ngs-fastq-qc

Validate FASTQ inputs, run local FastQC/MultiQC QC, interpret QC signals, and optionally execute fastp or Cutadapt trimming branches without overwriting raw reads.

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

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An action-dense, well-organized body with executable commands and valuable domain interpretation rules and no padding. The main gap is workflow_clarity: validation and error-recovery checkpoints are delegated to the runner rather than surfaced as an explicit feedback loop.

Suggestions

Add an explicit validate→fix→retry loop, e.g. 'If preflight or runner validation fails, read validation/, fix the sample sheet/inputs, and re-run preflight before --execute.'

Surface the runner's pre-execution validation as a concrete checkpoint step with what to check (sample-sheet pairing, FASTQ existence) before proceeding to execution.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no basic-concept explanations, just executable commands, a focused inputs checklist, tool list, and domain interpretation rules that each earn their place; not score 2 because there is no padded or unnecessary explanation.	3 / 3
Actionability	Fully executable bash with real flags and literal adapter sequences (e.g. '--adapter-r1 AGATCGGAAGAGC'), plus copy-paste fastp/FastQC/MultiQC examples; not score 2 because commands are complete rather than pseudocode.	3 / 3
Workflow Clarity	A clear section sequence (Preflight → Local Execution → Interpretation → Output Review) with preflight and runner pre-execution validation exists, but explicit validate→fix→retry feedback loops are not described and checkpoints are delegated to the runner; not score 3 because error-recovery loops are implicit, not score 1 because the sequence and some validation are present.	2 / 3
Progressive Disclosure	No bundle files exist; the single self-contained SKILL.md is cleanly sectioned with no nested references, so well-organized sections satisfy progressive disclosure; not score 2 because there is no monolithic wall or inline content that should be split out.	3 / 3
	Total	11 / 12 Passed

Description

82%Weight 40%Scale 1-3

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, well-targeted description with concrete actions and natural domain terms, but it states only what the skill does and never when to invoke it. Adding an explicit 'Use when...' clause would raise completeness.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when QC-ing or trimming FASTQ reads, interpreting FastQC/MultiQC reports, or deciding whether trimming is warranted.'

Keep the tool names but ensure the trigger covers common phrasings users say ('FASTQ quality control', 'read trimming', 'adapter removal').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools — 'Validate FASTQ inputs, run local FastQC/MultiQC QC, interpret QC signals, and optionally execute fastp or Cutadapt trimming branches' — matching the multiple-specific-actions anchor; not score 2 because actions are comprehensive rather than partial.	3 / 3
Completeness	Clearly answers 'what' but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 2; not score 3 because 'when' is entirely absent, and not score 1 because 'what' is strong.	2 / 3
Trigger Term Quality	Covers natural terms a genomics user would say — 'FASTQ', 'FastQC', 'MultiQC', 'QC', 'trimming', 'fastp', 'Cutadapt' — with good breadth; not score 2 because common variations are present rather than missing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear NGS FASTQ-QC niche with distinct tool triggers (FastQC/MultiQC/fastp/Cutadapt) unlikely to fire for unrelated skills; not score 2 because the scope is tightly scoped rather than broadly overlapping.	3 / 3
	Total	11 / 12 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-fastq-qc/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.