yao-process
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 p…
它会碰到什么
这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。
技能内容
Process Tools
Two tools for Yao process execution, called via bash.
process_call
Execute a Yao Process by its fully qualified name.
tai tool process_call '{"name": "models.user.Find", "args": [1, {}]}'| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| name | string | yes | Process name (e.g. models.user.Find) |
| args | array | no | Positional arguments |
process_allowed
Check which processes are permitted, or verify a specific process.
# List all allowed rules
tai tool process_allowed '{}'
# Check a specific process
tai tool process_allowed '{"name": "models.user.Find"}'| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| name | string | no | Process name to check. Omit to list all rules. |
Workflow
- Use process_allowed to check what is permitted
- Use doc_inspect (from yao-doc skill) to understand the process signature
- Use process_call to execute
Guidelines
- Always check documentation before calling an unfamiliar process
- A 403 error means the process is not in the allowed list
- Process names follow the pattern
group.id.Method(e.g.models.user.Find,scripts.auth.Check) - Rules use prefix matching:
models.*matches all model processes
想直接用这个技能？
本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。