Conciseness

The body assumes domain competence (never explains what QIIME 2, DADA2, or 16S are) and nearly every sentence carries operational content, but there are minor instances that could be trimmed — e.g., the 'illustrative, not universal' disclaimer appears twice and the merged-stats subcommand caveats run long. Not 5: a few hedging sentences and repeated qualifiers are padding-adjacent; not 3: there is no wholesale unnecessary explanation, and version numbers are load-bearing operational constraints rather than decorative time-sensitivity.

Actionability

Copy-paste-ready validate and run invocations with every flag spelled out, an exact manifest header/example, the concrete overlap threshold 'trunc_f + trunc_r - maximum_insert_length >= 12', and named output artifacts (retention-qc.json, stats/stats.tsv, commands.json, workflow.log). Not 4: the examples cover the common cases completely and are executable as written, not just mostly.

Workflow Clarity

The sequence is explicit — establish the assay, prepare inputs, 'First validate without QIIME', then run, then inspect — with feedback loops and checkpoints throughout: the runner 'stops on a failing QIIME command', runs 'maximum-level QIIME artifact validation before reporting completion', low primer-match rates are surfaced as warnings with candidate causes, and per-stage stats interpretation tells the user what to review when loss occurs. This is a batch operation with explicit validation, so no cap applies. Not 4: validation checkpoints and error-recovery guidance are explicit at every phase, not mostly present.

Progressive Disclosure

A clear overview body (assay setup, input format, two runnable commands, result inspection) with one-level-deep, well-signaled references that both exist in the bundle: scripts/amplicon_workflow.py for the executable helper and references/runtime-and-interpretation.md for the release-pinned action contract, restart handling and interpretation — content appropriately split out of the main file. Not 4: navigation is easy and the split is clean, with no inlined bulk reference material and no buried references.

Specificity

"Processes paired-end 16S amplicon reads into QIIME 2 ASVs and taxonomy with retained artifact provenance" plus a concrete checklist ("paired FASTQ manifests, primer orientation diagnostics, predicted post-trimming overlap, sample IDs, runtime versions and read retention") and "guides selection of compatible taxonomic classifiers" lists multiple specific, comprehensive concrete actions with no vague filler. Not 4: coverage is comprehensive rather than having minor gaps; not below: every clause names a concrete capability.

Completeness

The 'what' is explicit and clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance — when to use it is only weakly implied by the 16S/QIIME 2 domain wording, which the guidelines cap at 3. Not 4: the 'when' is not merely under-specified, it is absent as explicit guidance; not 2: the 'what' half is concrete and specific.

Trigger Term Quality

Natural domain terms users would actually say are well covered ("paired-end 16S amplicon reads", "QIIME 2", "ASVs", "taxonomy", "FASTQ"), matching the 'good keyword coverage' anchor. Not 5: it omits common synonyms and file extensions a user might mention (e.g., 'microbiome', '.fastq.gz', 'ASV table'); not 3: the present keywords are the primary natural phrases, not a subset missing common variations.

Distinctiveness Conflict Risk

"paired-end 16S amplicon reads", "QIIME 2 ASVs and taxonomy" and "compatible taxonomic classifiers" establish a clear niche with distinct triggers and minimal overlap risk with other bioinformatics skills. Not 4: the domain, tool and output artifacts named leave almost no ambiguity about which skill applies.