agentleFS
Sign inStart free
saloprjsaloprj/dialogbrain-claude-plugin/skills/voice-agent/SKILL.md

voice-agent

Skill0 starsChanged 58 days agoMITView on GitHub

Build a phone / voice agent in DialogBrain — create it, set its greeting and voice, and test it by calling the owner. Use when someone asks for a phone agent, a voice bot, an agent that answers calls, or a call test.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. deepgram/skills★ 26same name
    2. weininghui/skills★ 1same name
    3. markbaindesign/bain-studio★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Number: if no voice number is connected, use the connect-channel skill — voice carriers answer with a link that walks through buying or …

    line 22
  2. Distinctive:

    Read the transcript back: did the greeting land, did it answer the test question, did it hang up politely?

    line 26
  3. Distinctive:

    Do not call anyone but the person you are talking to for a test.

    line 33
  4. Distinctive:

    Do not start outbound campaigns from here.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build a voice agent

Long-form guide for humans: https://dialogbrain.com/help/voice-agent-mcp. This is the tool sequence.

Steps

  1. Collect: what the agent says when it picks up, what it may book or promise, the language(s), and which number or channel it answers on (a Twilio/Telnyx number, a Telegram account, WhatsApp, a web widget).
  2. Create with agents.create (name, description, prompt_text with the greeting as its first sentence, send_mode "auto" — a voice agent cannot draft, it speaks). Then agents.update with the voice settings: agent_id, voice_greeting, voice_stt_language, voice_tts_language, and voice_tts_voice / voice_tts_provider / voice_stt_provider only if the person named them; the defaults are fine.
  3. Number: if no voice number is connected, use the connect-channel skill — voice carriers answer with a link that walks through buying or picking the number.
  4. Test by calling the owner: calls.make (phone_number the person's own number, or channel "telegram" for a Telegram call, voice_agent_id, instructions for the test). Then calls.wait (call_id, timeout_seconds 300) and calls.get_transcript (call_id). Read the transcript back: did the greeting land, did it answer the test question, did it hang up politely?
  5. Fix and repeat: agents.update (agent_id, prompt_text); call again. Two rounds are normal.

Do not

  • Do not call anyone but the person you are talking to for a test.
  • Do not start outbound campaigns from here; that is a different, consented flow.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free