CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is tooluniverse-phylogenetics in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 with explicit validation checkpoints and copy-paste commands, but it is long and somewhat redundant (two batch-mechanism descriptions), and its progressive disclosure is weak — references are real but under-signaled while bulk detail is inlined.

Suggestions

Consolidate the duplicate PhyKIT batch guidance: present either `phykit_batch.py` or the `phykit_batch_analysis` tool as the primary path and demote the other to a one-line alternative to cut ~80 lines.

Move the detailed PhyKIT column-position cheat sheet and per-metric parsing rules into references/tree_building.md or a dedicated reference, keeping only the 'use the tool, it returns the right column' guidance inline.

Signal each reference where it is relevant (e.g., 'See references/sequence_alignment.md for full PhyKIT column parsing') instead of a single unlinked list at the end.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes competence, but the ~510-line body repeats batch-processing guidance in two forms (the `phykit_batch.py` script and the `phykit_batch_analysis` tool) and restates the same command examples, which is noticeable padding that could be consolidated.

3 / 5

Actionability

Copy-paste-ready bash and Python commands with exact argument names, documented stdout output blocks, column-parsing tables, and worked examples fully cover the common cases.

5 / 5

Workflow Clarity

RULE ZERO gives explicit ordering with validation checkpoints (pre-computed files first), sanity targets flag wrong-column/wrong-subset errors, and batch operations include feedback loops ('count files first', re-run with both per-tree stats if uncertain).

5 / 5

Progressive Disclosure

Real referenced files exist (references/sequence_alignment.md, tree_building.md, parsimony_analysis.md, scripts/tree_statistics.py), but a large amount of detail that belongs in those references is inlined in the body and the reference list is a bare one-liner buried at the very end rather than clearly signaled near the relevant sections.

3 / 5

Total

16

/

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.

The description is concrete, tool-named, and explicitly pairs a 'what' with a 'Use to...' 'when' clause, hitting the top anchors on specificity, completeness, and distinctiveness. Only minor synonym/extension gaps keep trigger-term quality at a strong 4.

DimensionReasoningScore

Specificity

Lists multiple concrete named 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, ... DVMC, long-branch detection, BUSCO orthologs' — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (alignment, tree building, QC metrics) and when ('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.') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-term coverage ('align a set of sequences', 'build a tree from sequences or an alignment', 'phylogenetic tree QC', 'multi-gene phylogenomics', 'evolutionary-rate analysis'), but file extensions like .fasta/.newick/.phylip and the synonym 'tree reconstruction' are missing, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clear niche (phylogenetics and sequence alignment) with named tools and specific triggers that would not naturally fire for unrelated skills; minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.