Start Telegram monitoring. Auto-enables voice pipeline if ElevenLabs or OpenAI TTS keys are detected.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Read .claude/context/runtime/channel-daemon.pid. If it exists and has content, verify the PID is alive using node -e "try { process.kill(PID, 0); console.log('ALIVE') } catch { console.log('DEAD') }". If ALIVE, tell the user the daemon is already running and show them status commands. Done — do NOT try to start again.
Spawn a developer agent:
subagent_type: developer
prompt: Run this command and report the output: node scripts/channels/telegram-ctl.cjs start
Read .env and check for ELEVENLABS_API_KEY or OPENAI_API_KEY. If either is set, tell the user:
"Voice pipeline auto-enabled — voice messages will be transcribed (Whisper) and responded to with audio (ElevenLabs/OpenAI TTS)."
If neither is set, just say:
"Text-only mode. Add ELEVENLABS_API_KEY or OPENAI_API_KEY to .env for voice message support."
Tell the user what's active:
/ in Telegram for the menunode -e with process.kill(pid, 0) or http.get for health checksNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
The English summary is being prepared. Showing the original description.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
The English summary is being prepared. Showing the original description.
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
The English summary is being prepared. Showing the original description.
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
The English summary is being prepared. Showing the original description.
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
The English summary is being prepared. Showing the original description.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
The English summary is being prepared. Showing the original description.