Loading...
Loading...
Compare original and translation side by side
/write📋 写作前检查清单（必须完成）：
✓ 1. memory/constitution.md - 创作宪法
✓ 2. memory/style-reference.md - 风格参考（如有）
✓ 3. stories/_/specification.md - 故事规格
✓ 4. stories/_/creative-plan.md - 创作计划
✓ 5. stories/\*/tasks.md - 当前任务
✓ 6. spec/tracking/character-state.json - 角色状态
✓ 7. spec/tracking/relationships.json - 关系网络
✓ 8. spec/tracking/plot-tracker.json - 情节追踪（如有）
✓ 9. spec/tracking/validation-rules.json - 验证规则（如有）
📊 上下文加载状态：✅ 完成/write📋 Mandatory Pre-Writing Checklist (Must Complete):
✓ 1. memory/constitution.md - Writing Constitution
✓ 2. memory/style-reference.md - Style Reference (if applicable)
✓ 3. stories/_/specification.md - Story Specification
✓ 4. stories/_/creative-plan.md - Creative Plan
✓ 5. stories/\*/tasks.md - Current Tasks
✓ 6. spec/tracking/character-state.json - Character State
✓ 7. spec/tracking/relationships.json - Relationship Network
✓ 8. spec/tracking/plot-tracker.json - Plot Tracker (if applicable)
✓ 9. spec/tracking/validation-rules.json - Validation Rules (if applicable)
📊 Context Loading Status: ✅ Completed/write/write用户: /write 第10章
↓
[pre-write-checklist 自动激活]
↓
步骤1：读取 memory/constitution.md
步骤2：读取 memory/style-reference.md（如有）
步骤3：读取 stories/*/specification.md
步骤4：读取 stories/*/creative-plan.md
步骤5：读取 stories/*/tasks.md
步骤6：读取 spec/tracking/character-state.json
步骤7：读取 spec/tracking/relationships.json
步骤8：读取 spec/tracking/plot-tracker.json（如有）
步骤9：读取 spec/tracking/validation-rules.json（如有）
↓
输出确认：
📋 写作前检查清单（已完成）：
✓ 1-9 所有文件已读取
📊 上下文加载状态：✅ 完成
关键信息摘要：
- 创作原则：[从constitution提取]
- 当前任务：[从tasks.md提取]
- 主要角色：[从character-state提取]
- 情节进度：[从plot-tracker提取]
↓
开始写作第10章...User: /write Chapter 10
↓
[pre-write-checklist activates automatically]
↓
Step 1: Read memory/constitution.md
Step 2: Read memory/style-reference.md (if exists)
Step 3: Read stories/*/specification.md
Step 4: Read stories/*/creative-plan.md
Step 5: Read stories/*/tasks.md
Step 6: Read spec/tracking/character-state.json
Step 7: Read spec/tracking/relationships.json
Step 8: Read spec/tracking/plot-tracker.json (if exists)
Step 9: Read spec/tracking/validation-rules.json (if exists)
↓
Output Confirmation:
📋 Mandatory Pre-Writing Checklist (Completed):
✓ All 9 files have been read
📊 Context Loading Status: ✅ Completed
Key Information Summary:
- Writing Principles: [Extracted from constitution]
- Current Tasks: [Extracted from tasks.md]
- Main Characters: [Extracted from character-state]
- Plot Progress: [Extracted from plot-tracker]
↓
Start writing Chapter 10...📋 写作前检查清单（已完成）：
✓ 1. memory/constitution.md - 创作宪法
→ 核心原则：[列出2-3条关键原则]
✓ 2. memory/style-reference.md - 风格参考
→ 风格要点：[提取关键风格要求]
✓ 3. stories/xxx/specification.md - 故事规格
→ 故事类型：[言情/悬疑/历史等]
→ P0元素：[必须包含的元素]
✓ 4. stories/xxx/creative-plan.md - 创作计划
→ 当前阶段：[第X卷/第X章]
→ 本章目标：[情节/情感目标]
✓ 5. stories/xxx/tasks.md - 当前任务
→ 待写章节：[第X章]
→ 任务状态：[pending/in_progress]
✓ 6. spec/tracking/character-state.json - 角色状态
→ 主要角色：[列出角色名和当前状态]
✓ 7. spec/tracking/relationships.json - 关系网络
→ 核心关系：[主角与谁的关系变化]
✓ 8. spec/tracking/plot-tracker.json - 情节追踪
→ 活跃线索：[当前进行中的情节线]
✓ 9. spec/tracking/validation-rules.json - 验证规则
→ 自动修复：[启用/禁用]
📊 上下文加载状态：✅ 完成（加载9个文件，约XXXX tokens）
🎯 准备写作第X章...📋 Mandatory Pre-Writing Checklist (Completed):
✓ 1. memory/constitution.md - Writing Constitution
→ Core Principles: [List 2-3 key principles]
✓ 2. memory/style-reference.md - Style Reference
→ Style Key Points: [Extract key style requirements]
✓ 3. stories/xxx/specification.md - Story Specification
→ Story Genre: [Romance/Suspense/History, etc.]
→ P0 Elements: [Mandatory elements to include]
✓ 4. stories/xxx/creative-plan.md - Creative Plan
→ Current Phase: [Volume X/Chapter X]
→ Chapter Goal: [Plot/Emotional Goal]
✓ 5. stories/xxx/tasks.md - Current Tasks
→ Chapter to Write: [Chapter X]
→ Task Status: [pending/in_progress]
✓ 6. spec/tracking/character-state.json - Character State
→ Main Characters: [List character names and current states]
✓ 7. spec/tracking/relationships.json - Relationship Network
→ Core Relationships: [Relationship changes between protagonist and others]
✓ 8. spec/tracking/plot-tracker.json - Plot Tracker
→ Active Plot Threads: [Current ongoing plot lines]
✓ 9. spec/tracking/validation-rules.json - Validation Rules
→ Auto-Fix: [Enabled/Disabled]
📊 Context Loading Status: ✅ Completed (Loaded 9 files, approximately XXXX tokens)
🎯 Ready to write Chapter X...📋 写作前检查清单（部分完成）：
✓ 1. memory/constitution.md - 创作宪法
✓ 2. ⚠️ memory/style-reference.md - 不存在（可选文件，跳过）
✓ 3. stories/xxx/specification.md - 故事规格
✓ 4. stories/xxx/creative-plan.md - 创作计划
✓ 5. stories/xxx/tasks.md - 当前任务
✓ 6. spec/tracking/character-state.json - 角色状态
✓ 7. spec/tracking/relationships.json - 关系网络
✓ 8. ⚠️ spec/tracking/plot-tracker.json - 不存在（可选文件，跳过）
✓ 9. ⚠️ spec/tracking/validation-rules.json - 不存在（可选文件，跳过）
📊 上下文加载状态：✅ 完成（加载6个必须文件 + 0个可选文件）
💡 建议：运行 `/track-init` 初始化完整追踪系统📋 Mandatory Pre-Writing Checklist (Partially Completed):
✓ 1. memory/constitution.md - Writing Constitution
✓ 2. ⚠️ memory/style-reference.md - Does not exist (optional file, skipped)
✓ 3. stories/xxx/specification.md - Story Specification
✓ 4. stories/xxx/creative-plan.md - Creative Plan
✓ 5. stories/xxx/tasks.md - Current Tasks
✓ 6. spec/tracking/character-state.json - Character State
✓ 7. spec/tracking/relationships.json - Relationship Network
✓ 8. ⚠️ spec/tracking/plot-tracker.json - Does not exist (optional file, skipped)
✓ 9. ⚠️ spec/tracking/validation-rules.json - Does not exist (optional file, skipped)
📊 Context Loading Status: ✅ Completed (Loaded 6 mandatory files + 0 optional files)
💡 Recommendation: Run `/track-init` to initialize the complete tracking system📋 写作前检查清单（失败）：
✓ 1. memory/constitution.md - 创作宪法
✓ 2. memory/style-reference.md - 风格参考
❌ 3. stories/xxx/specification.md - **文件不存在**
❌ 4. stories/xxx/creative-plan.md - **文件不存在**
❌ 5. stories/xxx/tasks.md - **文件不存在**
⛔ 错误：缺少必需文件，无法继续写作
必须先完成：
1. 运行 `/constitution` 创建创作宪法
2. 运行 `/specify` 定义故事规格
3. 运行 `/plan` 制定创作计划
4. 运行 `/tasks` 分解任务清单
然后才能执行 `/write`
这是seven-step methodology的推荐流程。📋 Mandatory Pre-Writing Checklist (Failed):
✓ 1. memory/constitution.md - Writing Constitution
✓ 2. memory/style-reference.md - Style Reference
❌ 3. stories/xxx/specification.md - **File does not exist**
❌ 4. stories/xxx/creative-plan.md - **File does not exist**
❌ 5. stories/xxx/tasks.md - **File does not exist**
⛔ Error: Missing mandatory files, cannot continue writing
Must complete the following first:
1. Run `/constitution` to create a Writing Constitution
2. Run `/specify` to define story specifications
3. Run `/plan` to develop a creative plan
4. Run `/tasks` to break down the task list
Then you can execute `/write`
This is the recommended workflow of the seven-step methodology./write/write执行顺序：
1. pre-write-checklist（本Skill）→ 读取所有文件
2. 输出确认报告
3. 检查setting-detector → 是否需要激活知识库
4. 开始实际写作Execution Order:
1. pre-write-checklist (this Skill) → Read all files
2. Output confirmation report
3. Check setting-detector → Whether to activate knowledge base
4. Start actual writing/analyze/analyze分析前先确保context完整：
1. pre-write-checklist → 重新加载所有文件
2. 基于最新状态执行分析Ensure complete context before analysis:
1. pre-write-checklist → Reload all files
2. Execute analysis based on the latest status/track/track更新流程：
1. 用户修改tracking文件
2. 运行 `/track` 更新
3. pre-write-checklist → 重新读取验证Update Workflow:
1. User modifies tracking files
2. Run `/track` to update
3. pre-write-checklist → Re-read and validate1. memory/constitution.md - 创作原则
3. stories/*/specification.md - 故事规格
4. stories/*/creative-plan.md - 创作计划
5. stories/*/tasks.md - 当前任务
6. spec/tracking/character-state.json - 角色状态
7. spec/tracking/relationships.json - 关系网络1. memory/constitution.md - Writing Principles
3. stories/*/specification.md - Story Specifications
4. stories/*/creative-plan.md - Creative Plan
5. stories/*/tasks.md - Current Tasks
6. spec/tracking/character-state.json - Character State
7. spec/tracking/relationships.json - Relationship Network2. memory/style-reference.md - 风格参考
8. spec/tracking/plot-tracker.json - 情节追踪
9. spec/tracking/validation-rules.json - 验证规则2. memory/style-reference.md - Style Reference
8. spec/tracking/plot-tracker.json - Plot Tracker
9. spec/tracking/validation-rules.json - Validation Rules第1章写作：
- AI记得所有设定
- 质量很好
第10章写作：
- 对话已经很长
- AI开始遗忘第1章的设定
第30章写作：
- 完全忘记早期设定
- 角色性格走样
- 情节自相矛盾Writing Chapter 1:
- AI remembers all settings
- High quality
Writing Chapter 10:
- Conversation has become very long
- AI starts to forget Chapter 1 settings
Writing Chapter 30:
- Completely forgets early settings
- Character personalities deviate
- Plot contradicts itself每次写作前：
- 强制重读所有核心文件
- 重新加载完整context
- 像写第1章一样对待第30章
结果：
- 第30章质量 ≈ 第1章质量
- 一致性保持
- 不再失焦Before each writing session:
- Mandatory re-reading of all core files
- Reload complete context
- Treat Chapter 30 like Chapter 1
Results:
- Quality of Chapter 30 ≈ Quality of Chapter 1
- Consistency maintained
- No more focus degradation| 对比维度 | 无检查清单 | 有检查清单 |
|---|---|---|
| 第1-10章 | ✓ 质量好 | ✓ 质量好 |
| 第11-30章 | ⚠️ 开始不稳定 | ✓ 保持稳定 |
| 第31-50章 | ❌ 明显失焦 | ✓ 依然稳定 |
| 第51+章 | ❌ 严重失焦 | ✓ 长期稳定 |
| Comparison Dimension | Without Checklist | With Checklist |
|---|---|---|
| Chapters 1-10 | ✓ High quality | ✓ High quality |
| Chapters 11-30 | ⚠️ Starts to be unstable | ✓ Remains stable |
| Chapters 31-50 | ❌ Obvious focus degradation | ✓ Still stable |
| Chapters 51+ | ❌ Severe focus degradation | ✓ Long-term stability |
"使用严格检查清单模式"
→ 缺少必需文件则阻止写作"使用宽松检查清单模式"
→ 允许跳过部分文件（不推荐，可能失焦）"Use strict checklist mode"
→ Blocks writing if mandatory files are missing"Use lenient checklist mode"
→ Allows skipping some files (not recommended, may cause focus degradation)"检查清单请额外包含：
- spec/knowledge/worldbuilding/magic-system.md
- spec/knowledge/characters/protagonist-profile.md""Please add the following to the checklist:
- spec/knowledge/worldbuilding/magic-system.md
- spec/knowledge/characters/protagonist-profile.md"每次写作的额外token成本：
9个文件读取：
- constitution.md：~200 tokens
- specification.md：~500 tokens
- creative-plan.md：~300 tokens
- tasks.md：~150 tokens
- character-state.json：~200 tokens
- relationships.json：~150 tokens
- 其他：~200 tokens
总计：约1700 tokens/次写作
收益：
- 避免失焦导致的重写（节省数万tokens）
- 保持质量一致（用户满意度）
- 长篇项目的可持续性Additional token cost per writing session:
Reading 9 files:
- constitution.md: ~200 tokens
- specification.md: ~500 tokens
- creative-plan.md: ~300 tokens
- tasks.md: ~150 tokens
- character-state.json: ~200 tokens
- relationships.json: ~150 tokens
- Others: ~200 tokens
Total: Approximately 1700 tokens per writing session
Benefits:
- Avoids rewrites caused by focus degradation (saves tens of thousands of tokens)
- Maintains consistent quality (user satisfaction)
- Sustainability of long-form projects同一写作会话中：
第1次写作：读取所有文件（1700 tokens）
第2次写作（1小时内）：检查文件是否修改
- 未修改：使用缓存（0 tokens）
- 已修改：重新读取（部分tokens）Within the same writing session:
1st writing: Read all files (1700 tokens)
2nd writing (within 1 hour): Check if files have been modified
- Not modified: Use cache (0 tokens)
- Modified: Re-read (partial tokens)"跳过检查清单，直接写作"
→ AI会警告："不推荐，可能导致失焦"
→ 但会尊重你的选择"Skip checklist and write directly"
→ AI will warn: "Not recommended, may cause focus degradation"
→ But will respect your choicepre-write-checklist：
- 加载项目特定文件（你的故事数据）
setting-detector：
- 加载通用知识库（类型惯例、写作技巧）
两者结合 = 完整context：
你的故事设定 + 类型专业知识pre-write-checklist:
- Loads project-specific files (your story data)
setting-detector:
- Loads general knowledge bases (genre conventions, writing techniques)
Combined = Complete context:
Your story settings + genre expertise长篇小说的挑战：
- 设定更复杂
- 角色更多
- 情节线更多
- AI更容易忘记
检查清单的作用：
- 确保第100章和第1章质量一致
- 防止角色性格突变
- 防止情节自相矛盾
这是长篇小说质量保证的基石。Challenges of long novels:
- More complex settings
- More characters
- More plot threads
- AI is more likely to forget
Role of the checklist:
- Ensures Chapter 100 has the same quality as Chapter 1
- Prevents sudden character personality changes
- Prevents plot contradictions
This is the cornerstone of quality assurance for long novels.✓ 角色状态变化 → 更新 character-state.json
✓ 关系变化 → 更新 relationships.json
✓ 新情节线 → 更新 plot-tracker.json✓ Character state changes → Update character-state.json
✓ Relationship changes → Update relationships.json
✓ New plot threads → Update plot-tracker.json/track/track建议频率：每5-10章运行一次 `/track`
作用：
- 更新tracking文件
- 验证一致性
- 发现潜在问题Recommended frequency: Run `/track` every 5-10 chapters
Purpose:
- Update tracking files
- Validate consistency
- Detect potential issues如果你手动修改了关键文件：
"请重新执行检查清单，重新加载所有文件"
确保AI看到最新状态。If you manually modify key files:
"Please re-execute the checklist to reload all files"
Ensure the AI sees the latest status.pre-write-checklist（写前）：
- 加载所有context
- 准备写作
consistency-checker（写中/写后）：
- 监控一致性
- 发现矛盾pre-write-checklist (before writing):
- Loads all context
- Prepares for writing
consistency-checker (during/after writing):
- Monitors consistency
- Detects contradictions优先级排序（重要的先读）：
1. constitution（最高原则）
2. specification（故事核心）
3. creative-plan（技术方案）
4. tasks（当前任务）
5. character-state（角色数据）
6. relationships（关系数据）
7. plot-tracker（情节追踪）
8. validation-rules（验证规则）
9. style-reference（风格参考）Priority Order (Most Important First):
1. constitution (highest principles)
2. specification (story core)
3. creative-plan (technical plan)
4. tasks (current tasks)
5. character-state (character data)
6. relationships (relationship data)
7. plot-tracker (plot tracking)
8. validation-rules (validation rules)
9. style-reference (style reference)文件不存在：
→ 必需文件：阻止写作，提示创建
→ 可选文件：警告，允许继续
文件格式错误：
→ JSON解析失败：显示错误，建议修复
→ Markdown格式问题：尽力读取，标记问题
文件过大：
→ 超过10000行：警告（可能影响性能）
→ 建议拆分文件File does not exist:
→ Mandatory files: Blocks writing, prompts creation
→ Optional files: Warns, allows continuation
File format error:
→ JSON parsing failed: Display error, recommend fixing
→ Markdown format issue: Try to read as much as possible, mark the problem
File too large:
→ Exceeds 10000 lines: Warns (may affect performance)
→ Recommend splitting the file