// Robot management expert. ALWAYS invoke this skill when you need to list, create, update, or manage robots, check robot status, trigger robot executions, cancel tasks, or retrieve execution results. Use this skill before guessing robot APIs.
| name | yao-robot |
| description | Robot management expert. ALWAYS invoke this skill when you need to list, create, update, or manage robots, check robot status, trigger robot executions, cancel tasks, or retrieve execution results. Use this skill before guessing robot APIs. |
Ten tools for managing robots and their executions, called via bash.
List robots with summary info. Use robot_get for full details.
tai tool robot_list '{}'
tai tool robot_list '{"keywords": "weather", "page": 1, "pagesize": 10}'
| Parameter | Type | Required | Description |
|---|---|---|---|
team_id | string | no | Filter by team ID |
status | string | no | Filter by robot status |
keywords | string | no | Search in name/bio |
page | integer | no | Page number (default 1) |
pagesize | integer | no | Page size (default 20, max 100) |
Get full robot profile including config, agents, prompts.
tai tool robot_get '{"member_id": "rob-abc123"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
Create a new robot with profile and config.
tai tool robot_create '{"display_name": "Weather Bot", "bio": "Reports weather daily"}'
tai tool robot_create '{"display_name": "Code Reviewer", "system_prompt": "You review code", "agents": ["yao.agent-smith"]}'
| Parameter | Type | Required | Description |
|---|---|---|---|
display_name | string | yes | Robot display name |
bio | string | no | Robot description |
system_prompt | string | no | System prompt |
agents | array | no | Agent IDs the robot can use |
workspace | string | no | Workspace ID to bind |
autonomous_mode | boolean | no | Enable autonomous mode |
robot_config | object | no | See robot_config structure below |
Only these sub-fields are accepted (others are silently ignored for security):
| Sub-field | Type | Description |
|---|---|---|
identity | object | {role, duties[], rules[]} — role definition (role required) |
quota | object | {max, queue, priority} — concurrency limits |
clock | object | {mode, times[], days[], every, tz, timeout} — scheduling |
triggers | object | {clock: {enabled}, intervene: {enabled}, event: {enabled}} |
executor | object | {mode, max_duration} — execution mode (standard/dryrun/sandbox) |
default_locale | string | Default language, e.g. "en", "zh" |
Update robot profile or config fields. Only provided fields are changed.
Warning:
robot_configis a full replace, not a merge. If you only pass{"quota": {"max": 5}}, other sub-configs (identity, clock, etc.) will be cleared. Always pass the complete robot_config when updating.
tai tool robot_update '{"member_id": "rob-abc123", "bio": "Updated description"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
| Others | varies | no | Same as robot_create (optional) |
Check if robot is busy: running task count, available slots, last/next run times.
tai tool robot_status '{"member_id": "rob-abc123"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
List executions (tasks in progress or recent history).
tai tool robot_execution_list '{"member_id": "rob-abc123"}'
tai tool robot_execution_list '{"member_id": "rob-abc123", "status": "running"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
status | string | no | Filter: pending, running, paused, completed, failed, cancelled, confirming, waiting |
page | integer | no | Page number (default 1) |
pagesize | integer | no | Page size (default 20) |
Get execution details: goals, tasks, progress, errors.
tai tool robot_execution_get '{"member_id": "rob-abc123", "execution_id": "exec-xyz"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
execution_id | string | yes | Execution ID |
Trigger a new execution. Returns execution_id for tracking.
tai tool robot_execution_create '{"member_id": "rob-abc123", "messages": [{"role": "user", "content": "Generate report"}]}'
tai tool robot_execution_create '{"member_id": "rob-abc123", "trigger_type": "human"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
messages | array | no | Input messages (text/images) |
trigger_type | string | no | "human" or "event" (default human) |
Cancel a running execution.
tai tool robot_execution_cancel '{"member_id": "rob-abc123", "execution_id": "exec-xyz"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
execution_id | string | yes | Execution ID |
List completed executions with delivery outputs (reports, files).
tai tool robot_result_list '{"member_id": "rob-abc123"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
member_id | string | yes | Robot member ID |
page | integer | no | Page number (default 1) |
pagesize | integer | no | Page size (default 20) |
robot_list — discover available robotsrobot_get — get full details of a specific robotrobot_status — check if the robot has available slotsrobot_execution_create — trigger a task, get execution_idrobot_execution_get — poll execution progress using execution_idrobot_result_list — retrieve completed resultsrobot_list for discovery, robot_get for details (list returns summaries only)robot_status tells you if the robot is busy before triggeringrobot_execution_create, use the returned execution_id with robot_execution_get to track progressrobot_result_list only shows completed executions with outputsSecret management expert. ALWAYS invoke this skill when you need to read API keys, tokens, or other secrets configured by the user. Never hardcode credentials — use this skill to retrieve them securely.
Workspace file I/O expert. ALWAYS invoke this skill when you need to list workspaces, read or write files in a workspace on a remote node, or browse workspace directories. Use this for cross-node file operations — for local sandbox files, use standard filesystem tools instead.
Agent management expert. ALWAYS invoke this skill when you need to list available agents, download or reference agent source code, deploy agent code to the host, or query the LLM connector matrix. Do not guess agent structures — use this skill first.
Image expert. ALWAYS invoke this skill when you need to read, analyze, describe, or generate images. Use for screenshots, photos, charts, diagrams, AI-generated images, or any visual content.
Yao process documentation expert. ALWAYS invoke this skill when the user needs to discover available processes, read process signatures, or validate process names. Do not guess process APIs — use this skill first.
Yao process execution expert. ALWAYS invoke this skill when the user needs to call a Yao process, query data models, run scripts, or check process permissions. Do not call processes without checking this skill first.