aiworkhub_manager_skill_mine
Clusters stored rejection instructions and adjudicated invariants by asserted rule, then returns read-only, evidence-backed gated skill proposals for families recurring across cards and files.
Instructions
MANAGER READ: mine the correction record into gated skill PROPOSALS.
Clusters every stored rejection instruction and adjudicated invariant by the
RULE it asserts -- instance vocabulary (paths, identifiers, ids, digits) is
deleted before anything is compared -- then promotes only families that
recurred across at least min_cards distinct cards in min_files
distinct files. Each candidate carries the exact card ids and request ids
where the rule was violated, plus a proposal draft whose closed-vocabulary
selection dimensions are left blank for the manager to fill in.
Read-only. It produces proposals, never activations: the returned draft reaches the store only if a manager proposes it through the skill-proposal step, and activation remains gated on evidence from two distinct actor identities.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "aiworkhub_manager_skill_mine"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| min_cards | No | Minimum distinct cards a family must recur across to become a candidate; default 3. | |
| min_files | No | Minimum distinct files a family must recur across to become a candidate; default 3. | |
| threshold | No | Similarity threshold for grouping correction statements into rule families; default 0.22. Higher values yield fewer, tighter families. | |
| include_sensitivity | No | True (default) also returns how the family count changes across the 0.18-0.30 thresholds; false omits that curve. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||