tooluniverse-phylogenetics

Production-ready phylogenetics and sequence analysis skill for alignment processing, tree analysis, and evolutionary metrics. Computes treeness, RCV, treeness/RCV, parsimony informative sites, evolutionary rate, DVMC, tree length, alignment gap statistics, GC content, and bootstrap support using PhyKIT, Biopython, and DendroPy. Performs NJ/UPGMA/parsimony tree construction, Robinson-Foulds distance, Mann-Whitney U tests, and batch analysis across gene families. Integrates with ToolUniverse for sequence retrieval (NCBI, UniProt, Ensembl) and tree annotation. Use when processing FASTA/PHYLIP/Nexus/Newick files, computing phylogenetic metrics, comparing taxa groups, or answering questions about alignments, trees, parsimony, or molecular evolution.

Quality

82%

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

65%

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

The body is well-organized and actionable with concrete code and a useful decision tree, but it carries redundant comparison tables and is missing the referenced bundle files it leans on for progressive disclosure. Batch workflows also lack explicit validation feedback loops.

Suggestions

Ship the referenced bundle files (references/sequence_alignment.md, tree_building.md, parsimony_analysis.md, troubleshooting.md, scripts/tree_statistics.py, scripts/format_alignment.py) or remove the references — the body currently points to files that do not exist.

Trim the ClustalW/MUSCLE/MAFFT and NJ/UPGMA/ML speed/accuracy comparison tables and the BixBench project-coverage table; these restate knowledge Claude already has and inflate the token budget.

Add an explicit validate→fix→retry feedback loop to the batch processing workflow (e.g. catch per-gene computation failures, log, retry, then re-verify the aggregate result) to satisfy the batch-operation validation requirement.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and tables, but padded with concepts Claude already knows — e.g. the ClustalW/MUSCLE/MAFFT and NJ/UPGMA/ML speed/accuracy comparison tables and the BixBench project-coverage table — that could be trimmed. Not level 3 because not every token earns its place; not level 1 because the bulk is actionable rather than explanatory prose.	2 / 3
Actionability	Provides copy-paste-ready executable snippets such as 'stats.mannwhitneyu(list(group1_treeness.values()), list(group2_treeness.values()), alternative='two-sided')' and 'tu.tools.NCBI_get_sequence(accession="NP_000546")'. Not level 2, which would use pseudocode or be missing key details.	3 / 3
Workflow Clarity	A clear decision tree and a 'Completeness Checklist' give sequencing, but batch operations (the skill's core) lack an explicit validate→fix→retry feedback loop; the checklist is pre-answer verification rather than error recovery. Per the rubric's feedback-loop note for batch operations this caps it at 2; not level 1 because steps are clearly sequenced.	2 / 3
Progressive Disclosure	References are well-signaled and one level deep in design ('See references/tree_building.md', 'See references/parsimony_analysis.md'), but the referenced references/ and scripts/ directories do not exist on disk, so the progressive disclosure is broken in practice. Not level 3 because the referenced detail files are missing; not level 1 because the signaling and organization are sound.	2 / 3
	Total	9 / 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.

The description is excellent: it enumerates concrete capabilities, names the underlying tools, and provides an explicit 'Use when' trigger clause covering file formats and question types. It is both specific and clearly scoped, with strong natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'Computes treeness, RCV, treeness/RCV, parsimony informative sites, evolutionary rate, DVMC, tree length, alignment gap statistics, GC content, and bootstrap support' and 'Performs NJ/UPGMA/parsimony tree construction, Robinson-Foulds distance, Mann-Whitney U tests' — matching the multiple-specific-actions anchor; not the level below, which only names a domain and some actions.	3 / 3
Completeness	Explicitly answers both 'what' (enumerated computations) and 'when' via 'Use when processing FASTA/PHYLIP/Nexus/Newick files, computing phylogenetic metrics, comparing taxa groups, or answering questions about alignments, trees, parsimony, or molecular evolution.' Not level 2, where the 'when' is missing or only implied.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'FASTA/PHYLIP/Nexus/Newick files', 'phylogenetic metrics', 'alignments, trees, parsimony, or molecular evolution' — terms a user would actually say. It is not level 2, which would have only some relevant keywords missing common variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche (PhyKIT/Biopython/DendroPy phylogenetics) with distinct file-format and metric triggers unlikely to fire for other skills. Not level 2, which could still overlap with similar 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
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-phylogenetics/SKILL.md
Commit: df37802

Reviewed: 2 days 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.