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

83%

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

Quality

Content

85%

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 clear, validated workflows and excellent progressive disclosure into real reference files. Its chief weakness is verbosity: several conversational and recapitulative sections could be removed without losing useful guidance.

Suggestions

Cut the 'Example Interactions', 'Handling User Requests', and 'Key Reminders' sections, which restate guidance already present in the workflow and best-practices sections.

Trim 'When to Use This Skill' since the trigger phrases duplicate the frontmatter description; keep only the file-type triggers not already covered.

Consolidate the 'Reference Documentation' section so each reference is described once rather than re-mentioned in multiple tool-category sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable and efficient, but sections like 'When to Use This Skill', 'Handling User Requests', 'Example Interactions', and 'Key Reminders' add conversational recap and meta-guidance that could be trimmed; it is not at the lean top anchor.	2 / 3
Actionability	Concrete, executable, copy-paste-ready commands with real parameters appear throughout (bamCoverage, bamCompare, computeMatrix, plotHeatmap, validate_files.py), matching the fully-executable top anchor.	3 / 3
Workflow Clarity	Workflows are clearly sequenced (QC → normalization → visualization) with an explicit 'Always validate files first' checkpoint, a validation script, and a troubleshooting section providing error-recovery guidance.	3 / 3
Progressive Disclosure	The SKILL.md is an overview pointing one level deep to real, well-signaled references (tools_reference.md, workflows.md, normalization_methods.md, effective_genome_sizes.md) and a quick_reference asset, each with a clear 'Use this reference when' cue.	3 / 3
	Total	11 / 12 Passed

Description

82%

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, well-targeted, and distinct, listing concrete deepTools capabilities and natural user trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when processing or visualizing ChIP-seq, RNA-seq, or ATAC-seq data, or when the user mentions BAM/bigWig coverage, QC, or heatmaps.'

The 'for ChIP-seq, RNA-seq, ATAC-seq visualization' phrase conflates domain with trigger; separate the 'when' guidance more clearly from the capability list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'BAM to bigWig conversion', 'QC (correlation, PCA, fingerprints)', 'heatmaps/profiles (TSS, peaks)' — rather than vague language, matching the top anchor.	3 / 3
Completeness	Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' trigger clause; the 'for ChIP-seq...' phrase only implies when, so completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	Natural terms a user would say are well covered — 'BAM to bigWig', 'QC', 'ChIP-seq, RNA-seq, ATAC-seq', 'heatmaps', 'TSS', 'peaks' — across experiment types.	3 / 3
Distinctiveness Conflict Risk	A clear NGS/deepTools niche with distinct domain-specific triggers (BAM, bigWig, fingerprints, TSS) makes it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (531 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/deeptools/SKILL.md
Commit: 52845c3

Reviewed: about 11 hours 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.