OpenClaw

eidolon-search

AI Agent memory search using SQLite FTS5. 90%+ token reduction (10x+) compared to reading full files. Use when the agent needs to search through markdown memory files, daily notes, or any text corpus efficiently. Triggers on memory search, file search, knowledge retrieval, or when context window is limited and full-file reading is too expensive.

dev-jslee0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install dev-jslee/eidolon-search

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Eidolon Search

FTS5-based memory search for AI Agents. Index markdown files once, search with 90%+ token savings.

Quick Start

1. Index memory files (once)

python3 scripts/build-index.py <memory_dir> <db_path>

Example:

python3 scripts/build-index.py ./memory ./memory.db

This creates a SQLite database with FTS5 full-text index of all .md files in the directory (recursive).

2. Search

python3 scripts/search.py <query> [limit] [db_path]

Example:

python3 scripts/search.py "Physical AI roadmap" 5
python3 scripts/search.py "project timeline" 10 ./memory.db

Default limit: 10. Default db_path: ./memory.db

Output: matching snippets with file paths and relevance scores.

3. Re-index when files change

Run build-index.py again. It rebuilds the index from scratch (fast, <1 second for typical workspaces).

When to Use

Memory search: Find specific information across many daily notes or memory files
Token-limited contexts: When reading all files would exceed context limits
Repeated searches: Index once, search many times
Large workspaces: 10+ markdown files with cumulative size >50KB

When NOT to Use

Single small file (<5KB): just read it directly
Need semantic/meaning-based search: FTS5 is keyword-based only
See references/QUALITY.md for known limitations

Search Tips for Agents

FTS5 is keyword-based. Improve results by:

Use specific terms: "Jetson Orin" not "hardware plans"
Use OR for synonyms: "car OR vehicle OR automobile"
Use quotes for phrases: "Physical AI"
Try multiple queries if first attempt returns nothing
Check file paths in results to read full context when needed

Benchmarks

Token savings: 90%+ (measured 93-98.9%)
Speed: 15x faster (measured 10-20x)
Details: references/PERFORMANCE.md

Run benchmarks yourself:

python3 scripts/benchmark-recall.py    # Recall@5, Reca...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/dev-jslee/eidolon-search
Version: —
Commit: 84983bfbec36f56d3e5a1643fce880d108579391
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Eidolon Search

FTS5-based memory search for AI Agents. Index markdown files once, search with 90%+ token savings.

## Quick Start

### 1. Index memory files (once)

```bash
python3 scripts/build-index.py <memory_dir> <db_path>
```

Example:
```bash
python3 scripts/build-index.py ./memory ./memory.db
```

This creates a SQLite database with FTS5 full-text index of all `.md` files in the directory (recursive).

### 2. Search

```bash
python3 scripts/search.py <query> [limit] [db_path]
```

Example:
```bash
python3 scripts/search.py "Physical AI roadmap" 5
python3 scripts/search.py "project timeline" 10 ./memory.db
```

Default limit: 10. Default db_path: `./memory.db`

Output: matching snippets with file paths and relevance scores.

### 3. Re-index when files change

Run `build-index.py` again. It rebuilds the index from scratch (fast, <1 second for typical workspaces).

## When to Use

- **Memory search**: Find specific information across many daily notes or memory files
- **Token-limited contexts**: When reading all files would exceed context limits
- **Repeated searches**: Index once, search many times
- **Large workspaces**: 10+ markdown files with cumulative size >50KB

## When NOT to Use

- Single small file (<5KB): just read it directly
- Need semantic/meaning-based search: FTS5 is keyword-based only
- See [references/QUALITY.md](references/QUALITY.md) for known limitations

## Search Tips for Agents

FTS5 is keyword-based. Improve results by:

- Use specific terms: "Jetson Orin" not "hardware plans"
- Use OR for synonyms: "car OR vehicle OR automobile"
- Use quotes for phrases: `"Physical AI"`
- Try multiple queries if first attempt returns nothing
- Check file paths in results to read full context when needed

## Benchmarks

- Token savings: 90%+ (measured 93-98.9%)
- Speed: 15x faster (measured 10-20x)
- Details: [references/PERFORMANCE.md](references/PERFORMANCE.md)

Run benchmarks yourself:
```bash
python3 scripts/benchmark-recall.py    # Recall@5, Reca...

搜索