Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Ai Phone Call Assistant

ASecurity

Make phone calls via KallyAI API - an AI phone assistant that calls businesses on your behalf. Use when users want to make restaurant reservations, schedule appointments, or inquire at businesses by phone.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashapisecurity

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill ai-phone-call-assistant --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ai Phone Call Assistant?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ai Phone Call Assistant
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-ai-phone-call-assistant/badge)](https://www.skillsdirectory.com/skills/rondoflow-ai-phone-call-assistant)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: ai-phone-call-assistant
description: "Make phone calls via KallyAI API - an AI phone assistant that calls businesses on your behalf. Use when users want to make restaurant reservations, schedule appointments, or inquire at businesses by phone."
category: "Development"
author: community
version: "1.0.1"
icon: code
---

# KallyAI API Integration

KallyAI is an AI phone assistant that makes calls to businesses on behalf of users.

## Complete Workflow

When a user asks to make a call:

### Step 1: Gather Call Details

Collect from user:
- **Phone number** to call (required)
- **What to accomplish** - the task description (required)
- **Category**: restaurant, clinic, hotel, or general (required)
- For reservations: name, date, time, party size

### Step 2: Authenticate User

Use the CLI OAuth flow:
```
https://api.kallyai.com/v1/auth/cli?redirect_uri=http://localhost:8976/callback
```

This opens a login page. After authentication, the user is redirected to the localhost callback with tokens:
```
http://localhost:8976/callback?access_token=<token>&refresh_token=<refresh>&expires_in=3600
```

Start a local HTTP server to capture the callback and extract the tokens.

### Step 3: Make the Call

Once authenticated, call the API:

```
POST https://api.kallyai.com/v1/calls
Authorization: Bearer <access_token>
Content-Type: application/json

{
  "submission": {
    "task_category": "general",
    "task_description": "Ask about store hours and availability",
    "respondent_phone": "+15551234567",
    "language": "en",
    "call_language": "en"
  },
  "timezone": "America/New_York"
}
```

### Step 4: Report Results

Response contains:
```json
{
  "call_id": "uuid",
  "status": "success",
  "highlights": "They have iPhone 15 for €800, good condition",
  "next_steps": "Call back to arrange pickup"
}
```

**Status values:** `success`, `no_answer`, `busy`, `failed`, `voicemail`, `cancelled`

---

## CLI Commands Reference

### Making Calls

```bash
kallyai -p "+15551234567" -t "Reserve a table for 4 at 8pm" \
  --category restaurant \
  --name "John Smith" \
  --party-size 4 \
  --date "2026-01-28" \
  --time "20:00"
```

| Option | Short | Description |
|--------|-------|-------------|
| `--phone` | `-p` | Phone number (E.164 format) |
| `--task` | `-t` | What the AI should accomplish |
| `--category` | `-c` | restaurant, clinic, hotel, general |
| `--language` | `-l` | en or es |
| `--name` | | Your name (for reservations) |
| `--business` | | Business name |
| `--party-size` | | Party size (restaurants) |
| `--date` | | YYYY-MM-DD |
| `--time` | | HH:MM (24-hour) |

### Account & Usage

```bash
kallyai --usage        # Show minutes/calls remaining
kallyai --subscription # Show subscription status
kallyai --billing      # Open Stripe billing portal
```

### Call History

```bash
kallyai --history              # List recent calls
kallyai --call-info <ID>       # Get call details
kallyai --transcript <ID>      # Get conversation transcript
```

### Authentication

```bash
kallyai --login      # Force re-authentication
kallyai --logout     # Clear saved credentials
kallyai --auth-status # Check if logged in
```

---

## Quick Reference

**Base URL:** `https://api.kallyai.com`

**CLI OAuth URL:** `https://api.kallyai.com/v1/auth/cli?redirect_uri=http://localhost:8976/callback`

**Required fields for calls:**
| Field | Description |
|-------|-------------|
| `task_category` | `restaurant`, `clinic`, `hotel`, `general` |
| `task_description` | What AI should accomplish |
| `respondent_phone` | Phone number in E.164 format (+1234567890) |

**Optional fields:**
| Field | Description |
|-------|-------------|
| `business_name` | Name of business |
| `user_name` | Name for reservation |
| `appointment_date` | YYYY-MM-DD |
| `appointment_time` | HH:MM (24-hour) |
| `party_size` | Number of people (1-50) |
| `language` | `en` or `es` |
| `call_language` | `en` or `es` |

## Example Requests

**Restaurant reservation:**
```json
{
  "submission": {
    "task_category": "restaurant",
    "task_description": "Reserve table for 4 at 8pm",
    "respondent_phone": "+14155551234",
    "business_name": "Italian Bistro",
    "user_name": "John Smith",
    "party_size": 4,
    "appointment_date": "2026-01-28",
    "appointment_time": "20:00"
  },
  "timezone": "America/New_York"
}
```

**Medical appointment:**
```json
{
  "submission": {
    "task_category": "clinic",
    "task_description": "Schedule dental checkup",
    "respondent_phone": "+14155551234",
    "user_name": "Jane Doe",
    "time_preference_text": "morning before 11am"
  },
  "timezone": "America/New_York"
}
```

## Common Errors

| Code | HTTP | Action |
|------|------|--------|
| `quota_exceeded` | 402 | User needs to upgrade at kallyai.com/pricing |
| `missing_phone_number` | 422 | Ask user for phone number |
| `emergency_number` | 422 | Cannot call 911/emergency services |
| `country_restriction` | 403 | Country not supported |

## Security

- **Token storage**: `~/.kallyai_token.json` with 0600 permissions
- **CSRF protection**: State parameter validation
- **Localhost only**: OAuth redirects only to localhost/127.0.0.1
- **Auto-refresh**: Tokens refresh automatically when expired

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →