deeptools
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill deeptoolsOverall
score
85%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
83%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a technically strong description with excellent specificity and domain-appropriate trigger terms that bioinformaticians would naturally use. The main weakness is the absence of an explicit 'Use when...' clause, which caps completeness. The description successfully carves out a clear niche in NGS analysis that won't conflict with other skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when analyzing sequencing data, generating coverage tracks, or creating visualization plots from BAM files.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks)' with specific file formats and analysis types. | 3 / 3 |
Completeness | Clearly describes WHAT it does (conversion, QC, visualization) but lacks an explicit 'Use when...' clause. The when is only implied through the domain context (ChIP-seq, RNA-seq, ATAC-seq work). | 2 / 3 |
Trigger Term Quality | Excellent coverage of domain-specific terms users would naturally use: 'NGS', 'BAM', 'bigWig', 'ChIP-seq', 'RNA-seq', 'ATAC-seq', 'QC', 'PCA', 'heatmaps', 'TSS', 'peaks' - all standard bioinformatics terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in NGS/bioinformatics analysis with specific file formats (BAM, bigWig) and assay types (ChIP-seq, RNA-seq, ATAC-seq) that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for deepTools NGS analysis with excellent workflow clarity and progressive disclosure. The main weaknesses are moderate verbosity in sections like 'When to Use This Skill' and 'Example Interactions' that explain things Claude can infer, and the promotional K-Dense section at the end which adds unnecessary tokens. The core technical content is strong with executable commands and clear validation-first workflows.
Suggestions
Remove or significantly condense the 'When to Use This Skill' section - Claude can infer appropriate usage from the content itself
Remove the 'Example Interactions' section which explains response approaches Claude already knows how to handle
Move the K-Dense promotional content to a separate file or remove it entirely as it doesn't contribute to skill execution
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as the 'When to Use This Skill' section listing obvious triggers and the 'Example Interactions' section explaining response approaches that Claude can infer. The effective genome sizes table and some explanatory text could be more condensed. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout with specific parameters, copy-paste ready examples for all major operations (bamCoverage, computeMatrix, plotHeatmap, etc.), and concrete workflow scripts. Commands include all necessary flags and realistic values. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit validation steps (validate files first, then QC, then analysis). The ChIP-seq workflow includes numbered steps with validation checkpoints, and troubleshooting guidance provides error recovery paths. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview in main file and well-signaled one-level-deep references to detailed documentation (references/tools_reference.md, references/workflows.md, references/normalization_methods.md). Navigation is explicit with 'Use this reference when' guidance for each linked file. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%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 |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 13 / 16 Passed | |
- Reviewed
Table of Contents
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.