内部技能，仅用于数字人 / VideoRetalk / 资产库角色口播视频链路中的 CosyVoice TTS 子步骤。普通 AI 聊天、普通音频、普通短视频、产品视频或广告视频请求不得直接调用本技能；这些视频请求必须先走 video-director。只有 video-director 已确认这是数字人口播，且需要把已批准的台词合成为角色驱动音频时，才可激活本技能。
Use when the user wants to做一整套图片、组图、卡片图、轮播图、配图包或电商套图. First identify the user's motive and final goal, then choose the right image-set type and ordering strategy, lock the batch-level subject anchor, keep the style guide concise, define text placement and…
Distill team members from profile, files, and YouTube subtitles into session-activated member skills.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Use when the user wants to plan or generate a social media cover image for a Xiaohongshu note, Douyin/TikTok photo post, Reels/Shorts cover, WeChat/Video Account post, Bilibili/Weibo post, Pinterest pin, Instagram cover, Facebook/Meta social post, or similar…
Use when generating expressive TTS, short-video voiceover, self-media narration, product explanation, ads, livestream clips, character speech, podcast-style voiceover, or any speech request that needs tone, speed, pitch, rhythm, pauses, or multi-segment…
Canonical entrypoint for every AI chat request that asks to make, generate, plan, or edit a video, including promotional films, ads, short videos, product videos, reference-image videos, image-to-video, first/last-frame transitions, storyboard/keyframes,…
What Would User Do for RedConvert. Infer how the current app user would decide, approve, reject, scope, phrase, prioritize, or route work inside RedClaw, automation approvals, creative workflows, manuscript/media decisions, advisor/member discussions, and…