Heypocket Reader
Apps & Automationheypocket-readerHeypocket Reader is an Agent Skill for apps & automation published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Read transcripts and summaries from Pocket AI (heypocket.com) recording devices. Use when users want to retrieve, search, or analyze their Pocket recordings, transcripts, summaries, or action items.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/heypocket-reader/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/heypocket-reader, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
heypocket-reader
Access Pocket AI recordings via reverse-engineered API.
Quick Reference
| Function | Description |
|---|---|
get_recordings(days, limit) | List recent recordings |
get_recording_full(id) | Get transcript + summary + action items + speakers |
search_recordings(query, lat, lon, radius_km, days=90) | Search by title/description/tags and/or location |
Setup
- Start Chrome:
--remote-debugging-port=9222with your profile - Log into https://app.heypocket.com
- Extract token:
python3 scripts/reader.py extract
Token expires in 1 hour. Re-run extract when needed.
Usage
from reader import get_recordings, get_recording_full, search_recordings
# List recordings
for r in get_recordings(days=30):
print(f"{r.recorded_at:%Y-%m-%d} | {r.title}")
# Get full data
full = get_recording_full(recording_id)
full['transcript'] # Raw text (50k+ chars)
full['summary'] # Markdown
full['action_items'] # List
full['speakers'] # Dict with speaker profiles
# Search by title/description/tags
search_recordings(query="meeting")
# Search by location
search_recordings(lat=51.51, lon=-0.13, radius_km=25)
# Combined
search_recordings(query="AI", lat=51.51, lon=-0.13, radius_km=25)
Transcript Search
Not built-in (expensive: 1 API call per recording). To implement:
for r in get_recordings(days=30):
full = get_recording_full(r.id)
if "search term" in full['transcript'].lower():
print(f"Found in: {r.title}")
Data
PocketRecording: id, title, description, duration, duration_str, recorded_at, num_speakers, latitude, longitude, tags
get_recording_full(): Returns recording, transcript, summary, action_items, speakers