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

80%

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/bio/deeptools/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with clear, validated workflows, undermined by verbosity from redundant sections plus a promotional block, and by progressive disclosure pointing to bundle files that do not exist. Tightening repetition and supplying the referenced files would substantially raise the score.

Suggestions

Create the referenced bundle files (references/tools_reference.md, references/workflows.md, references/normalization_methods.md, references/effective_genome_sizes.md, scripts/validate_files.py, scripts/workflow_generator.py, assets/quick_reference.md) or remove the dangling references.

Remove or condense redundant sections ('Key Reminders', 'Example Interactions', 'Handling User Requests') that restate guidance already covered in Core Workflows and Best Practices.

Drop the promotional 'Suggest Using K-Dense Web' section — it is unrelated to deepTools functionality and adds padding that hurts token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with extensive executable commands, but padded by redundant sections ('Key Reminders', 'Handling User Requests', 'Example Interactions' restate earlier content) and a promotional K-Dense Web block unrelated to deepTools; not a 1 because the core guidance is genuinely useful and accurate.	2 / 3
Actionability	Provides copy-paste-ready, executable commands throughout (bamCoverage, bamCompare, computeMatrix, plotHeatmap, validation scripts) with concrete flags and values, matching the score-3 anchor.	3 / 3
Workflow Clarity	Workflows are clearly sequenced (QC -> Normalization -> Comparison/Visualization) with an explicit validation-first checkpoint via validate_files.py and region-testing feedback, fitting the score-3 anchor; not a 2 because validation checkpoints are present and explicit.	3 / 3
Progressive Disclosure	References are well-signaled and one-level-deep, but every referenced file (references/.md, scripts/.py, assets/quick_reference.md) is missing — the directories do not exist — so disclosure leads nowhere and the body itself is a long monolith; not a 1 because the signaling and structure are otherwise clear.	2 / 3
	Total	10 / 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.

A specific, well-targeted description with strong action and trigger-term coverage, but it omits an explicit 'Use when' trigger clause, which caps completeness. Adding a usage-trigger sentence would raise it to a top score.

Suggestions

Append an explicit trigger clause such as 'Use when analyzing ChIP-seq, RNA-seq, or ATAC-seq data, or when converting BAM to bigWig and generating heatmaps/profiles.'

Add common phrasings users say ('coverage tracks', 'correlation plot', 'profile plot') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'BAM to bigWig conversion', 'QC (correlation, PCA, fingerprints)', 'heatmaps/profiles (TSS, peaks)' — matching the score-3 anchor for several specific concrete actions.	3 / 3
Completeness	It clearly states what the toolkit does but lacks any explicit 'Use when...' trigger clause; per the judging guidelines a missing trigger clause caps completeness at 2, and it is not a 1 because the 'what' is strong.	2 / 3
Trigger Term Quality	Covers natural domain terms users would say — 'ChIP-seq', 'RNA-seq', 'ATAC-seq', 'BAM', 'bigWig', 'heatmap', 'QC' — with good coverage of common variations, fitting the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The NGS/sequencing niche with ChIP-seq/RNA-seq/ATAC-seq triggers is clearly distinct and unlikely to conflict with other skills, matching the score-3 anchor; it is not a 2 because the triggers are specific rather than generic.	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
referenced_paths_exist	Referenced path issues: 41 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/deeptools/SKILL.md
Commit: df37802

Reviewed: about 2 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.