phylogenetics

Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein families, and cautiously interpreted dated phylogenies.

Quality

94%

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

92%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-engineered skill body: fully executable commands, a validated five-step workflow with explicit error-handling, and a clean one-level-deep split between core workflow and the IQ-TREE reference. The only trimmable material is the dated review-provenance commentary scattered through the body.

Suggestions

Consolidate the per-section provenance caveats ("trimAl was not installed for this review", "Qt rendering was not exercised in this review", "Version 2 compatibility is source-checked, not runtime-tested") into the existing "Versions and installation" section to reduce token cost without losing the verification distinctions.

Move the dated version matrix ("MAFFT **7.526**, IQ-TREE **3.1.4**") into a clearly labeled versions subsection or the reference file so stale time-sensitive details don't sit inline in the workflow path.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence with no basic-concept padding, but carries time-sensitive provenance statements ("Reviewed against current official documentation on 2026-10-01", "MAFFT 7.526, IQ-TREE 3.1.4", "trimAl was not installed for this review", "Qt rendering was not exercised in this review") that are not consolidated in a deprecated/old-patterns section and could be trimmed or relocated.	4 / 5
Actionability	Fully executable throughout: complete MAFFT and trimAl commands with flags, three copy-paste helper invocations covering nucleotide, protein, pre-aligned, and FastTree cases, and a runnable Python snippet for load_tree/tree_summary.	5 / 5
Workflow Clarity	Five clearly sequenced steps (input, align, infer, interpret, visualize) with explicit validation checkpoints and feedback loops: "A failed trim must stop the trimming step; do not silently copy the untrimmed input", "verify their order in the report", "verify executable versions after installation", and "--redo explicitly restarts and replaces results".	5 / 5
Progressive Disclosure	The body is an actionable overview with advanced topics (partitioning, concordance factors, ancestral states, dating) deferred via one clearly signaled, one-level-deep link to references/iqtree_inference.md, and the bundled script invoked with concrete commands; both referenced bundle files exist and no references are nested or buried.	5 / 5
	Total	19 / 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 description: concrete tool-anchored actions, an explicit "Applies to..." trigger clause, and a distinct phylogenetics niche in third-person voice. The only gap is a few natural synonyms (phylogeny, evolutionary tree, MSA) that would widen trigger coverage.

Dimension	Reasoning	Score
Specificity	"Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization." lists multiple concrete actions (alignment, ML inference, approximate inference, branch support, summaries, visualization) each tied to a named tool, giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	The "what" is explicit ("Builds and analyzes phylogenetic trees using MAFFT...") and the "when" is given as an explicit trigger clause with concrete conditions ("Applies to homologous nucleotide or protein sequences, microbial gene trees, protein families, and cautiously interpreted dated phylogenies"), in third-person voice.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ("phylogenetic trees", "multiple sequence alignment", "gene trees", "protein families", "nucleotide or protein sequences"), but common synonyms such as "phylogeny", "evolutionary tree", or "MSA" are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche anchored by named tools (MAFFT, IQ-TREE, FastTree, ETE3) and domain-specific triggers (gene trees, branch support, dated phylogenies), making conflict with other skills minimal.	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/phylogenetics/SKILL.md
Commit: 1549884

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.