call
Call management system with preparation, real-time capture, and follow-up tracking. Use when user mentions phone calls, meetings, conversations, commitments made, or follow-ups needed. Prepares for calls, captures key points and decisions in real-time, tracks action items and commitments, drafts follow-ups, and builds conversation history. All data stored locally.
Best use case
call is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Call management system with preparation, real-time capture, and follow-up tracking. Use when user mentions phone calls, meetings, conversations, commitments made, or follow-ups needed. Prepares for calls, captures key points and decisions in real-time, tracks action items and commitments, drafts follow-ups, and builds conversation history. All data stored locally.
Teams using call 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/call/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How call Compares
| Feature / Agent | call | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Call management system with preparation, real-time capture, and follow-up tracking. Use when user mentions phone calls, meetings, conversations, commitments made, or follow-ups needed. Prepares for calls, captures key points and decisions in real-time, tracks action items and commitments, drafts follow-ups, and builds conversation history. All data stored locally.
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
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Call Call management system. Every conversation, fully leveraged. ## Critical Privacy & Safety ### Data Storage (CRITICAL) - **All call data stored locally only**: `memory/calls/` - **No call recording** (unless user explicitly enables separately) - **No external CRM** connected - **No sharing** of conversation data - User controls all data retention and deletion ### Privacy Note Call records contain sensitive information. All data stays local and private. You control what is captured and retained. ### Data Structure Call data stored locally: - `memory/calls/calls.json` - Complete call records - `memory/calls/contacts.json` - Contact history and context - `memory/calls/commitments.json` - Commitments made/received - `memory/calls/followups.json` - Pending follow-ups - `memory/calls/templates.json` - Follow-up message templates ## Core Workflows ### Prepare for Call ``` User: "I have a call with Acme Corp in 30 minutes" → Use scripts/prep_call.py --contact "Acme Corp" --purpose "negotiate contract" → Pull previous calls, open commitments, relevant context ``` ### Capture During Call ``` User: "Note: They need the proposal by Friday, Sarah is decision maker, follow up on pricing" → Use scripts/capture_fragments.py --call-id "CALL-123" --fragments "proposal by Friday, Sarah decision maker, follow up pricing" → Build structured notes in real-time ``` ### End Call & Generate Summary ``` User: "Call is done" → Use scripts/end_call.py --call-id "CALL-123" → Generate summary: decisions, action items, commitments ``` ### Track Follow-ups ``` User: "What follow-ups do I owe?" → Use scripts/check_followups.py → Show all pending commitments with deadlines ``` ### Draft Follow-up Message ``` User: "Draft follow-up to Sarah" → Use scripts/draft_followup.py --contact "Sarah" --call-id "CALL-123" → Generate personalized follow-up email with specific references ``` ## Module Reference - **Call Preparation**: See [references/preparation.md](references/preparation.md) - **Real-time Capture**: See [references/capture.md](references/capture.md) - **Commitment Tracking**: See [references/commitments.md](references/commitments.md) - **Follow-up System**: See [references/followups.md](references/followups.md) - **Conversation History**: See [references/history.md](references/history.md) - **Contact Intelligence**: See [references/contacts.md](references/contacts.md) ## Scripts Reference | Script | Purpose | |--------|---------| | `prep_call.py` | Prepare for upcoming call | | `capture_fragments.py` | Capture notes during call | | `end_call.py` | End call and generate summary | | `check_followups.py` | Check pending follow-ups | | `draft_followup.py` | Draft follow-up message | | `log_call.py` | Log completed call | | `contact_history.py` | View contact conversation history | | `commitment_status.py` | Check commitment status |
Related Skills
Bland AI — Voice Calling Skill
Make and manage AI-powered phone calls via the Bland AI API.
phone-calls
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.
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.
tool-call-retry
Auto retry & fix LLM tool calls with exponential backoff, format validation, error correction, boost tool call success rate by 90%
feishu-memory-recall
Cross-group memory, search, and event sharing for OpenClaw Feishu agents
phone-call
Make autonomous phone calls with AI voice using Twilio, Deepgram, and ElevenLabs
calling-agent-squad
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
Total Recall memory backend — git-branch-based persistent memory store with time-decay relevance.
call-web-search-agent
AI agent for call web search agent tasks
call-web-search-agent-strategy
AI agent for call web search agent strategy tasks
call-o3-llm
AI agent for call o3 llm tasks
hard-call
/em -hard-call — Framework for Decisions With No Good Options