一键导入
call
// Use when the user wants to make a phone call, leave a voicemail, call a business, reach someone by phone, or navigate a phone menu. Triggered by "/call" followed by a phone number and purpose.
// Use when the user wants to make a phone call, leave a voicemail, call a business, reach someone by phone, or navigate a phone menu. Triggered by "/call" followed by a phone number and purpose.
Use when the user asks to "browse a website", "go to a URL", "fill out a form", "take a screenshot", "click on something", "extract data from a page", "automate a browser task", "control the desktop", "use the computer", or any task involving web pages or desktop applications.
Start or continue a progressive learning session. Use when the user says "learn", "let's learn", "continue learning", "let's continue", "pick up where we left off", "teach me", "next lesson", or wants to resume their learning curriculum. Requires a phase map to exist in docs/phases/.
Design progressive learning curricula and generate project phase maps. Use when the user says "learn-design", "design curriculum", "plan learning path", "set up next project", "what should I learn next", or wants to start learning a new technical area. Also triggers between projects to generate the next project's phase map calibrated to the learner's profile.
This skill converts any content source into podcast episodes. Triggers: sending a URL, PDF, YouTube link, book, or file with intent to listen; phrases like 'podcast this', 'make this a podcast', 'listen to this', 'generate a podcast'; sending content with instructions like 'split by chapters', 'make a series'. Handles single articles, multi-chapter books, YouTube playlists, and any document format.
This skill should be used when the user asks to "read a paper", "understand a paper", "analyze a research paper", "prepare for paper discussion", "work through a paper", "do a literature review", or provides PDF paths to research papers. Guides deep paper understanding using Keshav's three-pass method with AI as a patient professor. Supports multiple papers for literature review.
Guides Claude's behavior during Copilot-collaborative development sessions: automated reviews (designing/implementing phases) and interactive consultations (/consult)
| name | call |
| description | Use when the user wants to make a phone call, leave a voicemail, call a business, reach someone by phone, or navigate a phone menu. Triggered by "/call" followed by a phone number and purpose. |
| version | 0.1.0 |
| argument-hint | <phone_number> <purpose> |
| allowed-tools | ["Bash","Read","Write"] |
Make phone calls that leave voicemails, navigate IVR menus, and warm-transfer live humans to your phone.
/call <phone_number> <purpose in natural language>
Examples:
/call 3606765437 ask about enrollment for my 2.5yo daughter
/call 2065551234 schedule a dentist appointment for next week
/call 8005551234 cancel my internet service
call-logs/ in current projectClaude Code (brain, makes all decisions)
+ Pipecat Server (sandboxed voice worker, FastAPI + Twilio WebSocket)
+ Twilio (telephony, AMD, DTMF, call transfer)
+ Azure OpenAI gpt-4o-mini-transcribe (STT, segmented)
+ Azure OpenAI TTS HD (voicemail audio, pre-generated)
Security boundary: Pipecat is a sandboxed low-privilege process. It handles audio only. Claude Code never receives raw call audio -- only text transcripts. This prevents caller prompt injection from reaching Claude Code's privileged tools.
requested → dialing → ringing → answered
│
┌───────────┼───────────┐
▼ ▼ ▼
voicemail ivr_nav human
│ │ │
▼ ▼ ▼
leaving_msg navigating transferring
│ │ │
└───────────┼───────────┘
▼
completed
Terminal reasons: voicemail_left, transferred, no_answer, busy, ivr_failed, call_dropped, transfer_failed, timeout, error
Run the setup script:
${CLAUDE_PLUGIN_ROOT}/scripts/setup.sh
This will:
${CLAUDE_PLUGIN_ROOT}/config.jsonConfig stored at ${CLAUDE_PLUGIN_ROOT}/config.json:
{
"twilio": {
"account_sid": "ACxxxxxxxx",
"auth_token": "xxxxx",
"from_number": "+1XXXXXXXXXX"
},
"azure_openai": {
"endpoint": "https://xxx.openai.azure.com",
"api_key": "xxxxx",
"tts_model": "tts-hd",
"tts_voice": "onyx",
"stt_model": "gpt-4o-mini-transcribe"
},
"transfer_to": "+16083207152",
"ngrok_auth_token": "xxxxx",
"pipecat_port": 8765
}
Saved to <project>/call-logs/YYYY-MM-DD-xxxx<last4>.md:
# Call: (360) ***-5437
**Date:** 2026-03-22 2:34 PM
**Purpose:** Ask about enrollment for 2.5yo
**Outcome:** Voicemail left
**Duration:** 45 seconds
## Transcript
[0:00] IVR: "Thank you for calling..."
[0:08] Agent: Sent DTMF 1 (enrollment)
[0:15] Voicemail: "Please leave a message after the tone"
[0:18] Agent: Played voicemail message
<Say> (robotic but works)Every call produces a log. No call ends silently.
~$0.03-0.05 per call (Twilio minutes + AMD + Azure OpenAI tokens).
The skill logic is in $ARGUMENTS:
${CLAUDE_PLUGIN_ROOT}/config.json