@tangc

feishu-send-voice converts text to speech via edge-tts, transcodes to opus/ogg, then sends as a feishu audio message to avoid text degradation. requires ffmpeg, edge-tts, and feishu api credentials.

jimeng-t2i-i2i-image-generator wraps volcengine's jimeng ai 4.0 for text-to-image and image-to-image generation, with optional feishu delivery. docs are in chinese, procedures are command-based but lack failure handling.

tangzhan-skill-opencodeinsights is positioned to analyze session history and report on work patterns and friction points. the skill definition is incomplete and does not establish clear output contracts, trigger conditions, or concrete recovery paths.

执行每日 Agent 复盘行动（Retro）。读取指定日期（通常是昨天）的所有 session 聊天记录和动作，总结做对/做错的事情、提炼改进点与用户画像，并规范化地更新至 memory 文件及 USER.md、SOUL.md、AGENTS.md 和 MEMORY.md。当用户要求复盘、总结昨天表现时触发此技能。