etetoolkit

Analyze, manipulate, compare, annotate, and visualize phylogenetic or other hierarchical trees with ETE 4. Use for Newick/Nexus tree I/O, topology edits and pattern matching, Robinson-Foulds comparisons, gene-tree evolutionary events and reconciliation, NCBI/GTDB taxonomy, SmartView exploration, and publication rendering. Do not use it to infer trees from raw sequences; align sequences and infer a tree first.

Quality

89%

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

Quality

Content

86%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.

A well-structured, highly actionable skill body that keeps common workflows inline and pushes deep API, taxonomy, visualization, and migration detail into verified one-level references. It loses points only on minor verbosity and the absence of an explicit error-retry feedback loop.

Suggestions

Move the time-sensitive version/dates out of the main flow into a 'Pinned version' note or keep only the pin, since dated stamps (Sept 2025, July 2026) penalize conciseness without being in a deprecated/old-patterns section.

Tighten the seven-item 'Quality and Interpretation Checks' list to the four highest-value checks, or fold the rest into references/workflows.md, to reduce token cost.

Add an explicit validate→fix→retry loop for at least one fragile workflow (e.g., after `prune` or taxonomy `get_topology`, re-check leaf uniqueness and re-run on failure) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy and lean on prose, with ETE-4-specific gotchas rather than generic explanations Claude already knows; minor over-explanation remains in the dated 'Current Target' stamps (Sept 3 2025, July 23 2026) and the seven-item Quality checklist that could be trimmed.	4 / 5
Actionability	Fully executable copy-paste-ready Python examples for every common case (inspect, transform, compare, detect events, taxonomy, visualize) plus exact `uv run --with 'ete4==4.4.0'` bundled-script invocations with concrete flags, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Sequenced workflows with explicit validation checkpoints (missing-name `raise ValueError`, parser-mismatch guidance, the prune script refusing ambiguous names) and a pre-report checklist, but lacking the explicit validate→fix→re-validate feedback loop shown in the 5-anchor example.	4 / 5
Progressive Disclosure	Clear overview sections (Scope, Quick Start, Core Workflows, Bundled Scripts, Reference Map) with one-level-deep, well-signaled references — all five referenced files and two scripts verified to exist — and a Reference Map giving a one-line purpose for each, matching the clear-navigation anchor.	5 / 5
	Total	18 / 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 precise, third-person description that clearly states capabilities, trigger conditions, and an explicit out-of-scope boundary. Its only gap is the absence of file-extension triggers, which keeps trigger-term quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Analyze, manipulate, compare, annotate, and visualize') plus a comprehensive enumerated capability set (Newick/Nexus I/O, topology edits, Robinson-Foulds, gene-tree reconciliation, NCBI/GTDB taxonomy, SmartView, publication rendering), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers 'what' (the action verbs and capability list) and 'when' ('Use for Newick/Nexus tree I/O, topology edits...') with concrete trigger phrases, and adds a do-not-use boundary ('Do not use it to infer trees from raw sequences'), matching the 5-anchor example structure.	5 / 5
Trigger Term Quality	Strong natural-term coverage with synonyms (Newick/Nexus, NCBI/GTDB, Robinson-Foulds, SmartView), but no file extensions (.nwk/.nex/.tre) appear, leaving a few natural terms missing per the 5-anchor's 'including synonyms and file extensions' requirement.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (phylogenetic/hierarchical trees with ETE 4) with highly specific triggers (Newick/Nexus, Robinson-Foulds, NCBI/GTDB, SmartView) and an explicit negative boundary, giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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/etetoolkit/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.