# OpenClaw

### OpenClaw

OpenClaw is an autonomous AI agent framework with its own workspace and skills system. Tessl integrates with OpenClaw by installing skills directly into an agent workspace — no MCP configuration or rules files are used, to keep config clean.

### How skills work with OpenClaw

Tessl installs skills as symlinks into the `skills/` directory of your OpenClaw agent workspace. OpenClaw reads skills from this directory automatically.

Skills installed by Tessl are prefixed with `tessl__` so they can be identified and managed separately from your other skills, if necessary.

### Installing skills

Navigate to your agent workspace directory before running `tessl install`. A workspace is identified by the presence of a `.openclaw/workspace-state.json` file.

```bash
cd ~/.openclaw/workspace   # or whichever workspace you want to install into
tessl install tile-name
```

If you run `tessl install` from anywhere other than a workspace root, Tessl will exit with an error and suggest the correct directories to navigate to.

### Multiple agents

If you have more than one OpenClaw agent, run `tessl install` separately from each workspace:

```bash
cd ~/.openclaw/workspaces/agent1
tessl install tile-name

cd ~/.openclaw/workspaces/agent2
tessl install tile-name
```

### Installing for coding agents at the same time

If your OpenClaw agent uses coding agents (Claude Code, Codex, etc.), use the `--agent` flag to control which agents receive skills:

```bash
# Install for both OpenClaw and a coding agent
tessl install tile-name --agent openclaw --agent claude-code

# Install for a coding agent only, skip OpenClaw
tessl install tile-name --agent claude-code
```

With no `--agent` flag, Tessl auto-detects which agents are present in the workspace directory, and installs for all of them.

### Using tessl init

`tessl init` is not supported in OpenClaw workspaces. If you run it from a workspace root, Tessl will exit with an error and prompt you to run tessl install instead.