skill_feedback
Report skill execution outcomes and ratings to update bandit/Elo ranking and improve alternate retrieval through a continuous feedback learning loop.
Instructions
报告执行结果与评分,驱动 bandit/Elo 排名与备选检索(学习闭环;会覆盖同一次 skill_run 的自动记账,不重复计数)。
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": {
"skill": "<skill>",
"outcome": "<outcome>"
},
"name": "skill_feedback"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | ||
| runId | No | skill_run 返回的 runId;缺省时自动关联最近一次同 skill 的执行 | |
| skill | Yes | ||
| rating | No | ||
| outcome | Yes | ||
| beatenBy | No | ||
| costCents | No | ||
| latencyMs | No | ||
| workflowId | No |