vac-designlisted

Design the conversation architecture for a voice agent. Use after research to define conversation phases, transitions, dynamic variables, guardrails, behavioral modules, and no-gos. Produces the conversation blueprint that the prompt writer follows.
callflows/voice-agent-kit · ★ 1 · AI & Automation · score 74

Install: claude install-skill callflows/voice-agent-kit

# VAC Design Design the conversation architecture. Output: `conversation-design.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 | 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 `briefing.md` and `research.md` 2. Define conversation phases and transitions 3. Map dynamic variables to the 3-layer architecture 4. Design behavioral modules (greeting protection, closing, adaptive modes) 5. Define guardrails and no-gos 6. Define success/failure/edge-case paths 7. Knowledge Architecture gate: KB needed? (if yes → `vac-knowledge-base` runs next, before vac-prompt) 8. Write `conversation-design.md` ## Behavioral Control Layers (behavior steering) > **Do not confuse** these with the "3-Layer Architecture (law)" model directly below — that one sorts > variables by ORIGIN (prompt / variable / dispatcher). THESE layers sort BEHAVIOR by type of control. > Two different axes. SSOT: `../../VOI