CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deeptools

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

Quality

82%

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

81%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 well-structured, highly actionable skill body with genuine expert content (version-migration caveats, normalization selection, validation-first workflows) and clean one-level-deep references that all exist. Its main weakness is verbosity in the second half — response-style sections and reminder lists that restate earlier guidance and inflate the SKILL.md beyond overview size.

Suggestions

Cut or collapse 'Handling User Requests', 'Example Interactions', and 'Key Reminders' — they restate Best Practices or instruct Claude on behavior it can infer.

Replace the per-file 'Reference Documentation' section with the inline 'Use this reference when' pointers already present, removing the duplicated navigation.

De-duplicate the normalization quick-selection guide (currently listed twice within the same section) and keep only the inline genome-size table or the reference-file table.

DimensionReasoningScore

Conciseness

The bulk of the body is dense, non-obvious domain guidance (4.0 migration flags, normalization selection, effective genome sizes, SAM-flag filtering) that earns its tokens. However, sections like 'Handling User Requests', 'Example Interactions', and 'Key Reminders' largely restate Best Practices or instruct Claude on response styles it can infer, and 'Reference Documentation' re-describes files already pointed to inline — noticeable padding that could be trimmed.

3 / 5

Actionability

Guidance is fully executable throughout: copy-paste bash for installation, validate_files.py and workflow_generator.py invocations with real flags, troubleshooting commands (samtools index, --region chr1), and exact --effectiveGenomeSize values. Concrete examples cover the common cases (ChIP-seq QC, BAM conversion, heatmap creation, sample comparison).

5 / 5

Workflow Clarity

Sequences are explicit and validation-first: Quick Start mandates validate_files.py before any analysis, workflow generation includes a 'Review the generated script before running' checkpoint, and the Validation Errors + Troubleshooting sections provide feedback loops for error recovery. Validation is present for the batch operations, so no cap applies.

5 / 5

Progressive Disclosure

All referenced bundle paths (references/core_workflows.md, workflows.md, tools_reference.md, normalization_methods.md, effective_genome_sizes.md, review.md; assets/quick_reference.md; both scripts) exist and are signaled one level deep with 'Use this reference when' guidance — strong navigation. The score stops short of 5 because the body itself runs ~420 lines with some content duplicated between inline summaries and references (e.g., the genome-size table, normalization quick guide listed twice), and the 'Reference Documentation' section repeats pointers already made in context.

4 / 5

Total

17

/

20

Passed

Description

75%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 highly specific, well-targeted description with excellent domain keywords and near-zero conflict risk. Its only real weakness is the absence of an explicit 'Use when...' trigger clause, which both caps completeness and slightly limits its discovery phrasing.

Suggestions

Append an explicit trigger clause, e.g.: 'Use when working with BAM/bigWig/BED files in genomics, or when the user mentions ChIP-seq, RNA-seq, ATAC-seq coverage, QC, or heatmaps.'

Add one or two missing natural terms users say, such as 'coverage tracks', 'normalize', or file extensions like '.bam'/'.bw'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks)' — covering the toolkit's main capability areas comprehensively. No anchor above exists and no adjacent anchor fits better than the 'multiple specific concrete actions; comprehensive coverage' example.

5 / 5

Completeness

The 'what' is clearly and concretely answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'for ChIP-seq, RNA-seq, ATAC-seq visualization' only weakly implies when to invoke the skill. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Strong natural terms: 'BAM', 'bigWig', 'QC', 'correlation', 'PCA', 'fingerprints', 'heatmap', 'TSS', 'peaks', 'ChIP-seq', 'RNA-seq', 'ATAC-seq' — phrases a genomics user would naturally say. A few natural terms are missing (e.g., 'coverage', 'normalize', 'MNase-seq', '.bam'), so it falls just short of the comprehensive-with-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (NGS/deepTools bioinformatics) with distinct domain triggers (BAM, bigWig, ChIP-seq, TSS, fingerprints) that virtually no other skill would claim. Minimal conflict risk with any general-purpose skill.

5 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

K-Dense-AI/scientific-agent-skills

Path

skills/deeptools/SKILL.md

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.