skill_record
Record skill usage telemetry including kind (use, view, patch, create) and optional outcome (helped, partial, wrong) to enable curator decisions on archiving or pruning skills.
Instructions
Record usage telemetry for a mirrored skill.
kind: 'use' | 'view' | 'patch' | 'create'. Bumps the corresponding
counter + timestamp in skill_usage. The curator reads these to decide
what to archive.
outcome (optional, meaningful with kind='use'): 'helped' | 'partial'
| 'wrong'. When set, also emits an events.kind='skill_outcome' row
so the curator can identify skills that fire often but consistently
give 'wrong' verdicts — those are false-positive candidates to PRUNE.
The 'wrong' outcome is the primary signal an agent has to say "I consulted this skill, it didn't actually apply / was misleading; please patch or delete next curator pass." Don't be shy about marking 'wrong' — better a curated library than a polluted one.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| kind | No | use | |
| outcome | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |