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

88%

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

77%

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 tool signatures, examples, and well-sequenced reasoning workflows, but it is a long monolithic single file that re-explains some known biology and does not split detail into reference files.

Suggestions

Move the per-phase tool reference (Phases 0–8) into a separate references/ file and keep SKILL.md as a classification + reasoning overview with one-level-deep links, improving progressive_disclosure and reducing per-invocation token load.

Trim or condense explanations of concepts Claude already knows (histone-mark definitions, bivalent-promoter basics, 'association ≠ causation') to operational decision rules only.

If the full tool catalog must stay inline, add a short navigation/index block at the top so Claude can jump to the relevant phase without scanning all eight sections.

Dimension	Reasoning	Score
Conciseness	Largely dense and actionable, but the ~240-line single-load body explains concepts Claude already knows (histone-mark meanings, bivalent-promoter logic, 'association ≠ causation') and inlines all eight phases of per-tool reference that could be tightened or deferred.	2 / 3
Actionability	Gives exact tool names, REQUIRED parameters, defaults, and copy-paste Python snippets with result-parsing paths (e.g. result["data"]["experiments"][0]["accession"]), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Sequences work clearly via 'Classify the Question First' (a–d) then Phases 0–8, with reasoning checkpoints (gene-ID filtering, tissue-specificity checks, multi-layer synthesis rules) and a fallback table; operations are read-only so the destructive-batch cap does not apply.	3 / 3
Progressive Disclosure	No bundle files exist and the entire tool catalog plus reasoning sections sit in one monolithic SKILL.md over 50 lines; sections are well-headed but content that could be split into one-level-deep reference files is inlined rather than disclosed progressively.	2 / 3
	Total	10 / 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, trigger-rich, and complete with an explicit 'Use for' clause plus disambiguation redirects to sibling skills. It uses correct third-person voice throughout with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete analyses — "Histone-modification ChIP-seq, ATAC-seq accessibility, chromatin state, and TF binding analysis" plus "chromatin-state-by-tissue queries, TF-binding-by-region, regulatory landscape mapping, and ENCODE-cCRE annotations" — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what (the four analysis types from ENCODE/Roadmap/ChIP-Atlas) and when ("Use for chromatin-state-by-tissue queries, TF-binding-by-region, regulatory landscape mapping, and ENCODE-cCRE annotations").	3 / 3
Trigger Term Quality	Covers natural domain terms a user would say (ChIP-seq, ATAC-seq, chromatin, histone, ENCODE, cCRE, TF binding, regulatory landscape) with good variation rather than jargon-only phrasing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche and explicitly redirects overlapping cases ("For DNA methylation use tooluniverse-epigenomics; for RNA-seq use tooluniverse-rnaseq-deseq2"), making wrong-skill triggering unlikely.	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
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: 089eb8e

Reviewed: about 5 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.