Name: tooluniverse-epigenomics-chromatin
Rating: 70.39999999999999 (1 reviews)
Author: mims-harvard

tooluniverse-epigenomics-chromatin

Histone-modification ChIP-seq, ATAC-seq accessibility, chromatin state, and TF binding analysis from ENCODE, Roadmap Epigenomics, ChIP-Atlas. Use for chromatin-state-by-tissue queries, TF-binding-by-region, regulatory landscape mapping, and ENCODE-cCRE annotations. For DNA methylation use tooluniverse-epigenomics; for RNA-seq use tooluniverse-rnaseq-deseq2.

Quality

86%

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

The canonical home for this skill is tooluniverse-epigenomics-chromatin in mims-harvard/ToolUniverse

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.

The body is highly actionable with concrete executable examples and a clear phased workflow plus fallback strategies. It is dense and mostly token-efficient, though some reasoning sections re-explain known biology. The main weakness is monolithic structure: no bundle files exist and the substantial tool catalog is all inlined with no references to split-out detail.

Suggestions

Move the per-phase tool reference (Phases 1–7) into a separate references/TOOL_CATALOG.md and keep SKILL.md as an overview pointing to it, so the body practices one-level-deep progressive disclosure.

Tighten the Histone Marks and eQTL Interpretation reasoning sections into pure if/then decision rules, dropping definitions of marks and eQTL semantics Claude already knows.

Add an explicit validation checkpoint in Phase 0/Phase 8 (e.g., confirm gene-symbol resolution and cross-check layer convergence) to convert the implicit disambiguation into a stated verify step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, dense, high-signal content (tool + params + format notes + code), but the Histone Marks and eQTL Interpretation reasoning sections explain biology Claude largely already knows and could be trimmed to pure decision rules.	4 / 5
Actionability	Fully executable copy-paste Python examples with concrete result-access patterns, exact parameter names, and precise format strings (ENSG00000012048.20, rs4994, chr17_43705621_T_C_b38) covering the common cases.	5 / 5
Workflow Clarity	Clear Phase 0–8 sequence with upfront question classification, disambiguation, fallback table, and retry hints ("if 0 results, retry with polyA plus RNA-seq"); minor validation gaps but the skill is read-only query-based so the destructive-cap does not apply.	4 / 5
Progressive Disclosure	Well-organized section headers, but the body is a single monolithic ~230-line file with no bundle files or one-level-deep references; the per-phase tool catalog is content that could be split into a separate reference file and is instead fully inline.	3 / 5
	Total	16 / 20 Passed

Description

95%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 strong: it names a precise niche, enumerates concrete analysis types and use cases, and explicitly steers away overlapping domains toward sibling skills. Trigger term coverage is rich and natural for the target audience. The only minor gap is that actions are framed as analysis categories rather than crisp discrete verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete analysis types ("Histone-modification ChIP-seq, ATAC-seq accessibility, chromatin state, and TF binding analysis") plus specific use cases ("chromatin-state-by-tissue queries, TF-binding-by-region, regulatory landscape mapping, and ENCODE-cCRE annotations"), but the actions are domain categories rather than discrete verbs, leaving minor coverage gaps versus the comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what (histone-modification/chromatin accessibility analysis from named sources) and when ("Use for chromatin-state-by-tissue queries, TF-binding-by-region, regulatory landscape mapping, and ENCODE-cCRE annotations") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural domain terms with synonyms and source names a user would actually say ("ChIP-seq", "ATAC-seq", "chromatin state", "TF binding", "ENCODE", "Roadmap Epigenomics", "ChIP-Atlas", "ENCODE-cCRE").	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit disambiguation ("For DNA methylation use tooluniverse-epigenomics; for RNA-seq use tooluniverse-rnaseq-deseq2") that actively minimizes conflict with sibling skills.	5 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-epigenomics-chromatin/SKILL.md
Commit: 1b02920

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.