zenstory-ai/oh-story-claudecode / skills/story-setup
story-setup
Flagged网文写作工具集基础设施部署与检查。为 Claude Code / OpenCode / Codex / Google Antigravity / ZCode / OpenClaw / Reasonix 提供内置适配;Web AI / 通用 Agent 可走 skills + AGENTS.md 文件模式。触发方式:/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」「检查写作环境」。
references/templates/rules/story-consistency.md
View on GitHub---
paths:
- "**/设定/**"
- "**/大纲/**"
- "**/追踪/**"
---
# Story Consistency Rules
修改设定、大纲、追踪时遵守以下规则。
## Rules
1. **设定变更必须检查追踪/**:修改任何角色设定或世界规则时,必须运行 `tracking_commit.js check`,确认 `_tracking-state.json` 与全部自动生成的追踪文件一致,再核对伏笔当前表、相关角色快照,以及作者/读者时间线,确保变更不会制造冲突或提前泄露。
2. **新增主要角色必须独立建档**:每个主要角色应有独立的设定文件,并更新关系.md(如果存在)。
3. **时间线变更必须走事务**:如果修改涉及时间顺序、客观事实或读者认知,必须在对应章的 `mode=revision` 事务中更新事件;由工具统一生成 `作者真相.md` 与 `读者已知.md`。
4. **设定变更只提交一次语义事务**:永久生效的裁定写入事务的 `delta.constraints` 与当前完整 `context.long_term_constraints`;下一章必须兑现的写入 `delta.next_chapter_commitments`。工具负责生成紧凑增量和续写状态卡(固定 7 栏)。不得直接编辑 `逐章记录/`、`上下文.md`、角色快照、伏笔表、时间线视图或摘要。
5. **一致性检查必须用 grep**:搜索已有记录核对。常用命令:
- 角色属性:`grep -rn "角色名" 设定/ 正文/ | grep "属性关键词"`
- 时间线:`grep -rn "第.*天\|.*日后\|过了.*时" 正文/`,再对照 `追踪/时间线/作者真相.md` 与 `读者已知.md`
- 力量体系:`grep -rn "体系关键词" 设定/ 正文/`
- 伏笔状态:`grep -rn "F[0-9]" 追踪/伏笔.md`
## Examples
### Correct
```
修订 demo 第 10 章“专业团队拍得还不如他拍得好?”后:
1. 检查 F027、江晨快照以及第 10 章相关时间线事件
2. 构造第 10 章 `mode=revision` 事务,保留“专业重拍版缺了灵魂、张耀祖决定继续用手机原版”的正文事实
3. 作者真相可保留钟嘉嘉未公开的培养安排;读者视图只保留看片会已经揭示的结论
4. 提交后运行 `tracking_commit.js check`,确认逐章增量、角色快照、伏笔与双时间线视图一致
```
### Wrong
```
直接在 `伏笔.md` 末尾追加第二条 F027,并分别手改 `作者真相.md`、`读者已知.md` 和 `上下文.md`。
结果:同一伏笔出现多个“当前状态”,读者视图泄露钟嘉嘉的未公开安排,检查点却无法知道哪些生成的追踪文件已经失效。
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |