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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 concrete commands and parameters, and it uses progressive disclosure effectively to push detailed workflows and references to one-level-deep files. Its main weakness is conciseness: several sections (reference meta-descriptions, inline duplicated tables, example interactions, key reminders) pad the skill and could be tightened.

Suggestions

Trim the 'Reference Documentation' section — the per-file 'Use this reference when' lines already provide navigation; the bulleted contents lists are redundant with the files themselves.

Remove the duplicated inline Effective Genome Sizes table (or reduce it to 2-3 representative rows) since the full table lives in references/effective_genome_sizes.md.

Cut the 'Example Interactions' 'Response approach' lists and 'Key Reminders' section, which restate guidance already covered in Best Practices.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational content, but several padded sections — the verbose 'Reference Documentation' meta-descriptions, duplicated inline genome-size table, 'Example Interactions' meta-guidance, and 'Key Reminders' repetition — could be trimmed.	3 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (validate_files.py, workflow_generator.py with real flags, install, samtools index, bamCoverage) plus concrete parameter values and a genome-size table covering the common operational cases.	5 / 5
Workflow Clarity	Clear sequencing with a validate-first mandate, test-on-small-regions and QC-first checkpoints, and troubleshooting feedback loops, but validation is a pre-step rather than interleaved checkpoints within the analysis pipeline (full pipeline validation lives in references).	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references — each of the five reference files, two scripts, and one asset is linked with a 'Use this reference when' trigger — and detailed content appropriately split out.	5 / 5
	Total	17 / 20 Passed

Description

71%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 and action-dense, naming concrete capabilities and rich domain trigger terms for ChIP-seq/RNA-seq/ATAC-seq. Its main weakness is the absence of an explicit 'Use when...' clause (capping completeness) and a somewhat broad leading phrase that creates minor conflict risk with adjacent NGS skills.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when converting BAM to bigWig, running ChIP-seq/RNA-seq/ATAC-seq QC, or generating heatmaps/profiles around genomic features') to raise completeness above 3.

Include explicit file-extension trigger terms ('.bam', '.bw', '.bed') and plural variants to push trigger-term coverage from good to comprehensive.

Tighten the generic 'NGS analysis toolkit' lead toward the specific deepTools capabilities to reduce overlap risk with broader bioinformatics skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks)' — with comprehensive coverage of the toolkit's main function areas.	5 / 5
Completeness	Clear 'what' (NGS toolkit with named capabilities) but no explicit 'Use when...' clause; the 'when' is only weakly implied via the listed assay types, capping completeness at 3 per the missing-trigger guideline.	3 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms ('BAM to bigWig', 'QC', 'heatmaps', 'ChIP-seq', 'RNA-seq', 'ATAC-seq') and file-type names, but missing explicit extension-dot synonyms ('.bam', '.bw') and plural variants.	4 / 5
Distinctiveness Conflict Risk	Mostly distinct niche anchored by deepTools-specific terms (bigWig, fingerprints, TSS profiles), but the broad 'NGS analysis toolkit' lead creates minor overlap risk with other bioinformatics/NGS skills.	4 / 5
	Total	16 / 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: b2a92ba

Reviewed: 3 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.