tooluniverse-sequence-analysis

Biological sequence analysis — gene/protein sequence retrieval (NCBI, Ensembl, UniProt), nucleotide/protein search, ortholog discovery, and FASTQ QC + alignment workflows (Trimmomatic, BWA, samtools, coverage depth). Use for sequence retrieval, sequence comparison, FASTQ QC analysis, and read alignment pre-processing.

Quality

85%

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

78%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.

Highly actionable and well-structured with concrete tool calls, recipes, and verified bundled-script references. The main weakness is conciseness: several sections teach biology concepts (wobble pairing, foldamer helix nomenclature) that Claude already knows.

Suggestions

Trim or move the 'Codon-Anticodon Matching Reasoning' and 'Peptide & Foldamer Structure' sections — these explain concepts Claude already knows; keep only the 'use the script to verify' directives.

Add an explicit validate->fix->retry loop to the FASTQ/Trimmomatic and BWA alignment workflows (e.g. run FastQC after Trimmomatic and re-trim if quality is low) to match the validation rigor of RULE ZERO.

Replace the inline wobble-rule prose with a single pointer to `amino_acids.py --type wobble`, since the script already encodes the rules.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tool/param tables and recipes, but it includes concept explanations Claude already knows (the full "Codon-Anticodon Matching Reasoning" section, wobble rules, peptide/foldamer helix chemistry) that pad the context without earning their tokens.	3 / 5
Actionability	Provides concrete executable tool calls with exact parameter formats (e.g. `NCBIGene_search(term="TP53[Symbol] AND Homo sapiens[Organism]")`), runnable script invocations, and copy-paste recipes like the mRNA retrieval and ortholog-comparison sequences.	5 / 5
Workflow Clarity	The six-phase pipeline and numbered recipes sequence the work well, and RULE ZERO adds a pre-computed-results validation checkpoint, but the FASTQ/Trimmomatic and alignment flows lean on prose guidance rather than explicit validate->fix->retry feedback loops.	4 / 5
Progressive Disclosure	The body is a clear overview that points one level deep to four real, verified bundled scripts (amino_acids.py, biology_facts.py, sequence_tools.py, translate_dna.py) with explicit paths and mode tables, and no nested references.	5 / 5
	Total	17 / 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, specific description that names concrete tools and databases and provides an explicit 'Use for' trigger clause. The only minor gap is slightly less than comprehensive keyword coverage (missing common file extensions).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and tools across the domain — "gene/protein sequence retrieval (NCBI, Ensembl, UniProt)", "ortholog discovery", and "FASTQ QC + alignment workflows (Trimmomatic, BWA, samtools, coverage depth)" — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (the detailed capability list) and 'when' via the concrete "Use for sequence retrieval, sequence comparison, FASTQ QC analysis, and read alignment pre-processing" trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases users say ("sequence retrieval", "sequence comparison", "FASTQ QC analysis", "read alignment pre-processing"), but omits file extensions like .fastq/.fasta and some synonyms, so it is not quite comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (bioinformatics sequence analysis with named DBs and tools) with distinct triggers, making overlap with unrelated 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: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-sequence-analysis/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.