CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tooluniverse-sequence-analysis in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 highly actionable, well-structured skill body with concrete tool calls and recipes, held back by repeated guidance and missing validation feedback loops in its batch workflows. Progressive disclosure is good but the tool reference could live in its own file.

Suggestions

Consolidate the Trimmomatic 'discarded reads' guidance into a single authoritative block (keep the counter table once) to remove the triple repetition and tighten token use.

Add explicit validation checkpoints to the FASTQ/alignment workflow (e.g., verify sample count matches input pairs before summing, sanity-check that total discarded ≤ total input) so the batch operation qualifies for a higher workflow_clarity score.

Move the per-tool parameter reference (Phases 1-6 + quick-reference table) into a references/TOOLS.md file and keep SKILL.md as an overview pointing to it, improving progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and mostly earns its tokens — tool params, return shapes, gotchas, and recipes rather than explanations of concepts Claude already knows — but the Trimmomatic 'discarded reads' rule is restated three times (top-of-mind rule, the FASTQ counter table, and the trailing 'DO NOT report just D' line) and wobble rules appear both inline and via the script, so it is not fully lean.

4 / 5

Actionability

Fully executable: exact tool names with required params, return-value shapes, numbered recipes with example calls, and complete CLI invocations for every bundled script — copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

The Phase 1→6 sequence and RULE ZERO pre-check give a clear overall order, but the batch/sample-level operations (Trimmomatic counting, alignment/coverage) lack explicit validate→fix→retry checkpoints; per the batch-operation cap, a destructive/batch workflow without validation cannot exceed 3 even though steps are listed.

3 / 5

Progressive Disclosure

Bundled scripts are clearly signaled with full one-level-deep paths and usage, and sections are well-headed; however the large per-tool parameter reference (Phases 1-6) and the tool-quick-reference table are inlined rather than split into a separate reference file (no references/ directory exists), a minor organization gap.

4 / 5

Total

16

/

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 capabilities, tools, and explicit trigger phrases for both what and when. The only gap is modest synonym/extension coverage in the trigger terms.

Suggestions

Add common file extensions and synonyms to the trigger clause (e.g., '.fastq/.fq QC', '.bam alignment', 'FASTA retrieval') so the description fires on a wider range of natural user phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'sequence retrieval', 'nucleotide/protein search', 'ortholog discovery', 'FASTQ QC + alignment workflows' — alongside named tools (NCBI, Ensembl, UniProt, Trimmomatic, BWA, samtools), giving comprehensive coverage; not merely the 1-2 actions of a score-3 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (retrieval, search, ortholog discovery, FASTQ QC, alignment) and 'when' via the concrete 'Use for sequence retrieval, sequence comparison, FASTQ QC analysis, and read alignment pre-processing.' clause.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('sequence retrieval', 'sequence comparison', 'FASTQ QC analysis', 'read alignment pre-processing') and the major database names, but misses common synonyms/extensions like .fastq, .bam, .fasta; good but not the full synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear specialized niche (biological sequence analysis with specific bioinformatics databases/tools) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
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.