scitex-ai/claude-code-telegrammer/claude-code-ywatanabe

Claude Code and agent skill by scitex-ai/claude-code-telegrammer

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Custom Claude Code Skills for ywatanabe

Install

npx vskill@latest install scitex-ai/claude-code-telegrammer/claude-code-ywatanabe

SKILL.md

Custom Claude Code Skills for ywatanabe

Sub-skills

  • orchestrator — Master orchestrator: delegate work, stay responsive, never block
  • emacs-mcp-server — Emacs MCP server workarounds, vterm control via eval_elisp
  • self-compact — Self-compact context via Emacs vterm when auto-compact fails
  • master-worker — Master-worker architecture: one Telegram bot, screen sessions per project
  • environmental-variables — Env var locations for ywatanabe's secrets
  • self-identify-vterm — Pattern for agents to find their own Emacs vterm buffer after compaction

When to Use

  • Orchestrating work via Telegram (plotting, speaking, launching agents, monitoring)
  • Debugging multi-agent Python systems
  • Setting up Claude Code infrastructure (channels, plugins)
  • File placement conventions
  • Controlling Emacs vterm from Claude Code
  • Launching and monitoring Claude Code instances in Emacs vterm

Core Guidelines

Debugging

Multi-agent debugging approach: @HOW-TO-DEBUG-with-MULTIPLE_AGENTS.md

Claude Code Channels (Telegram)

One bot serves all projects. Master agent at ~/proj holds the Telegram channel. Workers run per-project in screen sessions. See master-worker.md for the full setup.

Key files:

  • Screen functions: ~/.bash.d/all/010_claude/020_claude_agents_in_screen.src
  • Channel functions: ~/.bash.d/all/010_claude/010_claude_channels.src
  • Token: ~/.claude/channels/telegram/.env
  • Requires: Bun runtime, claude.ai login, v2.1.80+

Gotchas:

  • CLAUDE_ID env var causes _cld_start_session to silently abort — must unset CLAUDE_ID before launching in screen
  • Bun PATH must be in .bash.d (not just ~/.bash_profile) for screen sessions
  • screen -dmS needs bash --rcfile approach + stuff to get interactive shell with functions loaded
  • One bot per channel, not per project — master receives all messages and delegates
Emacs MCP Server (~/proj/emacs_mcp_server/)
  • eval_elisp works even when list_buffers and vterm tools are broken — use as fallback
  • vterm creation: (vterm "buffer-name") via eval_elisp
  • vterm send: (with-current-buffer "name" (vterm-send-string "cmd") (vterm-send-return))
  • vterm read: (with-current-buffer "name" (buffer-substring-no-properties ...))
File Placement Conventions
TypeLocationExample
Installer scripts~/.bin/installers/install_claude_channels.sh
Shell functions~/.bash.d/all/<category>/*.src010_claude_channels.src
DocumentationSame dir as .src or skill dirCHANNELS_SETUP.md
Helper binaries~/.local/bin/NOT ~/.bin/ directly
CLI tools~/.bin/<category>/ subdir~/.bin/claude/, ~/.bin/emacs/

Never place raw binaries directly in `~/.bin/` — use ~/.local/bin/ or ~/.bin/<category>/ subdirs.

Environment Variables

Private env vars (Twilio, email, Claude Code tokens) live in:

  • ~/.dotfiles/src/.bash.d/secrets/
  • ~/.dotfiles/src/.bash.d/secrets/010_scitex

Always keep these up-to-date when adding new service credentials. See environmental-variables.md.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Refreshed 5 Nov 2026, 2 days ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/scitex-ai/claude-code-telegrammer/claude-code-ywatanabe/badge)](https://verified-skill.com/skills/scitex-ai/claude-code-telegrammer/claude-code-ywatanabe)

Something wrong with this skill or its page? Tell us.