Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to run G3 (positive smoke) and G4 (negative smoke) gates against a candidate meta-skill SKILL.md. Cross-vendor: fixture-generation LLM != classifier LLM. Returns JSON.
56
63%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./src/opensquilla/skills/bundled/skill-creator-smoke-test/SKILL.mdWhen invoked as a kind: agent, skill: skill-creator-smoke-test step, this sub-agent:
skill_md, fixture_gen_model, classifier_model from the parent step's with:simulate_meta_resolution with a positive fixture (LLM-generated using fixture_gen_model)simulate_meta_resolution with a negative fixture (LLM-generated, cross-domain){"G3": {...}, "G4": {...}} JSONIf OPENROUTER_API_KEY is absent OR either fixture_gen_model/classifier_model is unconfigured, the sub-agent falls back to the deterministic fixture generator and pins classifier_model="stub". In both cases the smoke step still emits G3/G4 records, but with a degraded: true flag.
If the sub-agent fails entirely, output {"G3": {"passed": false, "reason": "smoke unavailable"}, "G4": {"passed": false, "reason": "smoke unavailable"}}.
94ac35e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.