Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Start Telegram monitoring. Auto-enables voice pipeline if ElevenLabs or OpenAI TTS keys are detected.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
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 checks还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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
中文简介正在准备中。当前显示原文说明。