busco-phylogeny
Generate phylogenies from genome assemblies using BUSCO/compleasm-based single-copy orthologs with scheduler-aware workflow generation
65
57%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./phylo_from_buscos/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is technically precise and occupies a very clear niche in computational phylogenomics, making it highly distinctive. Its main weakness is the absence of an explicit 'Use when...' clause and missing common user-facing trigger term variations (e.g., 'phylogenetic tree', 'species tree', 'SLURM'). Adding these would significantly improve Claude's ability to select this skill at the right time.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to build phylogenetic trees from genome assemblies, run BUSCO analyses, or create phylogenomic pipelines.'
Include common user-facing trigger term variations such as 'phylogenetic tree', 'species tree', 'comparative genomics', 'evolutionary relationships', 'SLURM', 'HPC', and 'job scheduler'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Generate phylogenies from genome assemblies using BUSCO/compleasm-based single-copy orthologs' and 'scheduler-aware workflow generation'. These are precise, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (generate phylogenies from genome assemblies using specific tools and workflow generation), 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 strong domain-specific keywords like 'phylogenies', 'genome assemblies', 'BUSCO', 'compleasm', 'single-copy orthologs', and 'scheduler-aware workflow'. However, it misses common user variations like 'phylogenetic tree', 'species tree', 'comparative genomics', 'HPC', 'SLURM', or 'evolutionary analysis'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining phylogenomics, BUSCO/compleasm orthologs, and scheduler-aware workflows. Very unlikely to conflict with other skills due to the specificity of the bioinformatics domain and toolchain. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
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 sequencing, validation checkpoints, and comprehensive coverage of a complex bioinformatics pipeline. However, it is severely over-verbose for a SKILL.md file—much of the content (NCBI assembly quality explanations, model recommendation details, validation reporting templates) belongs in the referenced files rather than the main skill body. The heavy reliance on 'see REFERENCE.md' for actual implementation details reduces direct actionability.
Suggestions
Move Step 0A (NCBI query), substitution model recommendation details, and script validation reporting templates to separate reference files, keeping only brief summaries with links in SKILL.md
Remove explanations of concepts Claude already knows (what N50 is, what RefSeq vs GenBank means, what assembly levels are) and replace with concise decision rules
Eliminate the 'Important Notes' section which largely duplicates content from earlier sections, or consolidate into a brief checklist
Inline the most critical executable commands directly rather than deferring to templates/REFERENCE.md for every step—provide the core command with template references only for scheduler-specific wrappers
| 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 reminders ('ALWAYS', 'IMPORTANT'), and repeated information across sections. The 'Important Notes' section largely restates content already covered. Much content could be in reference files rather than the main skill. | 1 / 3 |
Actionability | Provides some concrete commands (compleasm, MAFFT, IQ-TREE, ASTRAL) and script invocations, but heavily relies on external templates and references for actual implementation. Many steps say 'see references/REFERENCE.md for detailed implementation' rather than providing executable guidance directly. The template system adds indirection. | 2 / 3 |
Workflow Clarity | Excellent workflow sequencing with clear step numbering (0 through 9), explicit input/output mappings between steps, a dedicated 'Script Validation' section with pipeline continuity verification, resource compatibility checks, and a structured error reporting format with feedback loops. The validation workflow is thorough with explicit checkpoints. | 3 / 3 |
Progressive Disclosure | Good use of external references (REFERENCE.md, templates/, scripts/) with clear signaling, but the main SKILL.md itself is a monolithic wall of text that includes too much inline content. Step 0A alone is enormous and could be a separate file. The quality filtering criteria, assembly selection tips, and substitution model details should be in reference files rather than inline. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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
f569911
- 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.