skill_execute
Execute a skill workflow by slug, automatically running all tool steps in order with credential injection and sensitive output redaction.
Instructions
Execute a skill workflow by slug. Runs all tool steps in order with automatic credential injection. Sensitive outputs are automatically redacted by the server.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"slug": "<slug>"
},
"name": "skill_execute"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Skill slug (e.g. "summarize-and-translate") | |
| input_json | No | Input data as a JSON string (must match skill input schema if defined) | |
| llm_response | No | LLM response to provide when resuming a paused execution | |
| resume_token | No | Opaque resume token from a paused execution (for LLM step continuation) | |
| step_overrides | No | Per-step parameter overrides as key-value pairs |