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

72%

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 ./backend/cli/skills/biology/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.

A well-structured, highly actionable skill body: executable commands throughout, clear sequenced workflows with validation-first guidance, and exemplary one-level-deep reference navigation to real bundle files. The main weakness is redundancy — several late sections (Key Reminders, Reference Documentation, Example Interactions) duplicate or over-explain earlier content — and only implicit error-recovery loops.

Suggestions

Cut or merge "Key Reminders" into "Best Practices" and trim the "Reference Documentation" section to a one-line pointer per file, since each reference is already introduced inline where it is used.

Make the validation feedback loop explicit (e.g. "If validate_files.py reports errors: fix the flagged issue, then re-run validation before proceeding") in the workflow sections.

Trim "Example Interactions" and "Handling User Requests" to a short table of request → workflow/template mapping instead of multi-step response-approach scripts.

Dimension	Reasoning	Score
Conciseness	Most of the body is dense, domain-specific commands and parameters that earn their tokens, but there are several padded or duplicated sections: "Key Reminders" restates "Best Practices", "Reference Documentation" re-describes files already pointed to inline, and "Example Interactions"/"Handling User Requests" over-explain response strategies Claude could infer. This fits "mostly efficient but could be tightened" better than the noticeably-verbose anchor 2, since the padding is a minority of the document.	3 / 5
Actionability	The body is full of copy-paste-ready commands (bamCoverage with normalization flags, computeMatrix/plotHeatmap pairs, workflow generator invocations, samtools index for missing indices) covering the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Sequences are clear ("QC → Normalization → Comparison/Visualization") with an explicit validation-first checkpoint ("Before running any analysis, validate BAM, bigWig, and BED files") repeated in Quick Start and Best Practices. It falls short of a 5 because the error-recovery feedback loop is only implied — the Validation Errors section says errors are "explained in script output" rather than giving an explicit validate → fix → re-validate cycle.	4 / 5
Progressive Disclosure	The body acts as an overview pointing to four reference files, two scripts, and one asset — all verified to exist with the referenced section names — via clearly signaled one-level-deep references, per-file "Use this reference when" guidance, named target sections, and grep navigation patterns. Content is appropriately split, with only brief inline summaries (quick selection guide, common genome sizes) fronting the full reference material.	5 / 5
	Total	17 / 20 Passed

Description

66%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 compact and domain-specific with concrete named capabilities and strong bioinformatics keywords, but it lacks an explicit "Use when..." trigger clause, capping completeness. It reads as a terse capability list rather than a full what-and-when statement.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with BAM/bigWig files, ChIP-seq/RNA-seq/ATAC-seq data, or when the user asks for coverage tracks, QC plots, or heatmaps around genomic features."

Use verb-led phrases ("Converts BAM to bigWig", "Generates heatmaps") instead of fragment-style noun phrases to make the capability list read as actions.

Include common synonyms and extensions users would say (e.g. ".bam", "coverage tracks", "sequencing data") to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "BAM to bigWig conversion", "QC (correlation, PCA, fingerprints)", "heatmaps/profiles (TSS, peaks)" — but they are fragment-style noun phrases with minor gaps (no mention of normalization or sample comparison), matching the anchor for several specific actions rather than the comprehensive coverage of a 5.	4 / 5
Completeness	The "what" is clearly stated, but the closing phrase "for ChIP-seq, RNA-seq, ATAC-seq visualization" is domain scoping rather than an explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 3. It is not a 2 because the what is concrete and the application domains give weakly implied trigger guidance.	3 / 5
Trigger Term Quality	Strong natural domain keywords users would say ("ChIP-seq", "RNA-seq", "ATAC-seq", "BAM", "bigWig", "heatmap", "PCA", "TSS") with good coverage, but common variations like "coverage tracks", "sequencing data", or file extensions (.bam, .bw) are missing, so it does not reach the comprehensive synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	NGS-specific terms like "bigWig", "TSS", and the named assay types create a clear niche with minimal conflict risk, but "NGS analysis toolkit" and "QC" are broad enough to overlap slightly with adjacent bioinformatics skills, keeping it below a 5.	4 / 5
	Total	15 / 20 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 (537 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: 4082a2e

Reviewed: 1 day 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.