mit einem Klick
webnovel-review
// Reviews chapter quality using 5 specialized checkers and generates comprehensive reports. Activates when user requests chapter review or /webnovel-review.
// Reviews chapter quality using 5 specialized checkers and generates comprehensive reports. Activates when user requests chapter review or /webnovel-review.
Writes webnovel chapters (3000-5000 words) using v5.1 dual-agent architecture. Context Agent gathers context, writer produces pure text (no XML tags), review agents report issues, polish fixes problems, Data Agent extracts entities with AI.
Initializes webnovel projects with settings, outline framework, and state.json. Supports quick/standard/deep modes. Activates when user wants to start a new novel or /webnovel-init.
Plans detailed volume outlines with chapter-by-chapter breakdown, cool-point distribution, and Strand Weave pacing. Activates when user requests outline planning or /webnovel-plan.
Queries project settings for characters, powers, factions, items, and foreshadowing. Supports urgency analysis and golden finger status. Activates when user asks about story elements or /webnovel-query.
Recovers interrupted webnovel tasks with precise workflow state tracking. Detects interruption point and provides safe recovery options. Activates when user wants to resume or /webnovel-resume.
| name | webnovel-review |
| description | Reviews chapter quality using 5 specialized checkers and generates comprehensive reports. Activates when user requests chapter review or /webnovel-review. |
| allowed-tools | Read Grep Write Edit Bash Task AskUserQuestion |
Copy and track progress:
质量审查进度:
- [ ] Step 1: 加载核心约束 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/core-constraints.md")
- [ ] Step 2: 加载爽点标准 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/cool-points-guide.md")
- [ ] Step 3: 加载节奏标准 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/strand-weave-pattern.md")
- [ ] Step 4: 加载常见错误 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/common-mistakes.md")
- [ ] Step 5: 加载项目状态 (cat .webnovel/state.json)
- [ ] Step 6: 确认上下文充足
- [ ] Step 7: 调用 5 个检查员 (并行 Task)
- [ ] Step 8: 生成审查报告
- [ ] Step 9: 处理关键问题
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/core-constraints.md"
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/cool-points-guide.md"
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/strand-weave-pattern.md"
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/common-mistakes.md"
可选加载节奏控制参考:
# 如需深入分析节奏控制,可加载此文件
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-review/references/pacing-control.md"
cat .webnovel/state.json
检查清单:
如有缺失 → 返回对应 Step
使用 Task 工具并行调用 5 个专职检查员:
调用格式示例(所有检查员并行执行):
high-point-checker 子代理:审查章节 {range},重点检查爽点密度和多样性consistency-checker 子代理:审查章节 {range},重点检查设定违规 vs state.jsonpacing-checker 子代理:审查章节 {range},重点检查 Strand 分布ooc-checker 子代理:审查章节 {range},重点检查角色行为一致性continuity-checker 子代理:审查章节 {range},重点检查时间线和剧情连贯注意:Claude 会自动根据描述匹配并调用对应的子代理
保存到: 审查报告/第{start}-{end}章审查报告.md
报告结构:
# 第 {start}-{end} 章质量审查报告
## 📊 综合评分
| 维度 | 评分 | 状态 |
|------|------|------|
| 爽点密度 | X/10 | ✅/🟡/🟠/🔴 |
| 设定一致性 | X/10 | ... |
| 节奏控制 | X/10 | ... |
| 人物塑造 | X/10 | ... |
| 连贯性 | X/10 | ... |
| **总评** | **X/50** | **等级** |
## 📋 修改优先级
### 🔴 高优先级(必须修改)
{检查员发现的问题}
### 🟠 中优先级(建议修改)
{检查员发现的问题}
### 🟡 低优先级(可选优化)
{检查员发现的问题}
## 📈 改进建议
{具体可行的建议}
评分标准:
如发现 🔴 问题,询问用户:
python "${CLAUDE_PLUGIN_ROOT}/scripts/update_state.py" \
--add-review "{start}-{end}" "审查报告/第{start}-{end}章审查报告.md"