phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/phylogenetics/SKILL.md

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 highly actionable with executable code and clear sectioning, but it is let down by missing validate/retry feedback loops and by ignoring its own bundle files. Signaling and offloading detail to the existing references/scripts would improve both workflow clarity and progressive disclosure.

Suggestions

Add explicit validation checkpoints and a fix-and-retry loop (e.g. verify the alignment length/columns, check IQ-TREE bootstrap support thresholds, re-run on failure) instead of only raising on non-zero exit.

Link the existing bundle files from the body ('See references/iqtree_inference.md for advanced model/partition testing' and 'See scripts/phylogenetic_analysis.py for the full runnable pipeline') and move the inlined IQ-TREE detail there to avoid duplication.

Tighten redundancies such as `model = "TEST" if sequence_type == "nt" else "TEST"` and the O(n^2) leaf-distance computation in basic_tree_stats.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and compact tables, but contains small redundancies (e.g. `model = "TEST" if sequence_type == "nt" else "TEST"`, an O(n^2) leaf-distance loop, and a copy-fallback in trim) and docstrings restating what the code shows; could be tightened.	2 / 3
Actionability	Provides fully executable Python functions with concrete CLI invocations (MAFFT/IQ-TREE 2/FastTree/TrimAl), specific method/model dictionaries, and copy-paste-ready pipeline scripts rather than pseudocode.	3 / 3
Workflow Clarity	The align -> trim -> tree -> visualize sequence is clearly numbered and tied together by a complete script, but validation is implicit (raise on non-zero returncode) with no validate -> fix -> retry feedback loops for these batch/destructive operations, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Bundle files exist (references/iqtree_inference.md, scripts/phylogenetic_analysis.py) but the body never references or links them; IQ-TREE detail is inlined rather than signaled and the bundled script is unreferenced, so structure is present but navigation to the bundles is missing.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 naming concrete tools and natural domain triggers, but it lacks an explicit 'Use when ...' trigger clause so the 'when' guidance is only implied. Adding an explicit use-when clause would raise completeness.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to build or analyze phylogenetic trees, infer evolutionary relationships, or trace viral/microbial lineages.'

Consider including common user phrasings ('phylogenetic tree', 'evolutionary tree', 'sequence alignment') as explicit trigger terms to reinforce the 'when' guidance.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools ('Build and analyze phylogenetic trees using MAFFT ... IQ-TREE 2 ... and FastTree', 'Visualize with ETE3 or FigTree'), matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	The 'what' is clear (align, infer, visualize with named tools), but the 'when' is only implied via a 'For ...' domain list rather than an explicit 'Use when ...' trigger clause, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Covers natural domain terms users would say ('phylogenetic trees', 'evolutionary analysis', 'microbial genomics', 'viral phylodynamics', 'protein family analysis', 'molecular clock studies'), giving good coverage of natural keywords.	3 / 3
Distinctiveness Conflict Risk	A clear, narrow niche (phylogenetics with MAFFT/IQ-TREE/FastTree/ETE3) with distinct triggers that are unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/phylogenetics/SKILL.md
Commit: 757b63b

Reviewed: about 10 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.