xiaoyangy/novel-studio/novel-pipeline
Claude Code and agent skill by xiaoyangy/novel-studio
- community
Checking that the SKILL.md file is still in the repository.
把各功能串成一条可恢复的流水线:(共创→)写作→评审→重写→交付,按阶段执行、断点续跑。触发:「一条龙写完整本书」「从头跑完整个流程」「中断后接着跑」,想要无人值守端到端、且能中断恢复时使用。
Install
npx vskill@latest install xiaoyangy/novel-studio/novel-pipelineSKILL.md
novel-pipeline:可恢复流水线
按阶段顺序跑完整流程,状态存 output/novel/meta/pipeline.json,已完成的阶段重跑时自动跳过, 从断点继续。流水线只做阶段编排;每个阶段复用对应子命令逻辑,阶段内部还有更细的恢复 (write 走 checkpoint、review/rewrite 按章号),两层恢复叠加。
阶段
cocreate(可选,多轮澄清)→ write(创作)→ review(评审)→ rewrite(重写)→ deliver(交付沉淀:推进台账 + RAG 事实入库 + 交付快照)
默认序列:write,review,rewrite,deliver(假设已有创作指令)。
前置条件
- 已完成首次配置(见
skills/README.md),LLM 可用(先novel-check)。 - 含
cocreate阶段时需要交互终端。
执行
参数
| 参数 | 默认 | 说明 | |
|---|---|---|---|
--prompt <text> / --prompt-file <path> | — | 创作指令(write 阶段用;- 表示 stdin) | |
--stages a,b,c | write,review,rewrite,deliver | 阶段子集与顺序 | |
--write-to <n> | 0 | write 阶段写到指定章节后暂停;0 表示写到全书完结 | |
--from <n> / --to <n> | 0 | review / rewrite 阶段章号范围 | |
--budget <dur> | 阶段默认 | review / rewrite 阶段每章 LLM 调用预算 | |
--role <name> | writer | rewrite 阶段模型角色 | |
--restart | 关 | 清空已保存状态,从头重跑 |
恢复语义
- 每个阶段成功返回后还要通过证据校验,才写入
pipeline.json的completed与evidence;失败或证据不足的阶段不标记完成,下次重跑从它继续 write阶段:本书已完结则跳过;已有进度则恢复创作;全新项目用创作指令起新书- 已标记完成的阶段重跑时会先复核证据;若产物被删或 checkpoint 缺失,会清掉完成标记并重跑该阶段
- 证据口径:
write看progress.phase=complete、章节文件和commit_chaptercheckpoint;review看reviews/*.md与meta/review-summary.md;rewrite看章节文件和.pre-rewrite.md备份;deliver看meta/delivery_log.jsonl/meta/delivery_log.md novel-studio --diag会只读报告meta/pipeline.json的证据漂移;真正清标记和重跑只发生在再次执行--pipeline时- 改了
--stages列表会重置进度(保留已捕获的创作指令) - 状态文件用临时文件 + rename 原子写入,写一半崩溃不损坏
--headless --prompt、--review-existing、--rewrite-existing只保留为兼容别名,新任务应直接调用--pipeline
长期资产
流水线过程中会持续读写 meta/writing_assets.json、book_world.json、meta/resource_ledger.json 和 meta/rag/*。这些文件是可编辑、可复用的创作资产;不要把写法、世界观或资源状态只写在 一次性 prompt 里。
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/novel-pipeline/SKILL.md
Popularity
- Repository stars
- 19
- 7-day trend score
- 15
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/xiaoyangy/novel-studio/novel-pipeline)