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

86%

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

81%Weight 40%Scale 1-5

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

The body is highly actionable and workflow-safe, with explicit validation checkpoints and feedback loops for fragile batch phylogenetic operations. Its main weaknesses are verbatim command repetition that hurts conciseness and an incomplete References section that leaves some bundle files under-signaled.

Suggestions

Deduplicate the repeated `phykit_batch_analysis` batch command blocks — show each operation once and reference it, removing the verbatim saturation/treeness repeats.

Complete the References section to list every bundle file actually used, including `references/troubleshooting.md` and the `scogs_paired_compare.py` / `scogs_phykit_pipeline.py` / `phykit_batch.py` / `busco_target_orthologs.py` scripts.

Move the long PhyKIT column-parsing cheat sheet and per-metric gotchas into `references/tree_building.md` or `references/parsimony_analysis.md`, keeping only a one-line pointer and the highest-signal rules in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but it is noticeably repetitive: the `phykit_batch_analysis` saturation/treeness batch commands appear ~3 times verbatim and the `phykit_batch.py` block largely duplicates the tool-based guidance, so it could be tightened.	3 / 5
Actionability	Guidance is fully executable — concrete Python imports, real bash invocations with flags (`--metric parsimony_informative`, `--per-tree-stat median`), and shown output-block formats (`# SUMMARY group=...`, `# MWU ...`) that make parsing copy-paste ready.	5 / 5
Workflow Clarity	A clear sequence is enforced by RULE ZERO (check pre-computed results first), a workflow decision tree, explicit feedback loops (sanity targets → 'count files first' / 're-derive the intersection'), and a completeness checklist; the batch operations do carry validation, so the cap-at-3 rule does not apply.	5 / 5
Progressive Disclosure	References are one level deep and scripts are clearly signaled inline in bash commands, and the body is well sectioned; however the References section is incomplete (it omits the existing `troubleshooting.md` and the heavily-used `scogs_*.py` scripts) and a ~500-line body inlines gotcha detail that partly belongs in the reference files.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 dense, specific description that clearly states capabilities and explicit use-when triggers with named tools, giving it strong specificity, completeness, and distinctiveness. Its only gap is the absence of file-extension trigger terms, which keeps trigger_term_quality just short of full marks.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions — 'de novo multiple sequence alignment (Clustal Omega/MUSCLE/MAFFT via EBI_msa_align)', 'neighbour-joining/UPGMA tree building (EBI_build_phylogenetic_tree)', 'treeness, saturation (PhyKIT), parsimony-informative sites, alignment gap analysis, DVMC, long-branch detection, BUSCO orthologs' — giving comprehensive, specific coverage rather than vague language.	5 / 5
Completeness	It explicitly answers both 'what' (a detailed capability list) and 'when' via the concrete trigger clause '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.'	5 / 5
Trigger Term Quality	Natural user-facing phrases are present ('align a set of sequences', 'build a tree from sequences or an alignment', 'phylogenetic tree QC', 'multi-gene phylogenomics', 'evolutionary-rate analysis') with method synonyms, but file-extension triggers (.fasta/.newick/.phylip) are absent, leaving a few common terms missing.	4 / 5
Distinctiveness Conflict Risk	The phylogenetics niche is clearly delimited with named tools (PhyKIT, Biopython, DendroPy, EBI services) and distinct triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	19 / 20 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: 1b02920

Reviewed: 1 day 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.