CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/phylogenetics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

Highly actionable with executable code and clear sequencing, but it inlines content that duplicates existing bundle files without ever linking to them, hurting progressive disclosure, and lacks explicit validation checkpoints for a batch pipeline.

Suggestions

Replace the inlined IQ-TREE section and full pipeline code with pointers to references/iqtree_inference.md and scripts/phylogenetic_analysis.py so SKILL.md stays an overview with one-level-deep references.

Add an explicit validation checkpoint after alignment (e.g., inspect/verify alignment quality before tree inference) and a verify-tree step with a fix-and-retry feedback loop.

Trim the conceptual Overview and verbose docstrings that re-explain phylogenetics basics Claude already knows.

DimensionReasoningScore

Conciseness

Mostly efficient actionable code with useful reference tables, but the conceptual Overview and verbose docstrings re-explain things Claude knows, and ~400 lines of inlined implementations could be tightened.

3 / 5

Actionability

Fully executable, copy-paste-ready functions for every pipeline stage plus a complete orchestrating script, with specific model guides and commands covering the common cases.

5 / 5

Workflow Clarity

Steps are clearly numbered (MAFFT → trim → tree → visualize) with return-code error handling, but as a batch operation it lacks explicit validation checkpoints (e.g., verify alignment quality before tree inference) and feedback loops in the workflow narrative, capping it at 3.

3 / 5

Progressive Disclosure

Bundle files exist (references/iqtree_inference.md, scripts/phylogenetic_analysis.py) that duplicate the inlined IQ-TREE content, yet the body never references or links them, inlining ~400 lines of code and reference tables that clearly belong in those separate files.

2 / 5

Total

13

/

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 strong, specific description that names concrete tools and actions and provides explicit use-case triggers. It would benefit from a couple of file-extension triggers but is otherwise comprehensive and distinct.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions (build/analyze trees, multiple alignment, ML inference, fast NJ/ML, visualization) named with specific tools (MAFFT, IQ-TREE 2, FastTree, ETE3, FigTree), giving comprehensive coverage.

5 / 5

Completeness

Clearly answers 'what' (build/analyze/visualize trees with named tools) and 'when' via the explicit 'For evolutionary analysis, microbial genomics, viral phylodynamics...' clause listing concrete trigger use-cases.

5 / 5

Trigger Term Quality

Strong natural keywords (phylogenetic trees, evolutionary analysis, microbial genomics, viral phylodynamics, molecular clock) but lacks file-extension triggers (.nwk, .fasta) and a few common synonyms, falling just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (phylogenetics) with tool-specific triggers (MAFFT, IQ-TREE 2, FastTree) that minimize overlap with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
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.