agent/claude/code/skills/community-chat/SKILL.md
Snider 9942ab8081 refactor: restructure as plugin monorepo
Reorganise as a marketplace with multiple focused plugins:
- claude/code: Core development (hooks, scripts, data collection)
- claude/review: Code review automation
- claude/verify: Work verification
- claude/qa: Quality assurance loops
- claude/ci: CI/CD integration

Structure:
- .claude-plugin/marketplace.json lists all plugins
- Each plugin has its own .claude-plugin/plugin.json
- Commands namespaced: /code:*, /review:*, /qa:*, etc.

Install individual plugins or all via marketplace:
  claude plugin add host-uk/core-agent
  claude plugin add host-uk/core-agent/claude/code

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-01 19:44:26 +00:00

1.9 KiB

Community Chat Collector

Archive Discord and Telegram community discussions.

Challenges

Platform Access Automation
Discord Bot token or user export Discord.py, DiscordChatExporter
Telegram User account or bot Telethon, telegram-export

Tools

Discord

Telegram

Manual Export

Discord Data Request

  1. User Settings → Privacy & Safety
  2. Request all of my Data
  3. Wait for email (can take days)
  4. Download and extract

Telegram Export

  1. Desktop app → Settings → Advanced
  2. Export Telegram Data
  3. Select chats and data types
  4. Download zip

Usage

# Generate job list for manual processing
./generate-jobs.sh lethean > jobs.txt

# Process exported Discord data
./process-discord.sh ./discord-export/ --output=./chat-archive/

# Process exported Telegram data
./process-telegram.sh ./telegram-export/ --output=./chat-archive/

Output

chat-archive/lethean/
├── discord/
│   ├── general/
│   │   ├── 2019.json
│   │   ├── 2020.json
│   │   └── ...
│   ├── development/
│   └── channels.json
├── telegram/
│   ├── main-group/
│   └── announcements/
└── INDEX.md

Known Communities

Lethean

Monero

  • Multiple community discords
  • IRC archives (Libera.chat)

Notes

  • Respect rate limits and ToS
  • Some messages may be deleted - export doesn't get them
  • Media files can be large - consider text-only first
  • User privacy - consider anonymization for public archive