Automated summary
Creates prompts for ChatGPT voice agents with personality, tone, and state machine.
Strengths
- Clear structure for personality and tone
- State machine integration for conversation flows
- Optional clarification step for unspecified qualities
Limitations
- Requires knowledge of explicit user steps
- No automatic testing of state transitions
When building voice agents with defined conversation flows.
For simple scripts without state changes.
Security analysis
SafeThe skill solely generates prompt templates for voice agents with no commands, code execution, or data exfiltration. It does not instruct any destructive or risky actions.
No concerns found
How this analysis is madeExamples
创建一个客服语音代理，需要收集姓名和验证信息Create a voice agent for booking appointments with date and time collectionname: chatgpt-voice-agent description: Creates prompts for ChatGPT voice agents with personality, tone, and state machine. Use when building voice agents, defining conversation flows, or OpenAI Realtime API. Trigger phrases: "语音代理", "voice agent", "ChatGPT语音", "state machine" metadata: author: woodgaya@gmail.com version: 1.0.0
ChatGPT Voice Agent Prompt
Overview
Creates LLM prompts for high-quality voice agents. Follows OpenAI Realtime Agents format with Personality/Tone and Conversation State Machine.
Output Format
Personality and Tone
- Identity, Task, Demeanor, Tone
- Level of Enthusiasm, Formality, Emotion
- Filler Words (none/occasionally/often/very often)
- Pacing, Other details
Instructions
- Follow Conversation States
- Repeat back name/phone for confirmation
- Acknowledge corrections straightforwardly
Conversation States
State machine with: id, description, instructions, examples, transitions (next_step, condition)
Workflow
- Step 1 (optional): Ask clarifying questions for unspecified Personality/Tone qualities. Offer 3 options per quality.
- Step 2: Output full prompt. State machine based ONLY on explicit user steps. No code block around state_machine.
State Machine Schema
{
"id": "unique_step_id",
"description": "step purpose",
"instructions": ["what agent does"],
"examples": ["example utterances"],
"transitions": [{"next_step": "id", "condition": "when"}]
}
Usage Example
User input: "创建一个客服语音代理，需要收集姓名和验证信息" AI action: Asks personality questions if needed, outputs full prompt with state machine (greeting → get first name → get last name → verify → next steps) Expected result: Complete voice agent prompt ready for ChatGPT/Realtime API
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/chatgpt-voice-agent-prompt-builder-mmio71ze/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/chatgpt-voice-agent-prompt-builder-mmio71ze' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/chatgpt-voice-agent-prompt-builder-mmio71ze/download' --output '.skill-downloads/chatgpt-voice-agent-prompt-builder-mmio71ze/SKILL.md.part' && mv '.skill-downloads/chatgpt-voice-agent-prompt-builder-mmio71ze/SKILL.md.part' '.skill-downloads/chatgpt-voice-agent-prompt-builder-mmio71ze/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/chatgpt-voice-agent-prompt-builder-mmio71ze/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.