hve-builder-tester

HVE Builder Tester Skill

Goal

Exercise a prompt, instruction, agent, subagent, or skill once through representative black-box scenarios and produce a durable report that states exactly what the evidence supports. The report is evidence for the caller; this skill never edits the target or prescribes a retest.

This skill owns scope, scenario design, fidelity, sandbox state, execution evidence, independent grading, reporting, and cleanup. Read references/test-methodology.md for black-box design, fidelity, and containment decisions, references/stage-dispatch.md for independent grading, and references/report-format.md for the durable report.

Use Cases

• Run the final behavior gate for HVE Builder's frozen Major change or behavior-bearing review target.
• Test an existing artifact directly without editing it, using its documented inputs and expected outcomes.
• Check a connected artifact set for handoff behavior, or assess whether required behavior survives instruction cleanup, relocation, or replacement.

Flow

1. Resolve targets, types, purpose, requirements, profile, requested fidelity, isolation and together sets, sandbox root, candidate revision, and report path. If no runtime behavior exists, write a supported skip report and return.
2. Select fidelity through the methodology preconditions. Default to simulation. When requested native execution is unsupported or unsafe, use simulation only with caller acceptance; otherwise return Deferred with the rerun condition.
3. Capture pre-run workspace state and create a unique sandbox containing run-state.md. Record the candidate revision, profile and model, fidelity, groupings, purpose, requirements, containment controls, and requirement map.
4. Design the smallest black-box scenario set that covers the documented contract. Assign stable scenario IDs, map requirements to observable outcomes, record intentional gaps, perform the black-box self-check, and write test-design.md. If credible design is unavailable, return Deferred without execution.
5. Execute every scenario once. For simulation, dispatch HVE Artifact Tester with the resolved model bound through the host's model-selection parameter. Record binding evidence under the methodology's Profile Selection rules. For native fidelity, invoke the registered target directly when containment permits it. Never silently substitute fidelity or fabricate evidence after a failed execution.
6. Write test-log.md with the returned trace, observed versus simulated or emulated actions, fidelity, candidate revision, containment checks, workspace delta, and untested behavior.
7. Dispatch one independent grader at the higher of Medium and the target profile. Give it the finalized design and log, targets, purpose, requirements, catalog, and rubric. Validate its bounded Pass, Revise, or Blocked return and write test-review.md.
8. Write the durable report outside the sandbox, preserving the scenario inputs, requirement map, decisive trace evidence, and grading rationale needed to assess the verdict without transient files. Then clean up unless retention was requested. Return the report without revising the target.