菜单
Runs parallel prose and craft review agents against a voice profile. Use when checking generated content for AI patterns and voice drift before publishing.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/athola/claude-night-market --skill voice-review命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Turn hunches into accepted results: worthiness score, evidence bar, research-to-rules. Use when vetting ideas. Not for QA; use night-market-validation-and-qa.
Generates and self-executes a diff-derived test plan for a PR. Use when validating PR changes before merge. Do not use for code review; use sanctum:pr-review.
Curate the web-capture index. Use when the capture backlog grows, captures sit unprocessed at seedling/pending, or to surface stored research during work.
正在显示 SKILL.md
基于 SOC 职业分类
| name | voice-review |
| description | Runs parallel prose and craft review agents against a voice profile. Use when checking generated content for AI patterns and voice drift before publishing. |
| globs | **/*.{md,txt} |
| alwaysApply | false |
| category | writing-quality |
| tags | ["voice","review","prose","craft","quality"] |
| tools | [] |
| complexity | medium |
| model_hint | standard |
| estimated_tokens | 1600 |
| progressive_loading | false |
| dependencies | ["scribe:voice-extract","scribe:voice-generate","scribe:slop-detector","imbue:review-core","imbue:structured-output"] |
Dispatch dual review agents and present unified findings.
scribe:voice-generate)scribe:slop-detector)Two agents run in parallel on the generated text:
Hard failures (banned phrases, em dashes) are auto-fixed. Everything else returns as advisory tables for user decision.
voice-review:text-loaded - Generated text readvoice-review:register-loaded - Voice register loadedvoice-review:agents-dispatched - Both reviewers launchedvoice-review:hard-fails-fixed - Auto-corrections appliedvoice-review:advisories-presented - Tables shown to uservoice-review:findings-verified - Citations confirmed by verifierRead:
Launch both agents in parallel:
Agent(prose-reviewer):
- text: {generated_text}
- register: {register_content}
- banned_phrases: {banned_list}
Agent(craft-reviewer):
- text: {generated_text}
- register: {register_content}
Apply all auto-fixes from prose reviewer silently:
Report: "Fixed N hard failures (X banned phrases, Y em dashes, Z patterns)"
Present both tables to the user:
Prose Review Advisories:
| # | Line | Anchor | Pattern | Current | Proposed fix |
|---|
Craft Review:
| Dimension | Rating | Notes | Proposed improvement |
|---|
For each advisory row, user can:
Present as:
[1] Prose: Frictionless transition at "Furthermore, the..."
Proposed: Cut transition, start mid-thought
[a]ccept / [r]eject / re[w]rite?
If the user has learning mode enabled:
~/.claude/voice-profiles/{name}/learning/snapshots/When dispatched from voice-generate, the flow is:
Can also be run on any existing text:
/voice-review path/to/file.md --profile myvoice --register casual
voice-review:findings-verified)Every advisory row must cite a real line and a verbatim anchor. Write
findings to .review/findings.json and confirm each citation resolves:
python plugins/imbue/scripts/citation_verifier.py \
--findings .review/findings.json --repo-root .
Drop or label UNVERIFIED any finding the verifier fails (exit 1); only
verified findings enter the advisory tables. See Skill(imbue:review-core)
Step 5 and Skill(imbue:structured-output) for the schema.
After the review completes, validate these conditions:
Line (file:line) and verbatim Anchor;
citation_verifier.py confirmed all citations (exit 0) or unverified
rows are dropped/labeled UNVERIFIEDThe test suite (test_voice_review.py) validates: