KS
Killer-Skills

novel-indexing-and-searching — how to use novel-indexing-and-searching how to use novel-indexing-and-searching, novel-indexing-and-searching setup guide, novel-indexing-and-searching vs traditional search methods, novel-indexing-and-searching install, what is novel-indexing-and-searching, novel-indexing-and-searching alternative solutions, novel-indexing-and-searching for AI agents, novel-indexing-and-searching workflow optimization, novel-indexing-and-searching file search efficiency

v1.0.0
GitHub

About this Skill

Perfect for Development Agents needing efficient file retrieval and indexing capabilities in large projects. novel-indexing-and-searching is a skill that enables efficient file search and retrieval through indexing and caching, using stable IDs and table structures.

Features

Generates indexes using Python scripts in the `.codex/skills/novel-indexing-and-searching/scripts` directory
Utilizes stable IDs for entities, such as `char-中文名` and `loc-中文名`, for reliable referencing
Supports table structures in `open-threads.md` and `timeline.md` for easy parsing
Creates derived caches in the `WORKDIR/_data` directory for fast access
Allows for rebuilding indexes at any time, prohibiting manual modifications

# Core Topics

chen893 chen893
[0]
[0]
Updated: 3/1/2026

Quality Score

Top 5%
30
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add chen893/--skill/novel-indexing-and-searching

Agent Capability Analysis

The novel-indexing-and-searching MCP Server by chen893 is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use novel-indexing-and-searching, novel-indexing-and-searching setup guide, novel-indexing-and-searching vs traditional search methods.

Ideal Agent Persona

Perfect for Development Agents needing efficient file retrieval and indexing capabilities in large projects.

Core Value

Empowers agents to precisely locate and retrieve files using stable IDs and indexed caches, leveraging Python scripts for seamless integration with project workflows, particularly in managing entities and events through `char-`, `loc-`, `fac-`, `item-`, and `sys-` prefixed IDs.

Capabilities Granted for novel-indexing-and-searching MCP Server

Indexing and searching large project files using stable IDs
Automating the generation and update of indexed caches for efficient file retrieval
Streamlining development workflows by quickly locating specific lines within files

! Prerequisites & Limits

  • Requires Python environment for script execution
  • Dependent on specific directory structure and file naming conventions
  • Manual editing of indexed caches is prohibited
Project
SKILL.md
1.4 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

索引与检索(novel-indexing-and-searching)

目标

  • 先检索、再打开文件:把“回读整书”变成“精准定位到行”。
  • 索引是派生缓存:写到 WORKDIR/_data/**,可随时重建,禁止手改(WORKDIR 为工作区目录名,默认 novel)。

核心约定(让索引靠谱)

  • 关键实体使用稳定 ID(禁止用拼音做 ID):
    • 实体:char-中文名/loc-中文名/fac-中文名/item-中文名/sys-中文名
    • 线索/事件:thr-####/evt-####
    • bible 文件名通常为:char-林瑶.md/loc-旧镇.md/fac-青竹会.md
  • open-threads.mdtimeline.md 尽量保持表格结构(便于解析)

最短路径工作流

1) 生成/更新索引

在项目根目录执行:

bash
1python .codex/skills/novel-indexing-and-searching/scripts/build_index.py --root .

输出写入:

  • WORKDIR/_data/entities.json
  • WORKDIR/_data/chapter_index.json
  • WORKDIR/_data/threads.json
  • WORKDIR/_data/timeline.json

2) 执行检索

在项目根目录执行:

bash
1python .codex/skills/novel-indexing-and-searching/scripts/search.py --root . --query "thr-0007"

常用技巧:

  • 优先搜 ID(最稳定),其次搜专名(次稳定),最后才搜泛关键词
  • 先在 summaries/continuity/ 搜,再回到 draft/ 精准回读正文
  • 若工作区目录名不是 novel:两条命令都加 --novel-dir WORKDIR

Related Skills

Looking for an alternative to novel-indexing-and-searching or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication