CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-microbial-genome-characterization

Genome-ASSEMBLY discovery, QC, and replicon mapping for any organism (bacteria, archaea, fungi, and beyond) using NCBI Datasets. Resolves an organism name or taxid to assemblies, picks the reference/representative or best-quality assembly, pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%, assembly level, RefSeq category), enumerates chromosomes and plasmids via per-replicon sequence reports, and compares candidate assemblies on quality. Use for "what genomes are available for [organism]", "assembly stats / N50 / GC content for [GCF_/GCA_ accession]", "how many plasmids does [strain] have", "compare assemblies for [species]", "find the reference genome for [taxon]", "is this assembly Complete Genome or just contigs". NOT for gene-level orthology/synteny (use tooluniverse-comparative-genomics), plant gene structure (use tooluniverse-plant-genomics), de novo assembly from raw reads (no tool exists), or taxonomy-only name/lineage lookups.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable and workflow-clarity is excellent — concrete tool calls, a phased process, and validation checkpoints — but it is a monolithic document with no bundle references and some redundancy between worked examples and the workflow. Progressive disclosure and conciseness are the weakest areas.

Suggestions

Split the Interpretation Table and the three Worked Examples into a separate references file (e.g., references/interpretation.md) and link to it one level deep, so the main body stays a lean overview — improving progressive_disclosure toward the level-3 anchor.

Remove the duplication between the description's "NOT for" clause and the body's "NOT this skill" section so the disambiguation lives in one place; tighten the worked examples to only the tool calls and answers that aren't already in the Workflow phases.

Trim redundant prose such as the re-stated assembly-level definitions that already appear in the Interpretation Table, so nearly every remaining token earns its place (conciseness level-3).

DimensionReasoningScore

Conciseness

The dense domain reference (assembly-level meanings, N50 interpretation, GCF_/GCA_ distinction) earns its place, but the three worked examples restate the workflow commands and the "NOT for/NOT this skill" disambiguation is duplicated between the description and body; the body could be tightened. It sits between the level-2 and level-3 anchors — useful but with some redundancy, not perfectly lean.

2 / 3

Actionability

Tool calls are copy-paste ready with exact params and sample payloads (e.g., `NCBIDatasets_suggest_taxonomy {"query": "Escherichia coli"}`), a complete tools table mapping key params to return fields, and concrete pandas sort logic (assembly_level rank, contig_n50 desc, number_of_contigs asc), matching the level-3 anchor.

3 / 3

Workflow Clarity

A clear six-phase sequence (Phase 0–5) with explicit selection priority and validation checkpoints, reinforced by "LOOK UP, DON'T GUESS" / "COMPUTE, DON'T DESCRIBE" feedback loops and a final Completeness Checklist (no guessed taxids, justified accession, use get_sequence_reports for plasmids).

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and the body is a single ~170-line monolith with no one-level-deep pointers to separate files; the worked examples and interpretation table are inline rather than split out, fitting the level-2 anchor of "content that should be separate is inline" rather than the simple-skill carve-out (this is well over 50 lines).

2 / 3

Total

10

/

12

Passed

Description

100%

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 exemplary: third person, concrete capability list, explicit "Use for" triggers with natural phrasings, and a "NOT for" disambiguation that routes overlapping requests elsewhere. It cleanly satisfies every dimension at the top of the scale.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "discovers... assemblies", "pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%...)", "enumerates chromosomes and plasmids via per-replicon sequence reports", "compares candidate assemblies on quality" — matching the level-3 anchor.

3 / 3

Completeness

Explicitly answers both what ("Resolves an organism name or taxid to assemblies..." with enumerated capabilities) and when (an explicit "Use for..." trigger list), plus a "NOT for..." clause, satisfying the level-3 anchor.

3 / 3

Trigger Term Quality

Embeds natural phrases users would actually say — "what genomes are available for [organism]", "assembly stats / N50 / GC content for [GCF_/GCA_ accession]", "how many plasmids does [strain] have" — giving broad coverage of likely user phrasings.

3 / 3

Distinctiveness Conflict Risk

Clear niche (genome assembly characterization) with distinct triggers and explicit routing to sibling skills ("NOT for gene-level orthology/synteny (use tooluniverse-comparative-genomics), plant gene structure (use tooluniverse-plant-genomics)"), making wrong-skill conflicts unlikely.

3 / 3

Total

12

/

12

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.