OpenParable
Skip to content
← Back to skills

Skill Creator Smoke Test

Agent Building
skill-creator-smoke-test

Skill Creator Smoke Test is an Agent Skill for agent building published in the opensquilla/opensquilla repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

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.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/opensquilla/opensquilla/blob/HEAD/src/opensquilla/skills/bundled/skill-creator-smoke-test/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/skill-creator-smoke-test, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Skill Creator Smoke Test

When invoked as a kind: agent, skill: skill-creator-smoke-test step, this sub-agent:

  1. Receives skill_md, fixture_gen_model, classifier_model from the parent step's with:
  2. Calls simulate_meta_resolution with a positive fixture (LLM-generated using fixture_gen_model)
  3. Calls simulate_meta_resolution with a negative fixture (LLM-generated, cross-domain)
  4. Returns {"G3": {...}, "G4": {...}} JSON

If 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.

Fallback

If the sub-agent fails entirely, output {"G3": {"passed": false, "reason": "smoke unavailable"}, "G4": {"passed": false, "reason": "smoke unavailable"}}.