Voice Check
Evaluate the passage against the voice context that actually governs the assignment.
Load Voice Context
Read ../../references/context-contract.md, then load the relevant maintained voice and style sources it identifies.
Use this authority order for voice work:
- Explicit instructions for the current passage.
- The active writer and project
VOICE.mdfiles. - Project, publication, column, or platform
STYLE.mdand more specific guides. - Relevant curated examples from the active project's
examples/folder. - Legacy
TASTE.md, only when the project still maintains it. - Plugin defaults only for unresolved gaps.
Name the sources used in the assessment. Do not treat plugin defaults as the writer's identity.
Diagnose
Check for:
- sentence architecture and cadence;
- diction and register;
- specificity, scenes, examples, and stakes;
- humor, vulnerability, priors, and distinctive asides;
- publication or platform fit;
- smoothing, generic symmetry, scaffolding, and other AI residue;
- phrases copied too closely from illustrative voice-guide examples.
Preserve intentional rule-breaking when it carries the writer's point of view. Treat examples as evidence for voice rules, not a corpus to imitate.
Output
Provide:
- Voice sources used — the live files or supplied instructions.
- Aligned — the strongest specific matches.
- Drift — the few highest-impact mismatches, quoted precisely.
- Closer revision — a usable rewrite that preserves meaning and authorship.
- Judgment call — any tension between writer voice and publication/platform constraints.
Do not turn the result into a generic style checklist. The test is whether this piece sounds like this writer in this context.