busco-phylogeny

Generate phylogenies from genome assemblies using BUSCO/compleasm-based single-copy orthologs with scheduler-aware workflow generation

Quality

65%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./phylo_from_buscos/SKILL.md

Quality

Content

47%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill demonstrates excellent workflow design with clear step sequencing, validation checkpoints, and comprehensive pipeline coverage for a complex bioinformatics task. However, it severely suffers from verbosity — explaining concepts Claude already knows (assembly quality metrics, RefSeq vs GenBank), repeating cross-references redundantly, and including detailed sub-procedures inline that should be in reference files. The actionability is moderate since many critical steps defer to templates and reference documents without providing complete inline examples.

Suggestions

Reduce the SKILL.md to ~200 lines by moving STEP 0A (NCBI query details, assembly quality explanations), the substitution model recommendation system, and the detailed validation procedures into separate reference files, keeping only brief summaries with links in the main file.

Remove explanations of concepts Claude already knows: what N50 means, what RefSeq vs GenBank is, what assembly levels are, what PDF/libraries are — these waste significant token budget.

Eliminate the 'Important Notes' section which largely duplicates instructions already given in the workflow steps, or consolidate into a brief 3-4 line checklist.

For steps that defer to templates/REFERENCE.md, include at least one complete executable example inline so the skill is actionable without reading external files.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~600+ lines. Contains extensive explanations Claude doesn't need (what assembly levels mean, what N50 is, what RefSeq vs GenBank is), redundant cross-references repeated multiple times, and numerous sections that restate the same information. The 'Important Notes' section largely duplicates earlier content. Many instructions like 'Be encouraging' and explaining basic bioinformatics concepts waste tokens.	1 / 3
Actionability	Provides some concrete commands (compleasm, MAFFT, IQ-TREE, ASTRAL) and executable code snippets, but many steps defer to templates and references/REFERENCE.md for actual implementation details. Key steps like alignment and trimming lack complete executable examples inline, instead saying 'see references/REFERENCE.md for detailed implementation.' The template system adds indirection that reduces immediate actionability.	2 / 3
Workflow Clarity	The workflow is clearly sequenced from Step 0 through Step 9 with explicit input/output mappings between steps. The Script Validation section provides a thorough feedback loop with pipeline continuity verification, resource compatibility checks, and structured error reporting. The validation workflow explicitly maps outputs to inputs across all steps and includes clear error recovery procedures.	3 / 3
Progressive Disclosure	The skill references external files well (templates/, references/REFERENCE.md, scripts/) and has a clear structure, but the SKILL.md itself contains far too much inline content that should be in reference files — the entire STEP 0A section with assembly quality considerations (~100 lines), the substitution model recommendation system, and the detailed validation procedures could all be in separate reference documents. The main file tries to be both overview and detailed guide simultaneously.	2 / 3
	Total	8 / 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.

This is a highly specific and technically precise description that clearly identifies its niche in phylogenomics pipeline generation. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology is appropriate for the target audience and provides excellent distinctiveness.

Suggestions

Add a 'Use when...' clause such as 'Use when the user asks to build phylogenetic trees, run phylogenomics pipelines, extract orthologs from genomes, or generate BUSCO-based phylogenies on HPC/cluster environments.'

Dimension	Reasoning	Score
Specificity	Lists specific concrete actions: generate phylogenies, use genome assemblies as input, employ BUSCO/compleasm-based single-copy orthologs, and generate scheduler-aware workflows. Multiple distinct technical capabilities are named.	3 / 3
Completeness	Clearly answers 'what does this do' (generate phylogenies from genome assemblies using BUSCO/compleasm orthologs with scheduler-aware workflows), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes highly relevant natural keywords a bioinformatics user would say: 'phylogenies', 'genome assemblies', 'BUSCO', 'compleasm', 'single-copy orthologs', 'scheduler', 'workflow'. These are the exact terms domain users would use.	3 / 3
Distinctiveness Conflict Risk	Extremely niche and specific to phylogenomics workflows using BUSCO/compleasm. The combination of phylogenies, genome assemblies, single-copy orthologs, and scheduler-aware workflow generation creates a very distinct fingerprint unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (820 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: brunoasm/my_claude_skills
Commit: d69f3ce

Reviewed: about 1 month 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.