agentsclimarketplace

Context weaver

Skill Huo0077/novel-qa-pipeline/context-weaver

上下文编织器。自动追踪小说三条线——伏笔、角色状态、世界观规则——在写前编织上下文摘要、在写后自动更新思维导图。与novel-dna协作。From its SKILL.md

Install
npx -y skills add Huo0077/novel-qa-pipeline --skill context-weaver

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.2 KB, 991 tokens by cl100k_base, as published. Nobody here has run it

Context Weaver — 上下文编织器

Iron Law

  • 写前必须编织上下文:每章写作前必须执行 /mindmap-read,不可跳过
  • 写后必须更新思维导图:每章完成后必须依次执行 update → scan → diff → check
  • 思维导图是唯一事实来源:所有角色状态、伏笔、规则以 .mindmap/ 为准

命令入口

命令说明触发时机
/mindmap-init初始化思维导图数据层开书时(一次)
/mindmap-read读思维导图,编织写前上下文摘要写前(自动)
/mindmap-update扫描章节,更新思维导图写后(自动)
/foreshadow-scan扫描章节中的伏笔(新埋/回收/过期)写后(自动)
/snapshot-save保存角色状态快照写后(自动)
/snapshot-diff角色状态快照对比,检测异常变化写后(自动)
/rule-check检测本章是否违反世界观硬规则写后(自动)

工作流

开书 → /mindmap-init(一次性)
     ↓
每章循环:
  /mindmap-read → [写作] → /mindmap-update → /foreshadow-scan → /snapshot-save → /snapshot-diff → /rule-check

工具脚本

所有工具位于 tools/ 目录,Python 3 标准库,零外部依赖。

# 初始化思维导图
python tools/mindmap_write.py init --project-root <项目目录>

# 写前编织上下文
python tools/mindmap_read.py weave --project-root <项目目录> --chapter <N> --characters <角色列表>

# 写后更新思维导图
python tools/mindmap_write.py update --project-root <项目目录> --chapter-file <章节文件>

# 伏笔扫描
python tools/foreshadow_scan.py --project-root <项目目录> --chapter-file <章节文件>

# 角色快照
python tools/snapshot_diff.py save --project-root <项目目录> --chapter <N> --characters <角色列表>
python tools/snapshot_diff.py diff --project-root <项目目录> --chapter <N>

# 规则检查
python tools/rule_check.py --project-root <项目目录> --chapter-file <章节文件>

思维导图结构 (.mindmap/)

.mindmap/
├── index.json              # 总索引(标题、题材、章节数)
├── timeline.json           # 时间线(每章:标题、地点、摘要)
├── characters/
│   ├── index.json          # 角色列表
│   └── <角色名>.json       # 角色详情(状态、关系、DNA、成长弧)
├── events.json             # 关键事件(含伏笔状态)
└── world-rules.json        # 世界观硬规则

状态文件 (.context-weaver/)

.context-weaver/
├── weaver-state.json         # 编织器状态
├── foreshadows/
│   ├── active/               # 进行中的伏笔
│   ├── resolved/             # 已回收的伏笔
│   └── abandoned/            # 废弃的伏笔
├── chapter-summaries/        # 章节摘要
└── character-snapshots/      # 角色快照

What ships with it: 7 files

29.9 KB alongside SKILL.md, 7 of them executable

tools/

Keep looking

Skills are one crate of 326,452. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.