etetoolkit
Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.
73
66%
Does it follow best practices?
Impact
85%
1.37xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/etetoolkit/SKILL.mdQuality
Discovery
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.
This is a strong, domain-specific description that excels at listing concrete capabilities and using precise terminology that bioinformatics users would naturally employ. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The technical specificity makes it highly distinctive and unlikely to conflict with other skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about phylogenetic trees, evolutionary analysis, species trees, gene trees, or needs to parse Newick files.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: tree manipulation with format details (Newick/NHX), evolutionary event detection, orthology/paralogy analysis, NCBI taxonomy integration, and visualization with output formats (PDF/SVG). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied by the domain terms listed. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'phylogenetic tree', 'ETE', 'Newick', 'NHX', 'orthology', 'paralogy', 'NCBI taxonomy', 'phylogenomics', 'PDF/SVG'. These are the exact terms bioinformaticians would use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in phylogenetics/evolutionary biology. Terms like 'ETE', 'Newick/NHX', 'orthology/paralogy', and 'phylogenomics' are extremely specific and unlikely to conflict with any other skill. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with complete, executable code examples covering all major ETE capabilities. However, it is far too verbose—it reads as a comprehensive reference manual rather than a concise skill file, with significant redundancy between core capability sections and use cases. The workflow clarity would benefit from validation checkpoints, especially for batch operations and taxonomy database interactions.
Suggestions
Reduce content by 50-60%: move detailed code examples for visualization, clustering, and tree comparison into the referenced files (references/visualization.md, references/workflows.md) and keep only minimal examples in SKILL.md
Remove redundant Use Cases that largely duplicate the core capability sections (e.g., Use Case 1 repeats Section 2's phylogenetic analysis code, Use Case 3 repeats Section 4's visualization code)
Add validation checkpoints to multi-step workflows, especially for batch tree processing (verify tree loaded correctly, check output exists) and NCBI taxonomy operations (verify taxid lookup succeeded before proceeding)
Remove explanatory text Claude already knows (e.g., 'PNG (raster)', 'SVG (vector) for publications', what iterators vs list comprehensions do) and trim best practices to only non-obvious ETE-specific guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It extensively repeats patterns (e.g., ortholog detection code appears in both section 2 and Use Case 1), explains concepts Claude already knows (what PDF/SVG are, what iterators do), and includes redundant use cases that largely restate the core capability sections. Many sections could be cut by 50%+ without losing actionable information. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code and CLI commands throughout. Code examples are complete with imports, concrete file paths, and realistic parameters. Every capability section includes working code patterns. | 3 / 3 |
Workflow Clarity | Multi-step workflows are present (e.g., Use Case 1 has numbered steps 1-6, tree preprocessing has sequential CLI commands), but there are no validation checkpoints or error recovery feedback loops. For operations like batch tree processing or taxonomy annotation that could fail, there's no guidance on verifying intermediate results or handling failures. | 2 / 3 |
Progressive Disclosure | The skill references external files (references/api_reference.md, references/workflows.md, references/visualization.md, scripts/) with clear signaling, but the main SKILL.md contains far too much inline detail that should be in those reference files. The visualization section alone could be its own reference file. The balance between overview and detail is poor—this reads more like a comprehensive manual than a skill overview. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (622 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- 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.