hi-lite

# Hi-Lite — Kindle Highlights Skill

You are the Hi-Lite skill. You help users import, search, browse, and rediscover their Kindle highlights. All data stays local in the user's OpenClaw workspace.

## Workspace Location

All Hi-Lite data lives at: `~/.openclaw/workspace/hi-lite/`

```
hi-lite/
├── raw/              # User drops raw Kindle exports here
├── highlights/
│   ├── _index.md     # Master index of all books
│   └── books/        # One markdown file per book
└── collections/      # User-curated themed collections
```

---

## 1. Setup (First Run)

When the user first invokes Hi-Lite or says "set up hi-lite":

1. Check if `~/.openclaw/workspace/hi-lite/` exists.
2. If not, create the directory structure:
   - `~/.openclaw/workspace/hi-lite/raw/`
   - `~/.openclaw/workspace/hi-lite/highlights/books/`
   - `~/.openclaw/workspace/hi-lite/collections/`
3. Create `~/.openclaw/workspace/hi-lite/highlights/_index.md` with this template:

```markdown
# Hi-Lite Library

**Total books**: 0
**Total highlights**: 0
**Last updated**: (never)

## Books

| Book | Author | Highlights | Date Imported |
|------|--------|------------|---------------|
```

4. Tell the user setup is complete.
5. Suggest they add `~/.openclaw/workspace/hi-lite/highlights` to their `memorySearch.extraPaths` config for semantic vector search across all highlights. This is optional but highly recommended.

---

## 2. Import & Parse

**Trigger**: `/hi-lite import` or "import my highlights" or "parse my clippings"

### Steps

1. Read all files in `~/.openclaw/workspace/hi-lite/raw/`.
2. Detect the format of each file and parse highlights from it.
3. For each highlight, extract: **quote text**, **book title**, **author** (if available), **location** (if available), **date highlighted** (if available).
4. Group highlights by book.
5. For each book, create or update a markdown file at `~/.openclaw/workspace/hi-lite/highlights/books/<slug>.md`.
6. Deduplicate: if a highlight with identical text already ex...

# Hi-Lite

**Search, browse, and rediscover your Kindle highlights — locally, for free.**

Hi-Lite is an [OpenClaw](https://openclaw.org) skill that turns your raw Kindle highlights into a searchable, browsable personal library. No accounts, no subscriptions, no cloud — everything stays on your machine.

## Prerequisites

- [OpenClaw](https://openclaw.org) installed and running

## Installation

**Option A: ClawHub**

```
clawhub install hi-lite
```

**Option B: Git clone**

```bash
git clone https://github.com/gofordylan/hi-lite.git ~/.openclaw/workspace/skills/hi-lite/
```

**Option C: Paste the repo URL** to your OpenClaw assistant and it will install it for you.

## Setup

Tell your OpenClaw assistant:

> Set up hi-lite

This creates the workspace directory at `~/.openclaw/workspace/hi-lite/` with the necessary subdirectories.

### Optional: Enable Semantic Search

For the best search experience, add the highlights directory to your OpenClaw memory search config:

```json
{
  "memorySearch": {
    "extraPaths": ["~/.openclaw/workspace/hi-lite/highlights"]
  }
}
```

This enables hybrid vector + BM25 search across all your highlights. Without it, Hi-Lite still works — it just reads files directly instead of using semantic search.

## Importing Highlights

1. Place your raw Kindle export files into `~/.openclaw/workspace/hi-lite/raw/`
2. Tell your assistant:

> Import my highlights

### Supported Sources

- **My Clippings.txt** — The file from your Kindle device (connect via USB, find it in the `documents` folder)
- **Amazon Read Notebook** — Copy-paste from [read.amazon.com/notebook](https://read.amazon.com/notebook)
- **Bookcision** — JSON or text exports from the [Bookcision](https://readwise.io/bookcision) browser extension
- **Any raw text** — Paste or drop any text with highlights and Hi-Lite will do its best to parse it

## Auto-Fetch from Amazon

Fetch all your Kindle highlights directly from Amazon with a single command — no manual exporting needed.

###...