菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
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.
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.
Secret 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.
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.
| name | yao-agent |
| description | 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. |
Five tools for managing agents on the host, called via bash.
List available agents. Returns ID, name, description, and capabilities for each agent.
tai tool agent_list '{}'
tai tool agent_list '{"namespace": "smith"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
namespace | string | no | Filter by namespace (e.g. yao, smith). Omit for all. |
Download a smith-namespace agent into the development directory for editing. Restricted to smith namespace only — for other agents, use agent_reference.
tai tool agent_download '{"id": "smith.weather"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | yes | Agent ID in dot notation. Must be smith.*. |
Downloaded code lands in agent-smith-dev/assistants/smith/<name>/.
Download agent source code from the host into .references/ for read-only study. Any agent across all namespaces can be referenced.
tai tool agent_reference '{"id": "yao.slides"}'
tai tool agent_reference '{"id": "yao.keeper"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | yes | Agent ID in dot notation (e.g. yao.slides) |
Referenced code lands in agent-smith-dev/.references/<namespace>/<name>/.
Deploy agent source code from the sandbox development directory to the host. Restricted to the smith namespace only — attempts to deploy to other namespaces will be rejected.
tai tool agent_deploy '{"id": "smith.weather"}'
tai tool agent_deploy '{"id": "smith.weather", "message": "add SUI page"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | yes | Agent ID in dot notation. Must use smith namespace. |
message | string | no | Optional deploy message for logging. |
Get the current user's LLM connector matrix. Returns metadata for each role (default, heavy, light, vision, etc.) without API keys. Use this to understand which models are available and their capabilities.
tai tool agent_connectors '{}'
No parameters required.
agent_list to discover agents before downloading or referencingagent_download is for editing smith agents — code lands in agent-smith-dev/assistants/smith/<name>/agent_reference is for studying any agent — code lands in agent-smith-dev/.references/<namespace>/<name>/smith namespace for safety