CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, action-dense skill body with executable commands, non-destructive safeguards, and genuine domain judgment (assay-aware duplication interpretation, overrepresented-sequence classification). The main gaps are the absence of an explicit validation-failure feedback loop and mild command duplication between the runner and direct-tool sections.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — interpretation rules and input checklists are genuine domain knowledge, with no basic-concept padding — but there is minor redundancy between the four runner invocations in 'Local Execution' and the direct-tool commands in 'Kickoff Pattern' that could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready commands with concrete flags ('--trim-mode cutadapt --adapter-r1 AGATCGGAAGAGC', '--sample-sheet', '-t 4') covering the common cases: QC-only, single paired sample, optional trimming, and explicit adapters.

5 / 5

Workflow Clarity

A clear sequence (Preflight → Local Execution → Interpretation Rules → Output Review) with most checkpoints present ('performs pre-execution validation', 'verify R1/R2 file counts and read-name pairing', 'Do not overwrite input FASTQs'), but there is no explicit error-recovery loop describing what to do when pre-execution validation fails.

4 / 5

Progressive Disclosure

No bundle files exist and the body has clean, well-labeled sections with no nested or buried references; the minor gap is that the four runner command variants could be consolidated or moved to a reference file. The under-50-line exception for a 5 does not apply to this ~120-line body.

4 / 5

Total

17

/

20

Passed

Description

75%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, well-anchored description with concrete named actions and tools, but it lacks any 'Use when…' trigger clause, so it answers 'what' thoroughly while leaving 'when' entirely implicit. Adding a trigger clause with a few synonyms/extensions would lift completeness and trigger-term quality.

Suggestions

Append a trigger clause such as 'Use when the user mentions FASTQ files (.fastq/.fq), read quality, adapter or primer trimming, or QC reports for sequencing data' to fix the missing 'when' that caps completeness at 3.

Add natural synonyms and file extensions users actually say — 'quality control', 'adapter trimming', '.fastq', '.fq.gz' — to improve trigger-term coverage from 4 to 5.

Consider naming the interpretation deliverable users ask for (e.g., 'produce QC interpretation and trimming recommendation') so the output expectation is explicit.

DimensionReasoningScore

Specificity

The description lists multiple concrete, named actions covering the full domain scope — 'Validate FASTQ inputs', 'run local FastQC/MultiQC QC', 'interpret QC signals', and 'optionally execute fastp or Cutadapt trimming branches' — plus an explicit safety constraint ('without overwriting raw reads'), matching the comprehensive-coverage anchor rather than the minor-gaps anchor.

5 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when…' clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guideline.

3 / 5

Trigger Term Quality

Natural user terms are well covered ('FASTQ', 'QC', 'FastQC', 'MultiQC', 'fastp', 'Cutadapt', 'trimming', 'raw reads'), but common variations and synonyms are absent — no '.fastq'/.fq' file extensions, no 'quality control' or 'adapter trimming' phrasing — so it falls short of the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

A clear niche (FASTQ quality control and trimming) with distinct tool-name triggers (FastQC, MultiQC, fastp, Cutadapt) and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.