prompt-analyze

Prompt Analyze Compatibility Skill

Goal

Preserve legacy prompt-analyze activation while producing review evidence through hve-builder in read-only review mode.

Flow

1. Translate promptFiles to targets and infer current open or attached prompt-engineering artifacts when omitted.
2. Activate hve-builder with mode=review, the targets, analysis requirements, and any caller-owned evidence root.
3. Keep source artifacts read-only. Permit only review and requested validation evidence writes.
4. Return the review verdict, validation as Not requested unless the caller requested it, overall outcome, findings summary, and evidence links.

Inputs

• promptFiles: existing prompt, instruction, agent, subagent, skill, reference, or template files to review
• requirements: optional purpose, criteria, or behavior to emphasize
• evidenceRoot: optional caller-owned HVE Builder evidence path

Success Criteria

• Source artifacts are unchanged.
• The review pass completes or carries an explicit deferral.
• Findings use the HVE rubric severity and disposition contracts.
• The response links the durable review evidence.

Constraints

• Do not dispatch retired named lifecycle workers.
• Do not research, fix, refactor, or create source artifacts in this mode.

Stop Rules

• Stop Pass when hve-builder review mode returns Pass.
• Preserve Revise, Deferred, or Blocked and its rerun condition.
• Stop before any source edit.

Handoff

Recommend prompt-builder for approved improvements or prompt-refactor for behavior-preserving cleanup. Both route changes through hve-builder.

Final Response Contract

Return targets, review verdict, validation result (Not requested unless requested), overall outcome, top findings, evidence links, and next action.