Pocket AI Skill
**Voice recording transcription, semantic search, and meeting intelligence across all conversations.**
Best use case
Pocket AI Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
**Voice recording transcription, semantic search, and meeting intelligence across all conversations.**
Teams using Pocket AI Skill 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/pocket-ai/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Pocket AI Skill Compares
| Feature / Agent | Pocket AI Skill | 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?
**Voice recording transcription, semantic search, and meeting intelligence across all conversations.**
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 Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
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
# Pocket AI Skill
**Voice recording transcription, semantic search, and meeting intelligence across all conversations.**
Pocket AI captures your meetings, calls, and thoughts via a wearable device, then transcribes and indexes everything for semantic search.
## Quick Reference
| What | Value |
|------|-------|
| API Base | `https://public.heypocketai.com/api/v1` |
| API Key | `~/.config/pocket-ai/api_key` |
| Auth | Bearer token |
| Docs | https://docs.heypocketai.com/docs/api |
## Core Capabilities
### 1. Semantic Search (Most Powerful)
Search across ALL recordings by meaning, not just keywords.
```bash
curl -s -X POST \
-H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
-H "Content-Type: application/json" \
-d '{"query": "your company manufacturing decisions"}' \
"https://public.heypocketai.com/api/v1/public/search"
```
**Returns:**
- `userProfile.dynamicContext[]` — AI-built insights from all recordings
- `relevantMemories[]` — Matching transcripts, action items, meeting sections
- Speaker identification, timestamps, relevance scores
### 2. Action Item Extraction
Pocket AI auto-extracts action items from meetings. Search for them:
```bash
curl -s -X POST \
-H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
-H "Content-Type: application/json" \
-d '{"query": "action items tasks follow up"}' \
"https://public.heypocketai.com/api/v1/public/search"
```
### 3. List Tags
```bash
curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
"https://public.heypocketai.com/api/v1/public/tags"
```
### 4. List Recordings
```bash
curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
"https://public.heypocketai.com/api/v1/public/recordings"
```
### 5. Get Recording Details
```bash
curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
"https://public.heypocketai.com/api/v1/public/recordings/{recording_id}"
```
### 6. Download Audio
```bash
curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
"https://public.heypocketai.com/api/v1/public/recordings/{recording_id}/audio"
```
---
## High-Value Query Patterns
### Contact Context
*"What has been discussed with [person]?"*
```json
{"query": "conversations with Dylan Acquisition.com"}
{"query": "Adrienne intercompany invoices discussion"}
{"query": "meetings with Charlene"}
```
### Business Decisions
*"What decisions were made about [topic]?"*
```json
{"query": "your company manufacturing team restructuring decisions"}
{"query": "entity streamlining strategy"}
{"query": "trading system rules discussed"}
```
### Action Items & Follow-ups
*"What needs to be done?"*
```json
{"query": "action items tasks todo follow up"}
{"query": "scheduled meetings upcoming"}
{"query": "things to review or approve"}
```
### Personal Insights
*"What have I said about [topic]?"*
```json
{"query": "trading psychology patience discipline"}
{"query": "family financial planning kids college"}
{"query": "team performance frustrations"}
```
### Meeting Summaries
*"What happened in [meeting type]?"*
```json
{"query": "your company staff meeting summary"}
{"query": "financial review discussion"}
{"query": "geopolitical analysis conversation"}
```
---
## Response Structure
### Search Response
```json
{
"success": true,
"data": {
"userProfile": {
"dynamicContext": [
"AI-built insight from recordings...",
"Another pattern detected..."
],
"staticFacts": []
},
"relevantMemories": [
{
"content": "Transcript segment or action item...",
"metadata": {"source": "turbopuffer", "sources": ["transcript_segment", "action_item"]},
"recordingDate": "2026-01-28 01:16:14",
"recordingId": "uuid",
"recordingTitle": "Untitled Recording",
"relevanceScore": 8.19,
"speakers": "SPEAKER_00, SPEAKER_01",
"transcriptionId": "uuid"
}
],
"total": 8,
"timing": 490
}
}
```
### Memory Content Types
- **Transcript segment:** `[timestamp] SPEAKER_XX: actual words spoken`
- **Action item:** `Action item: Do the thing`
- **Meeting section:** `(start-end) Section Title - Summary of what was discussed`
---
## Integration Points
### Athena (Family Agent)
- Query meeting context to understand your bandwidth
- "Am I free?" → Check if recent recordings show heavy commitments
- Feed meeting insights into scheduling decisions
### Daily Briefings
- Pull action items from yesterday's meetings
- Summarize key decisions made
- Flag urgent follow-ups
### Task Management
- Auto-surface action items as potential tasks
- Cross-reference with existing todo lists
- Track what's been mentioned but not yet acted on
### Operations Channel
- Post important decisions to #operations
- Alert on critical discussions (team changes, financial decisions)
---
## Tags (Your Categories)
Current tags: `ai`, `business`, `call`, `economy`, `finance`, `game`, `geopolitics`, `hockey`, `outlook`, `personal`, `sales`, `summary`, `test`, `victory`, `weather`, `work`
Use tags to filter or categorize queries.
---
## Heartbeat Integration
During heartbeats, optionally check for new action items:
```python
# Check for recent action items (last 24h)
query = "action items from today"
# Parse response for new follow-ups
# Surface anything urgent
```
---
## Privacy & Security
- All recordings encrypted end-to-end
- Stored on US servers
- API key should remain in `~/.config/pocket-ai/api_key`
- Never log full transcripts to public channels
---
## Troubleshooting
**Empty recordings list?**
- Recordings may need device sync before API access
- Use search endpoint instead (works with synced transcripts)
**Auth errors?**
- Check Bearer token format: `Authorization: Bearer pk_xxx`
- Verify key in `~/.config/pocket-ai/api_key`
**Search returns nothing?**
- Try broader query terms
- Check if recordings have been synced recently
---
## Helper Scripts
### search.sh
```bash
#!/bin/bash
# Usage: ./search.sh "your query"
API_KEY=$(cat ~/.config/pocket-ai/api_key)
curl -s -X POST \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d "{\"query\": \"$1\"}" \
"https://public.heypocketai.com/api/v1/public/search"
```
### Python Helper
See `pocket_api.py` for full Python integration.Related Skills
Pocket Alert – Push Notifications for iOS and Android
The Pocket Alert (pocketalert.app) skill for OpenClaw enables OpenClaw agents and workflows to send push notifications to iOS and Android devices. It is used to deliver alerts and updates from automated tasks, workflows, and background processes.
gotchi-pocket
Manage Aavegotchi pocket wallets (escrow) on Base with Bankr. Use when the user wants to deposit ERC20 tokens into a gotchi pocket, withdraw ERC20 tokens from a pocket, check pocket balances/ownership by gotchi ID, or issue plain-English pocket commands.
pocket-money-manager
理财小助手,收支记录、消费分析、预算提醒。
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.