ngs-amplicon-microbiome

Kick off public 16S, 18S, ITS, COI, or other marker-gene amplicon microbiome workflows using nf-core/ampliseq, QIIME2, DADA2, and Cutadapt.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/ngs-analysis/skills/ngs-amplicon-microbiome/SKILL.md

Quality

Content

65%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.

The body is highly actionable with executable commands and a clear staged workflow, but it is somewhat verbose and monolithic, with no progressive disclosure into reference files and only implicit error-recovery loops. Splitting detail tables/edge cases into referenced files and adding explicit validate-and-retry steps would raise the weaker dimensions.

Suggestions

Move the long output-table enumeration and resource-check advisory detail into a referenced file (e.g. references/outputs.md) and keep SKILL.md as a lean overview, enabling one-level-deep progressive disclosure.

Add an explicit feedback loop for backend runs, e.g. 'If qc_verdict.json reports not-ready, resolve the listed reason codes and re-run preflight before proceeding'.

Tighten the visualization/edge-case paragraphs (synthetic-diversity, BIOM-conversion) to the essential flags and verdicts to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body mostly assumes Claude's knowledge (no explaining of what 16S or DADA2 is) but several sections enumerate long output-table lists and edge-case advisory paragraphs that could be tightened, matching the mostly-efficient-but-could-be-tightened anchor.	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash commands with concrete flags, file paths, and primer examples across preflight, local, and backend stages, matching the executable-and-complete anchor.	3 / 3
Workflow Clarity	The preflight → local package → backend → visualization sequence is clear and includes validation artifacts (qc_verdict.json, readiness verdict gates), but explicit error-recovery feedback loops (validate → fix → re-run) for the batch/backend operations are only implicit, matching the steps-present-but-checkpoints-implicit anchor.	2 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the skill is a single ~95-line monolithic SKILL.md with detailed inline output/resource tables that could be split into reference files, so structure is present but content that should be separate is inline.	2 / 3
	Total	9 / 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.

The description is specific, distinctive, and rich in natural trigger terms, but it omits an explicit 'Use when ...' trigger clause, which caps completeness at 2. Adding an explicit when-to-use sentence would lift it to a top-tier description.

Suggestions

Append an explicit 'Use when ...' clause naming user phrasings (e.g. 'Use when the user mentions amplicon sequencing, 16S/ITS analysis, or wants an ASV/taxonomy workflow').

Consider listing the downstream endpoints (ASV table, taxonomy, diversity) in the description to make the 'what' even more complete.

Dimension	Reasoning	Score
Specificity	The description names concrete tools (nf-core/ampliseq, QIIME2, DADA2, Cutadapt) and concrete marker regions (16S, 18S, ITS, COI) tied to a concrete action ('Kick off ... workflows'), matching the multiple-specific-concrete-actions anchor.	3 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2 even though the 'when' context is implied by the domain terms.	2 / 3
Trigger Term Quality	Natural bioinformatics terms a user would say ('16S', '18S', 'ITS', 'COI', 'amplicon microbiome', 'marker-gene') are present with good coverage of common variations, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The narrow amplicon-microbiome niche with named tools and marker regions is clearly distinguishable from other skills and unlikely to trigger for the wrong skill, matching the clear-niche anchor.	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-amplicon-microbiome/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.