// 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-resume |
| description | 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. |
| allowed-tools | Read Bash AskUserQuestion |
Copy and track progress:
任务恢复进度：
- [ ] Step 1: 加载恢复协议 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/workflow-resume.md")
- [ ] Step 2: 加载数据规范 (cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/system-data-flow.md")
- [ ] Step 3: 确认上下文充足
- [ ] Step 4: 检测中断状态
- [ ] Step 5: 展示恢复选项 (AskUserQuestion)
- [ ] Step 6: 执行恢复
- [ ] Step 7: 继续任务 (可选)
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/workflow-resume.md"
核心原则（读取后应用）：
cat "${CLAUDE_PLUGIN_ROOT}/skills/webnovel-resume/references/system-data-flow.md"
检查清单：
如有缺失 → 返回对应 Step
| Step | 难度 | 恢复策略 |
|---|---|---|
| Step 1 | ⭐ | 直接重新执行 |
| Step 2 | ⭐⭐ | 删除半成品，重新开始 |
| Step 3 | ⭐⭐ | 重新运行提取 |
| Step 4 | ⭐⭐⭐ | 验证 state.json 一致性 |
| Step 5 | ⭐⭐ | 重新运行 strand 更新 |
| Step 6 | ⭐⭐⭐⭐⭐ | 成本高 - 5个检查员 ~$0.15 |
| Step 7 | ⭐ | 重新运行 git 备份 |
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" detect
输出情况：
展示给用户：
示例输出：
🔴 检测到中断任务：
任务：/webnovel-write 7
中断位置：Step 2 - 章节内容生成中
已完成：
✅ Step 1: 上下文加载
未完成：
⏸️ Step 2: 章节内容（已写1500字）
⏹️ Step 3-7: 未开始
恢复选项：
A) 删除半成品，从Step 1重新开始（推荐）
B) 回滚到Ch6，放弃Ch7所有进度
请选择（A/B）：
选项 A - 删除重来（推荐）：
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" cleanup --chapter {N}
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" clear
选项 B - Git 回滚：
git reset --hard ch{N-1:04d}
python "${CLAUDE_PLUGIN_ROOT}/scripts/workflow_manager.py" clear
如用户选择立即继续：
/{original_command} {original_args}
恢复选项：
A) 重新执行双章审查（成本：~$0.15）⚠️
B) 跳过审查，继续下一章（可后续补审）
⚠️ state.json 可能部分更新
A) 检查并修复 state.json
B) 回滚到上一章（安全）
⚠️ 中断已超过1小时
上下文丢失风险高
建议重新开始而非续写
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.
Reviews chapter quality using 5 specialized checkers and generates comprehensive reports. Activates when user requests chapter review or /webnovel-review.