tooluniverse-epigenomics

Production-ready genomics and epigenomics data processing for BixBench questions. Handles methylation array analysis (CpG filtering, differential methylation, age-related CpG detection, chromosome-level density), ChIP-seq peak analysis (peak calling, motif enrichment, coverage stats), ATAC-seq chromatin accessibility, multi-omics integration (expression + methylation correlation), and genome-wide statistics. Pure Python computation (pandas, scipy, numpy, pysam, statsmodels) plus ToolUniverse annotation tools (Ensembl, ENCODE, SCREEN, JASPAR, ReMap, RegulomeDB, ChIPAtlas). Supports BED, BigWig, methylation beta-value matrices, Illumina manifest files, and multi-sample clinical data. Use when processing methylation data, ChIP-seq peaks, ATAC-seq signals, or answering questions about CpG sites, differential methylation, chromatin accessibility, histone marks, or epigenomic statistics.

Quality

82%

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

Quality

Content

65%

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 executable code and a clear phased workflow, but it is over-long for a SKILL.md and monolithically inline with weak validation checkpoints. Splitting reference material into bundle files and adding explicit validation feedback loops would lift the lower dimensions.

Suggestions

Move the chromosome-length tables, the ToolUniverse tool-parameter reference, and the full function library into separate files under references/ and link to them one level deep, keeping SKILL.md a concise overview.

Add explicit validate -> fix -> retry checkpoints in the batch/destructive workflows (e.g. differential methylation, peak overlap) and require verification before reporting results.

Trim the restated Summary and the duplicate intro paragraph, and tighten inline function definitions, to reduce token cost while preserving the actionable code.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable code rather than concept-explanation Claude already knows, but it is padded with full chromosome-length tables for three builds (~80 lines of literals), a Summary that restates the intro, and inline function implementations that could be tightened. Not the lean level above; not verbose-with-concept-fluff below.	2 / 3
Actionability	Provides concrete, runnable Python with real imports and pandas/scipy/statsmodels usage, plus a tool-parameter reference table with required params; the local-computation code is copy-paste ready rather than pseudocode. Not the incomplete/pseudocode level below.	3 / 3
Workflow Clarity	Phases (0-7), a decision tree, and numbered use-pattern flows give a clear sequence, but there are no explicit validate-then-fix-then-retry checkpoints for batch/destructive operations, which the rubric caps at 2. Not the missing-sequence level below; not the explicit-checkpoint level above.	2 / 3
Progressive Disclosure	No bundle/reference files exist and the entire body is inline in one monolithic file; content such as chromosome-length tables, the tool reference, and the function library would be better split into referenced files. Well-sectioned but content that should be separate is inline, matching the 2 anchor; not the well-signaled one-level-deep references above.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, uses third-person voice, includes a clear 'Use when' trigger clause, and names a distinctive epigenomics niche with concrete file-format keywords. It is a strong, complete description with no over-claims or vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions per domain ("CpG filtering, differential methylation, age-related CpG detection, chromosome-level density"; "peak calling, motif enrichment, coverage stats"), matching the multiple-specific-actions anchor rather than the partial 'names domain and some actions' anchor.	3 / 3
Completeness	Explicitly states what it does (full capability list) and when to use it ("Use when processing methylation data, ChIP-seq peaks, ATAC-seq signals, or answering questions about CpG sites..."), satisfying both what and when; not the level below which lacks an explicit when clause.	3 / 3
Trigger Term Quality	Covers natural user terms broadly ("methylation", "ChIP-seq", "ATAC-seq", "CpG sites", "differential methylation", "chromatin accessibility", "histone marks", "BED", "BigWig", "Illumina"), matching the good-coverage anchor rather than the missing-common-variations anchor.	3 / 3
Distinctiveness Conflict Risk	The epigenomics niche plus ToolUniverse annotation tools and concrete file-format triggers give it a clear, distinct niche unlikely to fire for sibling RNA-seq/variant/protein skills; not the level below which could overlap.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1490 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: 2 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.