Execute a single L1-L4 verification layer from a subtask plan.
npx skills add https://github.com/phj128/autoworker --skill test-phj128
Please help me install this Agent Skill. Skill: test Source: https://github.com/phj128/autoworker/tree/main/skills/test Command: npx skills add https://github.com/phj128/autoworker --skill test-phj128
Execute ONE test level (L1/L2/L3/L4) from subtask verification plan. Only run tests, do not record results. Called by autoworker:dispatch with level argument. Ends by calling autoworker:checkpoint.
Run autoworker:test L2 to execute all tests for layer 2 in the current subtask plan.
High-intent search queries and answers about installing and using this skill.
To execute a single test layer from a verification plan, call the test execution command with an explicit level argument (L1-L4) to run only that chosen test level autonomously.
When test execution encounters consecutive failures, the system handles them by re-running the tests and entering diagnostic mode to log fixes for traceability.
Yes, you can run tests for a specific verification level without modifying other layers by executing only the chosen test level from the subtask verification plan.
If no explicit level is provided, the system determines which test level to run by inferring the next incomplete level from the subtask verification plan.
Test execution does not record results directly; instead, it invokes the checkpoint process upon completion to handle outcome recording and state tracking.
The best way to autonomously assess a single L1-L4 test layer is to use a test execution command that reads the plan, extracts items, executes commands, and compares actual versus expected results.
phj128Automate end-to-end implementation tasks with a state-machine workflow and quality gates.
gvkhoslaRun five parallel hypothesis agents to diagnose product traction stalls and rank failure modes.
phj128Automates preparation and verification of carpentry and other craftwork estimates and invoices.
icednutExecute n8n integration test scenarios and compare outputs against expected JSON results.
