tooluniverse-phylogenetics

Phylogenetic analysis — de novo multiple sequence alignment (Clustal Omega/MUSCLE/MAFFT via EBI_msa_align) and neighbour-joining/UPGMA tree building (EBI_build_phylogenetic_tree) from your own sequences, plus tree analysis, treeness, saturation (PhyKIT), parsimony-informative sites, alignment gap analysis, DVMC, long-branch detection, BUSCO orthologs. Uses PhyKIT, Biopython, DendroPy. Use to align a set of sequences, build a tree from sequences or an alignment, or for phylogenetic tree QC, multi-gene phylogenomics, evolutionary-rate analysis, and comparative-genomics studies.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with strong workflow sequencing and validation feedback loops for batch phylogenetic work, but it is verbose with some redundancy and basic concept explanations, and its bundle references are not woven into the body as clear one-level-deep navigation.

Suggestions

Tighten conciseness by removing concepts Claude already knows (e.g. the definition of treeness/internal branches) and de-duplicating the phykit_batch_analysis guidance that recurs across Common Patterns, Analysis conventions, and PhyKIT usage sections.

Improve progressive disclosure by linking reference files inline where relevant (e.g. "for alignment formatting see references/sequence_alignment.md") instead of a flat unlinked list, and add the unreferenced references/troubleshooting.md to navigation.

Move the long PhyKIT column-position cheat sheet and per-metric conventions into a reference file, keeping SKILL.md as an overview that points to those details.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and rich in non-obvious gotchas, but it is verbose for its length: it explains concepts Claude already knows ("Treeness = sum of internal branch lengths / total tree length. Internal branches are those that do not lead to a leaf") and repeats the phykit_batch_analysis tool guidance across several sections, so it could be tightened.	2 / 3
Actionability	Packed with fully executable, copy-paste-ready commands (scogs_paired_compare.py invocations, `tu run phykit_batch_analysis '{...}'`, complete Python import blocks) plus concrete output-block examples, matching the anchor for executable code and specific examples.	3 / 3
Workflow Clarity	Clear sequencing (RULE ZERO first, a Workflow Decision Tree, a Completeness Checklist) with explicit validation/sanity-check feedback loops for batch operations ("if your computed RCV/treeness/DVMC median diverges ... by >10%, count files first"), so batch workflow clarity is not capped at 2.	3 / 3
Progressive Disclosure	Bundle files exist and a References section lists several, but references are a flat, unlinked list at the end rather than well-signaled inline navigation; the long Analysis conventions/PhyKIT usage content that could live in reference files is inline, and references/troubleshooting.md is never referenced.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that names concrete capabilities, includes natural trigger terms, and explicitly covers both what the skill does and when to use it, all in third person. It is slightly dense but earns its length with concrete, distinguishing detail.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "de novo multiple sequence alignment", "neighbour-joining/UPGMA tree building", "treeness, saturation, parsimony-informative sites, alignment gap analysis, DVMC, long-branch detection, BUSCO orthologs" — rather than vague language, matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly answers both what (alignment/tree-building/analysis capabilities) and when via the explicit "Use to align a set of sequences, build a tree ... or for phylogenetic tree QC ..." trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Natural user-facing triggers are well covered: "align a set of sequences", "build a tree from sequences or an alignment", "phylogenetic tree QC", "multi-gene phylogenomics", "evolutionary-rate analysis", "comparative-genomics studies" — terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Phylogenetics is a clear, narrow niche with distinct triggers (sequence alignment, tree building, PhyKIT metrics) that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (513 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-phylogenetics/SKILL.md
Commit: 089eb8e

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.