ngs-epigenomics-peaks

Dispatch ATAC-seq, ChIP-seq, CUT&RUN, or CUT&Tag requests to assay-specific QC, alignment, signal-track, peak-calling, consensus, and differential peak workflows.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/ngs-analysis/skills/ngs-epigenomics-peaks/SKILL.md

Quality

Content

81%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.

An exceptionally lean, executable dispatcher body with copy-paste commands for every assay route and tidy section structure. Its main weakness is the absence of explicit validation checkpoints / feedback loops for what are inherently batch and potentially long-running operations, which caps workflow clarity.

Suggestions

Add an explicit validation gate after preflight, e.g. 'Check peak_calling_readiness.json; only proceed to the assay workflow when all samples pass,' to create a validate→fix→retry loop.

Include a brief checkpoint for confirming replicate/control metadata is present before the real analysis run, since the kickoff notes this but does not gate on it.

Note how to interpret preflight failures or where the readiness JSON schema lives, so Claude can recover from errors without guessing.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: every line is actionable input, command, or a one-line routing rule, with no padding or explanation of concepts Claude already knows; it assumes competence and every token earns its place.	5 / 5
Actionability	Fully executable copy-paste commands for preflight, the FASTQ assay package, and all three nextflow kickoff profiles, each with concrete flags, paths, and expected outputs; covers the common assay cases directly.	5 / 5
Workflow Clarity	A clear routing sequence (confirm inputs → choose workflow → preflight → run) is present, but batch bioinformatics operations have no explicit validation checkpoints or feedback loops, and the preflight emits a readiness artifact yet there is no 'validate-then-proceed' loop — the destructive/batch cap holds it at 3.	3 / 5
Progressive Disclosure	Well under 50 lines with no external bundle files and cleanly organized into Essential Inputs, Public Defaults, Preflight, Execution Package, and Kickoff Pattern sections; the simple-skill exception applies and structure is clear and navigable.	5 / 5
	Total	18 / 20 Passed

Description

66%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 specific, distinct dispatcher description that names the key assays and concrete workflow stages, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Adding a one-sentence trigger phrase would raise it to a top-tier description.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a user requests ATAC-seq, ChIP-seq, CUT&RUN, or CUT&Tag peak analysis,' to satisfy the missing 'when' and lift completeness.

Optionally add the file-format or data-type terms users mention (e.g. FASTQ/BAM, narrow vs broad peaks) to strengthen trigger-term coverage further.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('QC, alignment, signal-track, peak-calling, consensus, and differential peak workflows') across named assays, but these are workflow categories rather than the granular actions of a 5-level example; minor coverage gaps keep it just below 5.	4 / 5
Completeness	The 'what' is clear (dispatch to assay-specific workflows), but there is no explicit 'Use when...' trigger clause, and the judging guideline caps completeness at 3 when such guidance is missing.	3 / 5
Trigger Term Quality	Comprehensively names the natural assay terms users say — 'ATAC-seq, ChIP-seq, CUT&RUN, or CUT&Tag' — plus downstream keywords like peaks and differential, covering the core synonyms a user would utter.	5 / 5
Distinctiveness Conflict Risk	The assay name list carves a clear epigenomics dispatcher niche with distinct triggers, though the broad 'QC, alignment, peak-calling' verbs create minor overlap with adjacent NGS skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/ngs-analysis/skills/ngs-epigenomics-peaks/SKILL.md
Commit: 1dc1958

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.