate variants with functional effects using SnpEff or Ensembl VEP, adding gene impact, population frequencies, and clinical significance.
SkillDFreshness: D★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get metagenome-binning running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
metagenome-binning skill. Agent Mart. https://agentmart.dev/skills/scientific-tooling-metagenome-binning (last updated 2026-10-24)