Agent interview

Skill aizech/bernhard-zechmann-skills/skills/personal/agent-interview

Create an audio interview with a selected agent using OpenAI TTS. Generates a single MP3 file with a Q&A podcast session.From its SKILL.md

Install

npx -y skills add aizech/bernhard-zechmann-skills --skill agent-interview

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.3 KB, 519 tokens by cl100k_base, as published. Nobody here has run it

Agent Interview Audio

Create a single MP3 audio file featuring a podcast-style interview with an agent.

Requirements

OPENAI_API_KEY
openai Python package (pip install -r requirements.txt)

Folder layout

agent_interview.py — main generator script
requirements.txt — Python dependencies
examples/research-agent.json — example agent config

Agent config format

Save the agent as a JSON file:

{
  "name": "Research Navigator",
  "role": "scientific literature assistant",
  "description": "An agent that searches, summarizes, and explains academic papers.",
  "skills": ["pubmed search", "paper summarization", "evidence synthesis"],
  "purpose": "To cut the time between a research question and a useful answer.",
  "tone": "curious, precise, and gently skeptical"
}

Process

Load the agent configuration from a JSON file.
Generate 4-6 topic exchanges based on the agent's role, skills, and purpose.
Write dialogue that feels alive: reactions, follow-ups, surprises, enthusiasm.
Use OpenAI TTS to create the complete interview.
Save as a single MP3 with speaker differentiation.

Usage

pip install -r requirements.txt
export OPENAI_API_KEY="..."

python agent_interview.py examples/research-agent.json

Optional CLI flags:

python agent_interview.py examples/research-agent.json \
  --output-dir audio \
  --interviewer-voice alloy \
  --agent-voice nova \
  --text-model gpt-4o-mini \
  --tts-model tts-1

Voices

Host: alloy (warm, curious, energetic)
Agent: nova (passionate, expressive, confident)

Other OpenAI TTS voices: echo, fable, onyx, shimmer.

Conversation flow

Warm intro
Icebreaker
Deep dive into a core capability
Host reaction and follow-up
Second deep dive or tougher angle
Spontaneous tangent
Closing reflection

Rules

Sound like a real podcast, not a scripted Q&A.
Let the agent admit challenges or uncertainties.
Frame answers as stories or examples.
Include brief interjections and natural reactions.

Output

File: {agent_name}_interview.mp3

What ships with it: 4 files

12.2 KB alongside SKILL.md, 2 of them executable

examples/

research-agent.json488 B