vac-reviewlisted

# VAC Review Score the prompt against the rubric. Iterate or escalate. Output: `review-log.md`. > **Prompt architecture foundation:** `../../VOICE-AGENT-PROMPT-ARCHITECTURE.md` — the overarching SSOT > for rule-vs-goal steering. Pipeline mechanics stay in `PIPELINE.md`. ## Prerequisites (input check) Before starting, check that these files exist in the agent directory (`../voice-agents/<agent>/`): | File | Comes from | If missing | |---|---|---| | `briefing.md` | `vac-intake` (step 1) | Run `vac-intake` first | | `research.md` | `vac-research` (step 2) | Run `vac-research` first | | `conversation-design.md` | `vac-design` (step 3) | Run `vac-design` first | | `prompt.md` | `vac-prompt` (step 4) | Run `vac-prompt` first | | `config.json` | `vac-prompt` (step 4) | Run `vac-prompt` first | | `example-variables.md` | `vac-prompt` (step 4) | Run `vac-prompt` first | | `knowledge-base.md` | `vac-knowledge-base` (step 3b) | KB agents only; run `vac-knowledge-base` first | If an input is missing, do NOT improvise and do NOT carry on with placeholders: name the missing upstream step and ask the requester or workspace admin whether it should be run now. ## Process 1. Read all artifacts: `briefing.md`, `research.md`, `conversation-design.md`, `knowledge-base.md` (if present), `prompt.md`, `config.json`, `example-variables.md` 2. Score each of 20 dimensions (1-5 scale) 3. Write detailed feedback for any dimension < 4.0 4. If overall score >= 4.0 and no dimension < 3.0: **PASS** →