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

85%

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

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 highly actionable, well-sequenced analysis skill with concrete code and strong reasoning guidance, but it is a monolithic single file that inlines reference material a 240-line skill would benefit from splitting out.

Suggestions

Split the per-tool API reference (Phases 1-7) into a single one-level-deep references file (e.g. REFERENCES.md) and link to it from SKILL.md, keeping the reasoning and routing overview inline.

Dedupe the variant/eQTL multi-layer reasoning that recurs across 'Reasoning: Variant Regulatory Impact', 'Reasoning: eQTL Interpretation', and 'Phase 4/Phase 8' to reduce token cost.

Add a short 'Validate result' checkpoint per phase (e.g., confirm non-empty result / expected keys before synthesis) to make the integration feedback loop explicit.

Dimension	Reasoning	Score
Conciseness	Dense with load-bearing domain decision rules rather than trivia Claude already knows, but variant/eQTL reasoning is restated across the Reasoning, Phase 4, and Phase 8 sections and could be tightened.	4 / 5
Actionability	Provides copy-paste-ready Python calling exact tool methods with result-key extraction patterns, required parameters, ID formats, and per-phase fallbacks covering the common cases.	5 / 5
Workflow Clarity	Sequences work Phase 0 through 8 with an upfront question-classification routing step and convergence/synthesis rules, but lacks explicit validate-then-retry feedback loops (no destructive ops require them).	4 / 5
Progressive Disclosure	No bundle files exist and no external references are signaled; the 240-line body inlines all per-tool reference and integration-tier content that a larger skill would typically split into one-level-deep reference files.	3 / 5
	Total	16 / 20 Passed

Description

92%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.

A strong, specific description that names concrete capabilities, explicit use-when triggers, and clear deconfliction guidance against sibling skills. It is concise and written in the correct third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete analysis types (histone-modification ChIP-seq, ATAC-seq accessibility, chromatin state, TF binding) with named data sources, giving comprehensive coverage of the domain's actions.	5 / 5
Completeness	Explicitly answers what it does (analysis types + sources) and when to use it ('Use for ...'), plus concrete boundary guidance redirecting methylation and RNA-seq to sibling skills.	5 / 5
Trigger Term Quality	Includes natural query phrases a domain user would say ('chromatin-state-by-tissue queries', 'TF-binding-by-region', 'regulatory landscape mapping', 'ENCODE-cCRE annotations'), though a few common lay synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (histone marks, chromatin accessibility, TF binding) and explicitly disambiguates adjacent domains, minimizing overlap with sibling epigenomics 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: plugin/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.