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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/deeptools/SKILL.md

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.

The body is highly actionable with clean progressive disclosure to real reference, script, and asset files, and workflows carry explicit validation checkpoints. Its main weakness is verbosity from meta-guidance sections that restate best practices already covered elsewhere.

Suggestions

Trim or merge 'Example Interactions' and 'Handling User Requests' into the relevant workflow/reference sections to reduce token overhead.

Move the full effective-genome-size table and normalization-method list fully into their reference files, keeping only the quick-selection guide inline.

Promote one explicit validate→fix→retry loop inline (e.g. in Quick Start) to close the workflow-clarity gap toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and avoids explaining basic NGS concepts, but the 'Handling User Requests', 'Example Interactions', and 'Key Reminders' sections restate guidance already covered and inline tables (genome sizes, normalization) partly duplicate the reference files, so it could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout — 'python scripts/validate_files.py --bam ...', 'python scripts/workflow_generator.py chipseq_qc -o ...', 'uv pip install deepTools==3.5.6', 'bamCoverage --bam input.bam -o chr1.bw --region chr1' — covering the common cases.	5 / 5
Workflow Clarity	Clear sequences with explicit validation checkpoints ('Always validate files first', 'Start with QC', 'Test on small regions') and a troubleshooting feedback section; the full validate→fix→retry loops live in the reference workflows rather than inline, leaving a minor gap versus the 5 anchor.	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references — a '## Reference Documentation' section describes each of the 5 reference files, 2 scripts, and 1 asset with 'Use this reference when' guidance, and all cited paths resolve to real bundle files.	5 / 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.

The description is specific, distinct, and rich in natural trigger terms, but it omits an explicit 'Use when...' trigger clause, capping its completeness. Adding a concrete usage-trigger sentence would lift the completeness dimension.

Suggestions

Add an explicit 'Use when ...' clause naming user intents (e.g. 'Use when converting BAM to bigWig, running ChIP/RNA/ATAC-seq QC, or generating heatmaps and profiles around genomic features').

Include common file extensions (.bam, .bw/.bigWig, .bed) alongside the assay names to broaden trigger-term coverage.

Lead with the domain framing ('Use deepTools to ...') so the 'when' is as explicit as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'BAM to bigWig conversion', 'QC (correlation, PCA, fingerprints)', 'heatmaps/profiles (TSS, peaks)' — with comprehensive coverage of the toolkit's capabilities, matching the 5 anchor.	5 / 5
Completeness	Has a clear 'what' but the 'when' is only weakly implied via 'for ChIP-seq, RNA-seq, ATAC-seq visualization'; there is no explicit 'Use when...' clause, which per guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural keyword coverage ('ChIP-seq, RNA-seq, ATAC-seq', 'QC', 'PCA', 'heatmaps', 'TSS', 'peaks') that users would actually say, but no file extensions (e.g. .bam, .bw) to reach the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	A clear NGS niche with distinct deepTools-specific triggers (fingerprints, BAM-to-bigWig, TSS/peak heatmaps) and minimal overlap risk with unrelated skills.	5 / 5
	Total	17 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/deeptools/SKILL.md
Commit: 49c6e97

Reviewed: 9 days 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.