{"id":20659,"plugin_id":"plugins_6aa5c14ce164819185474f73c890b680","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:16:24.723Z","digest":"a1bfb5853613f70185768f1787bd283448520ebe843188866a13deb34ba09fe9","against":null,"payload":{"description":"Diagnose whether writing matches the active writer, project, publication, and platform voice context, then offer a closer revision. Use when the user asks whether text sounds like them, feels generic, or has drifted from an established voice.","included_files":[],"name":"cw-voice-check","skill_md_contents":"---\nname: cw-voice-check\ndescription: Diagnose whether writing matches the active writer, project, publication, and platform voice context, then offer a closer revision. Use when the user asks whether text sounds like them, feels generic, or has drifted from an established voice.\n---\n\n# Voice Check\n\nEvaluate the passage against the voice context that actually governs the assignment.\n\n## Load Voice Context\n\nRead `../../references/context-contract.md`, then load the relevant maintained voice and style sources it identifies.\n\nUse this authority order for voice work:\n\n1. Explicit instructions for the current passage.\n2. The active writer and project `VOICE.md` files.\n3. Project, publication, column, or platform `STYLE.md` and more specific guides.\n4. Relevant curated examples from the active project's `examples/` folder.\n5. Legacy `TASTE.md`, only when the project still maintains it.\n6. Plugin defaults only for unresolved gaps.\n\nName the sources used in the assessment. Do not treat plugin defaults as the writer's identity.\n\n## Diagnose\n\nCheck for:\n\n- sentence architecture and cadence;\n- diction and register;\n- specificity, scenes, examples, and stakes;\n- humor, vulnerability, priors, and distinctive asides;\n- publication or platform fit;\n- smoothing, generic symmetry, scaffolding, and other AI residue;\n- phrases copied too closely from illustrative voice-guide examples.\n\nPreserve intentional rule-breaking when it carries the writer's point of view.\nTreat examples as evidence for voice rules, not a corpus to imitate.\n\n## Output\n\nProvide:\n\n1. **Voice sources used** — the live files or supplied instructions.\n2. **Aligned** — the strongest specific matches.\n3. **Drift** — the few highest-impact mismatches, quoted precisely.\n4. **Closer revision** — a usable rewrite that preserves meaning and authorship.\n5. **Judgment call** — any tension between writer voice and publication/platform constraints.\n\nDo not turn the result into a generic style checklist. The test is whether this piece sounds like this writer in this context.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}