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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/deeptools/SKILL.md
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 highly actionable, well-structured skill body with strong workflows, validation checkpoints, and a genuinely well-wired one-level-deep bundle. The main cost is token efficiency: redundant restatements of the same rules and tables duplicated from the references inflate the body without adding capability.

Suggestions

State each domain rule once: consolidate the extend-reads (ChIP YES / RNA NO) guidance, currently repeated in the RNA-seq workflow, Common Parameters, Best Practices, and Key Reminders sections, into a single authoritative spot.

Trim the inline effective-genome-size table and normalization quick guide to a few exemplar rows and defer to references/effective_genome_sizes.md and references/normalization_methods.md, which already contain the full content.

Cut or compress the 'Handling User Requests' and 'Example Interactions' sections, which narrate conversational strategy Claude can derive, down to a short decision table of task → tool/workflow mapping.

DimensionReasoningScore

Conciseness

Mostly efficient — the body is dominated by concrete commands and domain-specific guidance — but it carries clear redundancy: the extend-reads rule (YES for ChIP-seq, NO for RNA-seq) is stated four times, the effective-genome-size table and normalization quick guide duplicate full reference files, and the padded 'Handling User Requests'/'Example Interactions' sections narrate response style rather than instruct. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened'; it is not severe enough for score 2 since nearly all content is skill-specific rather than concepts Claude already knows.

3 / 5

Actionability

The body provides fully executable, copy-paste-ready commands for the common cases (bamCoverage, bamCompare, multiBamSummary/plotCorrelation, computeMatrix → plotHeatmap/plotProfile, samtools index) plus runnable helper scripts with exact invocations and flags, matching the top anchor.

5 / 5

Workflow Clarity

Workflows follow an explicit QC → Normalization → Comparison/Visualization pattern with numbered steps, an upfront validation checkpoint (scripts/validate_files.py before any analysis), test-on-region guidance, interpretation criteria (e.g., correlation >0.9, fingerprint shape), and a troubleshooting section with concrete error-recovery loops (missing index → samtools index; OOM → per-chromosome --region).

5 / 5

Progressive Disclosure

Excellent structure: every referenced bundle file (references/tools_reference.md, workflows.md, normalization_methods.md, effective_genome_sizes.md, both scripts, assets/quick_reference.md) exists, is one level deep, is signaled with 'Use this reference when' guidance, and cited section headings match the real files — plus grep navigation snippets. It falls short of the top anchor only because content that belongs solely in the references (the full genome-size table, the normalization selection guide) is duplicated inline in the body.

4 / 5

Total

17

/

20

Passed

Description

70%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 dense, specific description with strong domain trigger terms and low conflict risk. Its main weakness is the absent explicit 'Use when...' trigger clause, which both caps completeness and slightly weakens the actionable-when signal for skill routing.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with BAM/bigWig files, or when the user mentions ChIP-seq, RNA-seq, ATAC-seq, coverage tracks, or sequencing QC." to resolve the completeness gap.

Include a few missing natural synonyms users actually say — "coverage", "quality control", "fragment size" — to lift trigger term coverage toward comprehensive.

Mention enrichment analysis at peak regions to close the coverage gap against the skill's full capability set.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "BAM to bigWig conversion", "QC (correlation, PCA, fingerprints)", "heatmaps/profiles (TSS, peaks)" — but omits a few capabilities the skill covers (e.g., enrichment analysis at peaks, GC-bias correction), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor at 5.

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance — only a weak implicit cue in "for ChIP-seq, RNA-seq, ATAC-seq visualization". Per the judging guideline, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Strong natural keywords a genomics user would say: "BAM", "bigWig", "ChIP-seq", "RNA-seq", "ATAC-seq", "QC", "heatmap", "PCA", "TSS", "peaks". A few common terms are missing (e.g., "coverage", "quality control" spelled out, "fragment size"), placing it just below the comprehensive synonym/extension coverage anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous: NGS/QC/coverage-track/heatmap terms with named formats (BAM, bigWig) and assays (ChIP-seq, RNA-seq, ATAC-seq) are distinct triggers unlikely to fire for the wrong skill, matching the clear-niche anchor. It is not generic enough to fit the 'minor overlap' anchor below.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (531 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository

googolme/run0204

Path

scientific-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.