Yes. Add extra directories via `skills.load.extraDirs` in `~/.openclaw/openclaw.json` (lowest precedence). Default precedence is `<workspace>/skills` → `<workspace>/.agents/skills` → `~/.agents/skills` → `~/.openclaw/skills` → bundled → `skills.load.extraDirs`. `clawhub` installs into `./skills` by default, which OpenClaw treats as `<workspace>/skills` on the next session. If the skill should only be visible to certain agents, pair that with `agents.defaults.skills` or `agents.list[].skills`.

</Accordion>

<Accordion title="How can I use different models for different tasks?">

<Accordion title="How can I use different models or settings for different tasks?">

Today the supported patterns are:

- **Cron jobs**: isolated jobs can set a `model` override per job.

- **Sub-agents**: route tasks to separate agents with different default models.

- **Agents**: route tasks to separate agents with different default models, thinking levels, and stream params.

- **On-demand switch**: use `/model` to switch the current session model at any time.

See [Cron jobs](/automation/cron-jobs), [Multi-Agent Routing](/concepts/multi-agent), and [Slash commands](/tools/slash-commands).

For example, use the same model with different per-agent settings:

```json5

{

agents: {

list: [

{

id: "coder",

model: "xiaomi/mimo-v2.5-pro",

thinkingDefault: "high",

params: { temperature: 0.1 },

},

{

id: "chat",

model: "xiaomi/mimo-v2.5-pro",

thinkingDefault: "off",

params: { temperature: 0.8 },

},

],

},

}

```

Put shared per-model defaults in `agents.defaults.models["provider/model"].params`, then put agent-specific overrides in flat `agents.list[].params`. Do not define separate nested `agents.list[].models["provider/model"].params` entries for the same model; `agents.list[].models` is for per-agent model catalog and runtime overrides.

See [Cron jobs](/automation/cron-jobs), [Multi-Agent Routing](/concepts/multi-agent), [Configuration](/gateway/config-agents), and [Slash commands](/tools/slash-commands).

</Accordion>