test_skill
Test a SKILL.md. No model, every call: lint (gate on lint.valid) and review (description lacks what/when, words shared with other_skills, leftovers, no done-check, missing files; why + fix each). Unless lint_only, a model picks a skill per request from names+descriptions: trigger_accuracy PASS ≥80, FIX ≥50, else BLOCK; your scenarios = gate, generated = signal; unanswered = INCONCLUSIVE. Server key 10 runs/day.
Example tool call
This call uses example arguments supplied in the tool’s input schema.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"skill_md": "---\nname: json-formatter\ndescription: Pretty-print a JSON string the user pastes.\n---\nFormat the JSON with 2-space indentation."
},
"name": "test_skill"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | Paths in its folder. | |
| model | No | Default openai/gpt-oss-20b. | |
| api_key | No | Used once, not stored. | |
| dir_name | No | Its folder. | |
| skill_md | Yes | Full SKILL.md, frontmatter included. | |
| lint_only | No | ||
| scenarios | No | Max 20, near misses included. | |
| other_skills | No | Installed next to it. | |
| scenario_count | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lint | No | ||
| review | No | ||
| verdict | No |