What do I need to use Voice Agent Design?

The line and its traffic; What the agent may actually do; The escalation reality; Compliance context.

Is Voice Agent Design free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Voice Agent Design

Q: How do I know the Voice Agent Design output is good?

The skill verifies itself against its own quality checks: Every owned intent is completable with the agent's *actual* system access — no "owns refunds" without refund API access; The opening discloses AI status and the escape hatch, verbatim in the spec; No designed utterance exceeds two sentences before yielding; The repair ladder changes strategy at each rung — no repeat-louder step.

🔵 Stable🕐 updated 2026-07-02 🔷 SkillSpec L3 pm-agentnative

Design a voice AI agent for phone or in-app conversations — call flows, interruption handling, escalation to humans, and the metrics that catch a bad voice experience. Use when asked to design a voice agent, automate a phone line, spec an IVR replacement, or review why callers hate an existing voice bot. Produces a voice agent spec: persona and disclosure policy, conversation architecture, barge-in and repair behaviour, human-handoff rules, and a launch scorecard.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The line and its traffic — what people call about (top intents with rough volumes), current handle times

▸What the agent may actually do — which systems it can read/write, what it can promise

▸The escalation reality — human hours, queue lengths, what happens after-hours

▸Compliance context — recording consent, disclosure requirements, regulated statements in this domain

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every owned intent is completable with the agent's *actual* system access — no "owns refunds" without refund API access

✓The opening discloses AI status and the escape hatch, verbatim in the spec

✓No designed utterance exceeds two sentences before yielding

✓The repair ladder changes strategy at each rung — no repeat-louder step

✓Handoff carries the whisper summary; "please hold while I transfer you" to a cold human fails the spec

✓The scorecard pairs containment with caller-scored success

⚠️ What it refuses to do

Do not port the chatbot script to voice — text tolerates paragraphs and menus; ears don't

Do not hide the human escape hatch to protect containment metrics — callers find the exit anyway, angrier

Do not let the agent bluff on regulated topics (medical, legal, financial advice) — pass or read the approved statement

Do not re-ask a failed question unchanged — the caller heard you; the strategy failed, not their ears

Do not launch without the mid-flow hang-up metric — it's where voice agents quietly hemorrhage trust

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="voice-agent-design"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Voice Agent Design is one of 581 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog