knowledge-management

# Knowledge Management Skill (Local Storage)

Organize your OpenClaw memory files into a structured local knowledge base. Automatically parses `MEMORY.md` and daily memory files, classifies entries by content type, and stores each as a timestamped markdown file in the appropriate folder.

## Available Tools

### Core Commands
- `km sync [options]` - Sync memory entries to local files
- `km classify [options]` - Parse and classify without storing (JSON output)
- `km summarize [options]` - Generate index files for each content type
- `km cleanup [options]` - Remove orphaned files
- `km list_types` - List all available content types

## Setup

No API keys needed! The skill uses two locations:

- **Input Workspace**: Where `MEMORY.md` and `memory/` daily files are read from.
- **Output Directory**: Where organized folders (`Research/`, `Decision/`, etc.) are written.

Both are detected automatically:

### Input Workspace (source files)
1. `OPENCLAWORKSPACE` environment variable
2. `--workspace <path>` CLI argument
3. Current working directory (if it contains `MEMORY.md`)
4. Default: `~/.openclaw/workspace`

### Output Directory (organized files)
1. `--output-dir <path>` CLI argument (relative to workspace or absolute)
2. Default: `<workspace>/memory/KM`

The skill will create the output directory and all content-type folders automatically.

If you want to pre-create:
```bash
mkdir -p ~/.openclaw/workspace/memory/KM/{Research,Decision,Insight,Lesson,Pattern,Project,Reference,Tutorial}
```

## Usage Examples

### Default locations (input at workspace root, output in memory/KM)
```bash
# From any directory (workspace auto-detected)
km sync --days_back 7 --cleanup
```

### Custom input workspace and output directory
```bash
km sync --workspace /custom/input/workspace --output-dir /custom/output/KM --days_back 7
```

### Using environment variables
```bash
export OPENCLAWORKSPACE=/custom/input/workspace
km sync --output-dir /custom/output/KM --days_back 7
```

### Dry run (p...

# Knowledge Management Skill (Local Storage)

Organize your OpenClaw memory files into a structured local knowledge base. Automatically parses `MEMORY.md` and daily memory files, classifies entries by content type, and stores each as a timestamped markdown file in the appropriate folder.

## Setup

No API keys needed! Just ensure your workspace structure exists:

```bash
mkdir -p ~/.openclaw/workspace/{Research,Decision,Insight,Lesson,Pattern,Project,Reference,Tutorial}
```

The skill will create folders automatically if missing.

## Tools

### `km sync`
Extract and store knowledge entries as markdown files.

**Options:**
- `--days_back <num>` (default: 7) — Include N days of daily files
- `--dry_run` — Preview without creating files
- `--limit <num>` — Max entries to process
- `--cleanup` — Delete orphan files (files in folders but not tracked in state)
- `--verbose` — Detailed logs

**Example:**
```bash
km sync --days_back 14 --dry_run
km sync --days_back 7 --cleanup
```

### `km classify`
Parse and classify entries without storing. Outputs JSON with full metadata.

**Options:**
- `--days_back <num>` (default: 0) — 0 = only MEMORY.md, otherwise include daily files

**Example:**
```bash
km classify --days_back 3 > entries.json
```

### `km summarize`
Create index files listing all entries in each content type folder.

**Options:**
- `--output_dir <path>` — Where to write index files (default: workspace root)

**Example:**
```bash
km summarize --output_dir ~/.openclaw/workspace
```

### `km cleanup`
Remove orphaned files (files in content folders that are not tracked in the sync state).

**Options:**
- `--dry_run` — Preview what would be deleted

**Example:**
```bash
km cleanup --dry_run
km cleanup
```

### `km list_types`
List all available content types and their descriptions.

**Example:**
```bash
km list_types
```

## Storage Structure

```
~/.openclaw/workspace/
├── Research/
│   ├── 20260215T1448_OpenClaw_Optimization_Findings_e4b30e75.md
│   └── 20260215T1448...