{"id":65442,"plugin_id":"plugin_asdk_app_6ac538f379848191b06f48cdf910de4b","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-27T06:07:20.316Z","digest":"673b36e05b415e94d45c221bc6c341183892c1d273c898777c1e2b1701310eb7","against":null,"payload":{"description":"Test a ThunderPhone agent and decide whether it is ready to deploy. Use when someone asks to test an agent, run test scenarios or simulated calls, check a change before deploying, or read test results.","included_files":[],"name":"test-agent","skill_md_contents":"---\nname: test-agent\ndescription: Test a ThunderPhone agent and decide whether it is ready to deploy. Use when someone asks to test an agent, run test scenarios or simulated calls, check a change before deploying, or read test results.\nlicense: MIT\ncompatibility: Requires the ThunderPhone MCP server, connected with OAuth. No step asks for a password, API key or other secret.\nmetadata:\n  author: thunderphone\n  version: \"1.0\"\n---\n\n# Test an agent\n\nPick the check that fits the change and what it could break.\n\n| Check | Tool | Cost | Good for |\n|---|---|---|---|\n| Text test | `test_in_text` | Free, about a minute | Wording, facts, which tools the agent calls |\n| Saved scenarios | `test_my_agent` | Test credit first | A pass/fail run over the agent's scenarios |\n| One simulated call | `run_simulation` | Test credit first | Timing, the voice, hearing the caller |\n| Talk to it | `create_talk_link` | Billed like a test call | The user's own ear |\n\n1. **Text first.** Run `test_in_text` on the draft with callers aimed at the\n   change and one whose call should go as before. Read each transcript the way a\n   caller would hear it. Tool results are simulated; say so.\n2. **Billed runs need a yes.** Before `test_my_agent`, `run_agent_tests` or\n   `run_simulation`, tell the user that test calls draw on the free test credit\n   first, and set `consent_to_charge` only after they agree.\n3. **One call does the loop.** `test_my_agent` runs the saved scenarios, or\n   generates some when there are none, and waits for the verdicts. If it returns\n   before they are in, check again with `get_test_run` and the `batch_id`.\n4. **Report evidence.** For each failure, quote the turn that failed and propose\n   one change. Make it on the draft with `update_agent` and test again.\n5. **Deploy only after a yes** with `deploy_agent`.\n\nDocs: https://thunderphone.com/docs/guides/test-agents\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}