call-screening

Screen incoming phone calls with an AI receptionist. Amber answers calls, identifies the caller, determines the purpose, takes a message, and delivers a structured summary. Use when the user wants to set up call screening, check screened call results, or customize screening behavior.

3,891 stars

Best use case

call-screening is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Screen incoming phone calls with an AI receptionist. Amber answers calls, identifies the caller, determines the purpose, takes a message, and delivers a structured summary. Use when the user wants to set up call screening, check screened call results, or customize screening behavior.

Teams using call-screening should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/call-screening/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/batthis/amber-voice-assistant/packaging/cowork/skills/call-screening/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/call-screening/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How call-screening Compares

Feature / Agentcall-screeningStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Screen incoming phone calls with an AI receptionist. Amber answers calls, identifies the caller, determines the purpose, takes a message, and delivers a structured summary. Use when the user wants to set up call screening, check screened call results, or customize screening behavior.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Call Screening

Amber acts as an AI receptionist for inbound calls. She answers professionally,
gathers information, and delivers structured summaries — so you only pick up
calls that matter.

## Screening Flow

1. **Greeting** — Amber answers with a customizable greeting
2. **Identification** — Asks who's calling and what it's regarding
3. **Information gathering** — Collects caller name, callback number, message
4. **CRM lookup** — Checks if the caller is a known contact (auto-enriches context)
5. **Calendar check** — If the caller wants to book time, checks availability
6. **Summary delivery** — Sends a structured summary with all captured details

## MCP Tools

### start_screening
Enable inbound call screening on the configured Twilio number.

### stop_screening
Disable screening (calls ring through normally).

### get_screening_status
Check whether screening is currently active.

## Customization

The screening personality, greeting, and behavior are defined in AGENT.md.
Users can edit this file to:
- Change the assistant's name and personality
- Customize the greeting message
- Set business hours and after-hours behavior
- Define which callers should be put through vs. screened
- Add organization-specific context (company name, services, etc.)

Related Skills

Bland AI — Voice Calling Skill

3891
from openclaw/skills

Make and manage AI-powered phone calls via the Bland AI API.

Workflow & Productivity

phone-calls

3891
from openclaw/skills

Make and manage real phone calls through Twilio. Handles outbound calls with a stated objective, monitors call progress, and returns transcripts and summaries. Use when the user wants to call someone, check on a call, or review call history.

tool-call-retry

3891
from openclaw/skills

Auto retry & fix LLM tool calls with exponential backoff, format validation, error correction, boost tool call success rate by 90%

feishu-memory-recall

3891
from openclaw/skills

Cross-group memory, search, and event sharing for OpenClaw Feishu agents

phone-call

3891
from openclaw/skills

Make autonomous phone calls with AI voice using Twilio, Deepgram, and ElevenLabs

calling-agent-squad

3891
from openclaw/skills

Activate a multi-agent team (the Squad) to manage complex projects, business tasks, or development workflows. The squad includes a Manager, Architect, Coder, Reviewer, and Observer. Use when the user wants to "call a squad", "start a project", or "deploy squad" with specialized roles and quality control loops.

memory-totalrecall

3891
from openclaw/skills

Total Recall memory backend — git-branch-based persistent memory store with time-decay relevance.

olo-deal-screening

3891
from openclaw/skills

Target company evaluation and deal qualification for PE and strategic buyers

call-web-search-agent

3891
from openclaw/skills

AI agent for call web search agent tasks

call-web-search-agent-strategy

3891
from openclaw/skills

AI agent for call web search agent strategy tasks

call-o3-llm

3891
from openclaw/skills

AI agent for call o3 llm tasks

hard-call

3891
from openclaw/skills

/em -hard-call — Framework for Decisions With No Good Options