Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Voice Agent Design · stijnman | DecimalAI

agent toolingby stijnman

Voice Agent Design

stijnman/voice-agent-design

Source stijnman/grok-custom-skills ↗License MIT

Design a safe, vendor-neutral voice agent with conversation flows, consent notices, escalation paths, and approval-gated actions.

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 9/4/2026

What it changes

Passed 20 of 22 test cases with the skill, and 19 of 22 without it.

Without skill86%

With skill91%

Checks it passed that the model alone missed

Includes test cases for ambiguous calls in the test matrix.
Includes AI identity disclosure during the initial greeting flow.
Mandates asking one concise clarification before offering a human handoff when user intent remains unclear.

and 1 more in the full report

2 fixed18 passed either way1 still failing1 broke

Pass-rate lift: +5 pp
Tokens: -21%
Agent turns: 0%
Response time: -24%

Model gemini-3.6-flashMeasured 9/4/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stijnman-voice-agent-design/SKILL.md https://app.decimal.ai/s/stijnman-voice-agent-design/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stijnman-voice-agent-design, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stijnman-voice-agent-design/ and pins it in .decimal/skills.lock

decimalai skills add stijnman-voice-agent-design

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/stijnman-voice-agent-design/SKILL.md https://app.decimal.ai/s/stijnman-voice-agent-design/SKILL.md

Raw file: /s/stijnman-voice-agent-design/SKILL.md ↗ · machine-readable summary at /s/stijnman-voice-agent-design.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

Create an error handling routine for a pharmacy voice assistant that handles prescription refill requests. When a caller's speech is unclear or ambiguous, should the agent continue asking clarifying questions three or four times until it gets a clear response, or how should it handle persistent ambiguity?

What was checked, without and with the skill
Checked	Without skill	With skill
Limits intent clarification to one concise follow-up question before offering escalation to a human representative.	Missed	Passed

case-05 · gemini-3.6-flash · 9/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md27 linessingle file

Voice Agent Design

Purpose

Design a voice-agent specification that is concise, understandable, and safe for callers. The skill is vendor-neutral and does not assume a specific telephony or model provider.

Workflow

Define the agent’s purpose, audience, supported tasks, and explicit exclusions.
Draft a short conversation flow: greeting, disclosure where appropriate, intent capture, information gathering, resolution, confirmation, and close.
Identify sensitive data, recording notices, retention rules, and a path to a human representative.
List every external action, such as booking, messaging, payment, or account change, and require explicit confirmation immediately before it occurs.
Define failure handling for uncertainty, silence, interruption, bad transfer, and urgent or sensitive topics.
Write a test plan covering normal, ambiguous, adversarial, and escalation calls.

Safety boundaries

Obtain explicit consent before voice cloning a real person. Do not imitate a person without authorization, conceal an AI identity where disclosure is required, or make promises the system cannot verify. Keep recordings and transcripts to the minimum authorized scope.

Error handling

Situation	Response
Intent remains unclear	Ask one concise clarification, then offer human handoff.
Caller requests a consequential action	Restate scope and obtain confirmation before acting.
Sensitive or emergency topic arises	Follow the approved escalation path; do not improvise advice.
Tool or knowledge source fails	State the limitation, avoid guessing, and offer a safe alternative.

Track record

Benchmark

20 / 22

test cases passed, vs 19 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/15/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/voice-agent-design/SKILL.md

View on GitHub ↗

License MITImported 8/15/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

mohitagw15856/voice-agent-designDesign 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.Close match+18 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Voice Agent Design

Purpose

Workflow

Safety boundaries

Error handling

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills