Agent skill

Bio Phylo Tree Manipulation

by GPTomics in GPTomics/bioSkills

Edit phylogenetic tree structure with Biopython Bio.Phylo, and treat rooting as a separate statistical inference rather than a display choice.

MITAuto-check passedResearch & Science

Install Bio Phylo Tree Manipulation

skills CLI
$ npx skills add GPTomics/bioSkills --skill bio-phylo-tree-manipulation -a claude-code

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

GitHub CLI
$ gh skill install GPTomics/bioSkills bio-phylo-tree-manipulation --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/GPTomics/bioSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/phylogenetics/tree-manipulation .claude/skills/bio-phylo-tree-manipulation && 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
bio-phylo-tree-manipulation
GitHub stars
1.2k
Used in
1 other repo
Token cost
~5k tokens
SKILL.md length
2,166 words
Files
6
Skills in repo
559
Repo updated
First seen
Licence
MIT

At a glance

Edit phylogenetic tree structure with Biopython Bio.Phylo, and treat rooting as a separate statistical inference rather than a display choice.

  • Works in 3 steps: Rooting needs its own justification and… → The deep nodes near an outgroup-defined… → The choice of rooting METHOD is a…
  • Subsetting taxa
  • SKILL.md covers Version Compatibility, The Single Most Important…, Rooting Method Decision and Tool Taxonomy, plus 9 more sections
  • Runs Python scripts from its folder; calls pip

What it does

Bio Phylo Tree Manipulation is an agent skill from GPTomics/bioSkills. Edit phylogenetic tree structure with Biopython Bio.Phylo, and treat rooting as a separate statistical inference rather than a display choice. Covers why most inference returns an unrooted tree so placing the root creates every ancestor/descendant and basal claim; why a distant or lonely outgroup misroots inside the ingroup via long-branch attraction; the outgroup/midpoint/MAD/MinVar/non-reversible-likelihood rooting tradeoffs; why pruning must suppress degree-2 nodes and sum their branch lengths or all patristic…

Its SKILL.md is about 5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `examples/collapse_support.py`, `examples/common_ancestor.py` and `examples/prune_taxa.py`).

It sits in Research & Science, covering Bioinformatics and Data visualization. It works with Biopython and Python. The repository describes itself as: a set of SKILLS.md for doing bioinformatics with agents like claude code. The licence is MIT.

When your agent uses it

  • Subsetting taxa
  • Extracting a clade
  • Induced subtree
  • Collapsing low-support branches

Example prompts

  • “/bio-phylo-tree-manipulation”

Requirements

  • Python 3

Workflow steps

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

  1. Rooting needs its own justification and its own uncertainty statement, distinct from branch support. Bootstrap 95 on an ingroup clade says…
  2. The deep nodes near an outgroup-defined root are the LEAST trustworthy. A distant outgroup sits on a long branch, and long branches…
  3. The choice of rooting METHOD is a modeling choice with assumptions (clock? outgroup monophyly? non-reversible model?), and the wrong…

What it can do on your machine

Read from SKILL.md and the folder at commit d91ed3d. 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:

    • pip

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

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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

Bio Phylo Tree Manipulation loads about 5k tokens when it runs. Until then it costs about 244 tokens; SKILL.md has 2,166 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~244
When it runs · the whole SKILL.md, loaded when a task matches
~5k

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 GPTomics/bioSkills at commit d91ed3d, republished under its MIT licence (© GPTomics). 2,166 words, ~4,985 tokens.

Download SKILL.mdSave it as .claude/skills/bio-phylo-tree-manipulation/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
bio-phylo-tree-manipulation
description
Edit phylogenetic tree structure with Biopython Bio.Phylo, and treat rooting as a separate statistical inference rather than a display choice. Covers why most inference returns an unrooted tree so placing the root creates every ancestor/descendant and basal claim; why a distant or lonely outgroup misroots inside the ingroup via long-branch attraction; the outgroup/midpoint/MAD/MinVar/non-reversible-likelihood rooting tradeoffs; why pruning must suppress degree-2 nodes and sum their branch lengths or all patristic distances silently corrupt; and why collapsing by support makes SOFT (uncertainty) polytomies, not HARD (radiation) ones. Use when rooting, re-rooting, pruning or subsetting taxa, extracting a clade or induced subtree, collapsing low-support branches, resolving polytomies, or ladderizing. Routes clock-based rooting to divergence-dating, inference to modern-tree-inference, and reading/plotting to tree-io and tree-visualization.
tool_type
mixed
primary_tool
Bio.Phylo

Version Compatibility

Reference examples tested with: BioPython 1.83+. Alternatives: ape 5.8+ / phangorn / phytools (R), DendroPy 5+ and ete3 (Python), Newick Utilities 1.6+, MAD and RootDigger as standalone CLIs.

Before using code patterns, verify installed versions match. If versions differ:

  • Python: pip show biopython then help(module.function) to check signatures
  • R: packageVersion('ape') then ?drop.tip to verify parameters
  • CLI: <tool> --version then <tool> --help to confirm flags

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

ape has NO midpoint function of its own (use phangorn::midpoint or phytools::midpoint.root); ete3 prune drops branch lengths unless preserve_branch_length=True; ape di2multi filters by branch LENGTH (tol), not support.

Tree Manipulation -- Rooting Is an Inference, Not a Cosmetic Operation

"Root and prune my tree" -> Edit an existing tree object, treating the root placement as a separate statistical inference and every structural edit as potentially distance-corrupting.

  • Python: tree.root_with_outgroup(...), tree.root_at_midpoint(), tree.prune(...), tree.collapse_all(...) (Bio.Phylo)
  • R: root(), phangorn::midpoint(), drop.tip(), di2multi() (ape/phangorn); CLI: nw_reroot, nw_prune (Newick Utilities); outgroup-free rooters: mad, FastRoot.py, rootdigger

Scope: editing an existing tree -- rooting, pruning/subsetting, extracting clades or induced subtrees, collapsing branches into polytomies, resolving polytomies, ladderizing. Reading/writing/converting tree files -> tree-io. Plotting and mapping annotations -> tree-visualization. Inferring the tree in the first place -> modern-tree-inference. Clock-based or Bayesian rooting co-estimated with dates -> divergence-dating.

The Single Most Important Modern Insight

Rooting is a separate statistical inference layered on top of the topology, and it is the highest-error decision in the entire tree. Nearly every inference method (ML under a time-reversible model, neighbor-joining, most Bayesian runs) returns an UNROOTED tree: a reversible model is blind to the direction of time, so the likelihood is identical wherever the root sits. The unrooted tree states which taxa are neighbors; it is silent about who is ancestor and who is descendant. Placing the root is what converts a neighbor-graph into an evolutionary narrative, and it CREATES every "X is basal", every "the common ancestor had trait T", every character-polarity, every divergence ordering. Three load-bearing facts:

  1. Rooting needs its own justification and its own uncertainty statement, distinct from branch support. Bootstrap 95 on an ingroup clade says nothing about whether the root is in the right place. The relationships can be robust while the root -- the thing every downstream story hangs on -- is the least reliable part of the figure.
  2. The deep nodes near an outgroup-defined root are the LEAST trustworthy. A distant outgroup sits on a long branch, and long branches attract each other (long-branch attraction): the outgroup pulls the fastest ingroup taxon toward the root and makes it look artifactually "basal". Accuracy degrades monotonically as outgroup distance grows.
  3. The choice of rooting METHOD is a modeling choice with assumptions (clock? outgroup monophyly? non-reversible model?), and the wrong method silently fabricates basal lineages. Pruning, collapsing, and ladderizing are comparatively mechanical -- but each has its own silent traps (distance corruption, soft/hard polytomy conflation, perceived trends).

Rooting Method Decision

MethodCore assumptionNeedsRobust to rate variationGives root uncertaintyBest whenAvoid when
Outgroup (multiple, close)outgroup truly outside ingroup, not LBA-misplaceda priori outgroup taxa + sequencesmoderate (depends on outgroup branch)weakly (via ingroup-monophyly check)closely related, balanced, monophyletic outgroups existonly a distant/lonely outgroup available
Outgroup (single)same, but one long branchone outgroup taxonpoor (max LBA exposure)noa close single sister exists, nothing betteronly a distant/lonely outgroup (one long branch, max LBA exposure)
Midpointstrict molecular clocktree with branch lengthsnonoshallow, clock-like, intraspecific/viral datadeep trees, heterotachy, any long branch
MinVarclock deviations are random/unbiasedtree with branch lengthsbetter than midpointnooutgroup-free, noise looks like unbiased clock scatterstrong lineage-specific rate shifts
MADminimal relative ancestor deviationtree with branch lengthsyes (tolerates heterotachy)yes (root ambiguity index)outgroup-free deep/prokaryotic trees; default no-outgroup choicestrongly structured rate variation
Non-reversible likelihood (RootDigger / IQ-TREE)non-reversible model carries directional signaltree + ALIGNMENT; enough datayes (model-based)yes (per-branch likelihood confidence)the alignment is available and a root confidence is neededlittle data; weak signal; compute-limited
Relaxed clock (BEAST) -> divergence-datingexplicit clock + tree prioralignment + calibrations/tip dates; MCMCyesyes (posterior over roots)time-scaled / dated / phylodynamic analysesa quick structural edit, no dating intended

Rule: never report a root from a single method without a sanity check. If a close, monophyletic outgroup is available, use it. If not, run MAD and MinVar and prefer agreement; disagreement means the root is poorly determined and all "basal" claims must be hedged. With an alignment and a need for a confidence value, use RootDigger (Bettisworth and Stamatakis 2021) or non-reversible IQ-TREE. MAD = Tria et al. 2017; MinVar = Mai et al. 2017; outgroup-free CLIs and Newick Utilities = Junier and Zdobnov 2010.

Tool Taxonomy

Tool (lang)RootingPruning / cladeCollapse / resolveWhen
Bio.Phylo (Py)root_with_outgroup, root_at_midpointprune, common_ancestorcollapse_allgeneral Python pipelines; the default here
ape / phangorn / phytools (R)root, phangorn::midpoint, phytools::midpoint.rootdrop.tip, extract.cladedi2multi, multi2diR workflows; drop.tip sums suppressed branch lengths correctly
DendroPy (Py)reroot_at_edge, reroot_at_midpointretain_taxa_with_labels(suppress_unifurcations=True)edge collapse, resolve_polytomiesmetadata-aware edits, posterior tree sets
ete3 (Py)set_outgroup, set_outgroup(get_midpoint_outgroup())prune([...], preserve_branch_length=True), detachdelete, resolve_polytomyNHX features; MUST pass preserve_branch_length
Newick Utilities (CLI)nw_rerootnw_prune, nw_cladenw_ed, nw_condensestreaming/Unix-pipeline edits on many trees
MAD / MinVar / RootDigger (CLI)mad, FastRoot.py, rootdigger----outgroup-free or likelihood rooting when no trustworthy outgroup exists

Root with an Outgroup (Multiple, Monophyletic)

Goal: Root the tree using known sister-group taxa, preferring multiple close outgroups and verifying ingroup monophyly first.

Approach: Confirm the outgroup taxa form a monophyletic group, root on the branch separating them from the ingroup, then check the ingroup is recovered as monophyletic -- if not, the rooting is suspect.

python
from Bio import Phylo

tree = Phylo.read('tree.nwk', 'newick')
outgroup = [{'name': 'OutA'}, {'name': 'OutB'}]      # multiple close outgroups beat a single long branch

if tree.is_monophyletic([tree.find_any(name='OutA'), tree.find_any(name='OutB')]):
    tree.root_with_outgroup(*outgroup)               # root_with_outgroup, NOT root_with_midpoint
else:
    print('outgroup not monophyletic: root placement is unreliable, re-check taxon choice')

Root at the Midpoint (Clock-Limited Fallback)

Goal: Root an outgroup-free tree where evolution is approximately clock-like (shallow/viral data).

Approach: Place the root at the midpoint of the longest tip-to-tip path; trust it only when no single long branch can hijack that path. For deep trees with rate variation prefer MAD/MinVar.

python
tree = Phylo.read('tree.nwk', 'newick')
tree.root_at_midpoint()                              # assumes a clock; a long branch slides the root onto the fast lineage
# Outgroup-free and clock-relaxed (deep trees): standalone CLIs run on the Newick file
# MAD:    mad tree.nwk           -> tree.nwk.rooted   (per-branch root ambiguity index)
# MinVar: FastRoot.py -i tree.nwk -m MV -o rooted.nwk

Prune Taxa With Branch-Length Preservation

Goal: Remove tips and keep every surviving patristic distance unchanged.

Approach: Drop the tip and SUPPRESS the resulting degree-2 ("knee") node, ADDING its branch length to the child so path lengths are conserved. Bio.Phylo prune and ape drop.tip do this by default; ete3 prune needs preserve_branch_length=True.

python
tree = Phylo.read('tree.nwk', 'newick')
keep = {'Human', 'Chimp', 'Mouse'}

for term in list(tree.get_terminals()):
    if term.name not in keep:
        tree.prune(term)                             # collapses the degree-2 parent and sums branch lengths
# ape (R):   drop.tip(phy, c('X','Y'))               # sums suppressed branch lengths by default
# ete3 (Py): tree.prune(list(keep), preserve_branch_length=True)   # the flag is mandatory, else distances shrink

Non-monophyletic targets cannot be "extracted as a clade" -- there is no node whose descendants are exactly those taxa. Prune to the taxon set to get the induced subtree instead; common_ancestor of non-monophyletic taxa returns an MRCA whose clade contains EXTRA taxa.

Collapse Low-Support Branches Into SOFT Polytomies

Goal: Replace poorly-supported resolved nodes with multifurcations that honestly say "unresolved".

Approach: Collapse any internal branch whose support is below a stated cutoff. The result is a SOFT (uncertainty) polytomy, never a HARD (simultaneous-radiation) one -- label it as such.

python
tree = Phylo.read('tree.nwk', 'newick')              # support parsed into clade.confidence

tree.collapse_all(lambda c: c.confidence is not None and c.confidence < 70)   # 70 for std bootstrap; use 95 for UFBoot2
tree.collapse_all(lambda c: c.branch_length is not None and c.branch_length < 1e-8)   # collapse genuinely-zero branches
# ape (R): di2multi filters by LENGTH (tol), not support -> zero out low-support branch lengths first, THEN di2multi(phy)

Resolving the inverse direction (multi2di / resolve_polytomy) invents an arbitrary order with zero-length branches; analyzing one random resolution treats an arbitrary choice as fact. If a binary tree is required, integrate over many random resolutions and treat the inserted zero-length branches as "no information", not instantaneous divergence.

Per-Method Failure Modes

Distant Outgroup Roots Inside the Ingroup

Trigger: A single distant outgroup, or many outgroups all far from the ingroup, used to root. Mechanism: The long outgroup branch attracts the fastest ingroup taxon (LBA), pulling the root into the ingroup; far outgroups attach at essentially random positions (DeSalle et al. 2023). Symptom: Ingroup not recovered as monophyletic; a fast taxon appears "basal"; the root jumps as the outgroup set changes. Fix: Use multiple CLOSELY-related, monophyletic, roughly-equidistant outgroups; verify ingroup monophyly; treat a lonely distant outgroup as a red flag.

Show full SKILL.md (904 more words)Show less
Single Distant Outgroup -- Long-Branch Misrooting

Trigger: Rooting on one distant outgroup taxon. Mechanism: One unbroken long branch maximizes LBA exposure, with no way to subdivide it or check ingroup monophyly, so the root is drawn toward other long branches. Symptom: The root lands inside the ingroup or on a spurious deep branch; deep nodes near the root are unstable across analyses. Fix: Add multiple closer, monophyletic outgroups to subdivide the long branch and enable a monophyly check, or use an outgroup-free method (MAD/MinVar).

Midpoint Misroots Under Rate Variation

Trigger: Midpoint rooting a deep tree with heterotachy or any long branch. Mechanism: Midpoint assumes a clock; a long branch hijacks the longest path and slides the root onto the fast lineage. Symptom: A rate-elevated taxon appears earliest-diverging; the root sits on a suspiciously long branch. Fix: Use MAD or MinVar (clock-relaxed) or a close outgroup; report root uncertainty and hedge "basal".

Soft vs Hard Polytomy Conflation

Trigger: Collapsing branches below a support threshold, then describing the multifurcation as a radiation. Mechanism: Threshold-collapse encodes UNCERTAINTY (soft polytomy = "we cannot resolve the order"); a hard polytomy is a biological claim of simultaneous divergence -- different meanings. Symptom: A paper claims simultaneous divergence from what is just unresolved data. Fix: Label threshold-collapsed nodes as unresolved/soft; never read them as a biological radiation.

Pruning Leaves a Spurious Node or Drops Distances

Trigger: A tool that leaves the degree-2 node in place, or removes it without summing branch lengths (notably ete3 prune without preserve_branch_length=True). Mechanism: The suppressed knee's branch length is not added to its child, so every path through that lineage shortens. Symptom: Patristic distances shrink; subsequent midpoint/MAD/MinVar rooting on the pruned tree is now wrong. Fix: Use Bio.Phylo prune / ape drop.tip (correct by default) or pass ete3 preserve_branch_length=True; verify a known pairwise distance is unchanged.

Randomly Resolving a Polytomy Biases Downstream

Trigger: multi2di / resolve_polytomy to satisfy a binary-tree requirement, then analyzing the single tree. Mechanism: An arbitrary order with zero-length branches is invented; the downstream result depends on a topology the data never supported. Symptom: Results that change under a different random resolution. Fix: Integrate over many resolutions and summarize; treat zero-length branches as "no info", not instantaneous divergence.

Ladderizing Manufactures an Apparent Trend

Trigger: Ladderizing a figure so one lineage sits visually at the top/bottom. Mechanism: Rotation about internal nodes changes no topology, branch lengths, or bipartitions, but readers unconsciously read the staircase as an early-to-late sequence. Symptom: Reviewers infer a basal-to-derived trend that does not exist. Fix: Ladderize only for legibility; state that rotation changes no biology. -> tree-visualization.

Quantitative Thresholds

QuantityValueSource / rationale
Midpoint root recovery, single-outgroup source data~54% (barely a coin flip)Hess and Russo 2007
Midpoint root recovery, multiple-outgroup source data~82% (inconsistent) to ~94% (consistent)Hess and Russo 2007
MAD accuracy on benchmarks>~70%, beating midpointTria et al. 2017
MinVar vs midpointmatched or beat midpoint in all simulated conditionsMai et al. 2017
Bootstrap collapse cutoff<50% (near-uninformative floor) or <70% (reliability boundary); state whichcommon practice
UFBoot2 collapse cutoff<95% (a different scale from bootstrap -- not 70)Hoang 2018
Bayesian posterior collapse cutoff<0.95common practice
Zero-length collapse tolerance~1e-8 (or machine epsilon)removes genuinely-zero branches without deleting real short ones
Outgroup distanceaccuracy degrades monotonically with distanceprefer the closest credible outgroup

Common Errors

Error / symptomCauseSolution
ape::midpoint function-not-foundmidpoint is not in base apeuse phangorn::midpoint or phytools::midpoint.root
Pruned tree has wrong distancesdegree-2 node not suppressed / not summedBio.Phylo prune / ape drop.tip default, or ete3 preserve_branch_length=True
"Extract the clade of X,Y,Z" returns extra taxa or NoneX,Y,Z are not monophyleticprune to the taxon set (induced subtree) instead of extracting a clade
di2multi(tol) did not drop low-support nodestol filters branch LENGTH, not supportzero out low-support branch lengths first, then di2multi
Bootstrap re-read as support for a pruned subtreesupport was computed on the full taxon setre-run inference on the subset for valid support
MAD and MinVar disagree on the rootthe root is genuinely poorly determinedtreat as uncertain; seek a close outgroup or RootDigger confidence; hedge all ancestral claims
root_with_midpoint AttributeErrorno such methodthe methods are root_at_midpoint() and root_with_outgroup()

References

Tria FDK, Landan G, Dagan T. 2017. Phylogenetic rooting using minimal ancestor deviation. Nature Ecology & Evolution 1:0193. Mai U, Sayyari E, Mirarab S. 2017. Minimum variance rooting of phylogenetic trees and implications for species tree reconstruction. PLOS ONE 12(8):e0182238. Bettisworth B, Stamatakis A. 2021. Root Digger: a root placement program for phylogenetic trees. BMC Bioinformatics 22:225. Hess PN, De Moraes Russo CA. 2007. An empirical test of the midpoint rooting method. Biological Journal of the Linnean Society 92(4):669-674. DeSalle R, Narechania A, Tessler M. 2023. Multiple outgroups can cause random rooting in phylogenomics. Molecular Phylogenetics and Evolution 184:107806. Junier T, Zdobnov EM. 2010. The Newick utilities: high-throughput phylogenetic tree processing in the Unix shell. Bioinformatics 26(13):1669-1670. Huerta-Cepas J, Serra F, Bork P. 2016. ETE 3: reconstruction, analysis, and visualization of phylogenomic data. Molecular Biology and Evolution 33(6):1635-1638. Paradis E, Schliep K. 2019. ape 5.0: an environment for modern phylogenetics and evolutionary analyses in R. Bioinformatics 35(3):526-528.

  • tree-io - reading and writing the trees these edits consume and produce, without dropping annotations
  • tree-visualization - ladderize is a perception choice; mapping support onto branches
  • divergence-dating - clock-based and Bayesian rooting co-estimated with node ages, not bolted on by midpoint
  • modern-tree-inference - produces the unrooted ML tree and the support values these edits act on

© GPTomics, 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 5 other files in phylogenetics/tree-manipulation of GPTomics/bioSkills.

  • SKILL.md
  • examples/collapse_support.py
  • examples/common_ancestor.py
  • examples/prune_taxa.py
  • examples/root_tree.py
  • usage-guide.md

Open the folder on GitHubat commit d91ed3d

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 GPTomics/bioSkills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Bio Phylo Tree Manipulation 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.

Bio Phylo Tree Manipulation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bio Phylo Tree Manipulation this skillGPTomics/bioSkills1.2k1 repos~5kAutomated safety check: PassMIT
deepTools NGS Toolkitdavila7/claude-code-templates33k12 repos~4.5kAutomated safety check: PassMIT
FBA Flux Analyzeraiming-lab/AutoResearchClaw15k—~2.3kAutomated safety check: PassMIT
Biopythondavila7/claude-code-templates33k12 repos~3.4kAutomated safety check: PassMIT
Ggetdavila7/claude-code-templates33k10 repos~6.3kAutomated safety check: PassMIT
GgetK-Dense-AI/scientific-agent-skills48k1 repos~2.8kAutomated safety check: NotesBSD-2-Clause

Similar skills

  • 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.

    33k GitHub starsUsed in 12 repos~4.5k tokens
    Research & ScienceAuto-check passed
  • FBA Flux Analyzer

    aiming-lab/AutoResearchClaw

    Turns raw flux balance analysis output and a COBRApy model into gene essentiality maps, phenotypic phase planes, flux sampling results, pathway summaries and secretion predictions.

    15k GitHub stars~2.3k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Biopython

    davila7/claude-code-templates

    Primary Python toolkit for molecular biology. An agent skill from davila7/claude-code-templates.

    33k GitHub starsUsed in 12 repos~3.4k tokens
    Research & ScienceAuto-check passed
  • Gget

    davila7/claude-code-templates

    CLI/Python toolkit for rapid bioinformatics queries. An agent skill from davila7/claude-code-templates.

    33k GitHub starsUsed in 10 repos~6.3k tokens
    Research & ScienceAuto-check passed
  • Gget

    K-Dense-AI/scientific-agent-skills

    Queries 20+ bioinformatics resources through CLI/Python. An agent skill from K-Dense-AI/scientific-agent-skills.

    48k GitHub starsUsed in 1 repo~2.8k tokens
    Research & ScienceAuto-check: notes
  • Biopython

    K-Dense-AI/scientific-agent-skills

    Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez).

    48k GitHub starsUsed in 1 repo~4.3k tokens
    Research & ScienceAuto-check: notes

More from GPTomics/bioSkills

All 559 skills in this repo
  • Bio Alignment Io

    GPTomics/bioSkills

    Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO.

    1.2k GitHub starsUsed in 3 repos~4.9k tokens
    Auto-check passed
  • bioSkills Installer

    GPTomics/bioSkills

    Installs the bioSkills collection of 425 bioinformatics skills in one step, or only chosen categories, so sequencing, RNA-seq, single-cell and variant tasks get specialized help.

    1.2k GitHub starsUsed in 1 repo~789 tokens
    Auto-check passed
  • Bio Write Sequences

    GPTomics/bioSkills

    Write biological sequences to files (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO.

    1.2k GitHub starsUsed in 3 repos~2.1k tokens
    Auto-check passed
  • Amplicon Primer Clipping

    GPTomics/bioSkills

    Soft- or hard-clips PCR primer footprints from aligned amplicon BAMs so primer bases stop masquerading as confirmed reference sequence.

    1.2k GitHub starsUsed in 2 repos~2.2k tokens
    Auto-check passed
  • Filters BAM alignments by FLAG bits, mapping quality and regions with samtools view or pysam, with recipes for common keep and drop cases.

    1.2k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed
  • Bio Alignment Indexing

    GPTomics/bioSkills

    Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam.

    1.2k GitHub starsUsed in 2 repos~2.4k tokens
    Auto-check passed

Works with

Questions about Bio Phylo Tree Manipulation

What does Bio Phylo Tree Manipulation do?

Edit phylogenetic tree structure with Biopython Bio.Phylo, and treat rooting as a separate statistical inference rather than a display choice. Bio Phylo Tree Manipulation is an agent skill from GPTomics/bioSkills.Phylo, and treat rooting as a separate statistical inference rather than a display choice.

When should I use Bio Phylo Tree Manipulation?

Bio Phylo Tree Manipulation fits situations like: subsetting taxa; extracting a clade; induced subtree; collapsing low-support branches.

How do I install Bio Phylo Tree Manipulation in Claude Code?

Run `npx skills add GPTomics/bioSkills --skill bio-phylo-tree-manipulation -a claude-code`. Or copy the skill folder (phylogenetics/tree-manipulation in GPTomics/bioSkills) into .claude/skills/bio-phylo-tree-manipulation in your project. Claude Code loads it when a task matches its description.

How do I install Bio Phylo Tree Manipulation in Codex?

Run `npx skills add GPTomics/bioSkills --skill bio-phylo-tree-manipulation -a codex`. Or copy the skill folder (phylogenetics/tree-manipulation in GPTomics/bioSkills) into .agents/skills/bio-phylo-tree-manipulation in your project. Codex loads it when a task matches its description.

Can I use Bio Phylo Tree Manipulation 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 GPTomics/bioSkills --skill bio-phylo-tree-manipulation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bio-phylo-tree-manipulation, .gemini/skills/bio-phylo-tree-manipulation, .github/skills/bio-phylo-tree-manipulation and .opencode/skills/bio-phylo-tree-manipulation in your project.

What does Bio Phylo Tree Manipulation need to run?

Going by SKILL.md and its folder, Bio Phylo Tree Manipulation needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Bio Phylo Tree Manipulation access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Bio Phylo Tree Manipulation 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 Bio Phylo Tree Manipulation use?

Bio Phylo Tree Manipulation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bio Phylo Tree Manipulation use?

About 5k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bio Phylo Tree Manipulation?

Skills that share tags, products or a category with Bio Phylo Tree Manipulation: deepTools NGS Toolkit (davila7/claude-code-templates, 33k stars), FBA Flux Analyzer (aiming-lab/AutoResearchClaw, 15k stars), Biopython (davila7/claude-code-templates, 33k stars) and Gget (davila7/claude-code-templates, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bio Phylo Tree Manipulation?

GPTomics (a GitHub organization) maintains it in GPTomics/bioSkills, which has 1,218 GitHub stars. The repository holds 559 skills in this directory. The repository was last updated on August 15, 2026.

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