技能列表

>-

|

>

>

Choose public search tags for Dribbble and Pinterest, run public search flows without login, and extract normalized result fields such as title, high-resolution image, author, source URL, and publish/update time when available. Use when Codex needs to collect design inspiration from Dribbble or Pinterest, design a keyword taxonomy for B-end/data-visualization themes, or explain how to get public search result fields from these two platforms.

Synthetic dreaming system — emotional tracking, dream orchestration, and simulated dream experiences for an AI that doesn't sleep.

>

Reusable framework skill for designing and setting up strategy-job trading systems with shared engine logic, config-driven jobs, pluggable market-data providers, paper-first execution, approval-gated buy/sell workflow, and daily assessment reporting. Use when creating, installing, extending, or auditing a local trading-system deployment, especially when the user wants a conversational setup wizard, provider configuration, watchlists, strategy/job configs, paper-trading flows, or daily assessment

Audio/video transcription module using Docker Whisper ASR. Extract speech from audio or video files and convert to text. Use when: (1) Transcribing audio files (mp3, wav, m4a, etc.), (2) Transcribing video files (mp4, mkv, etc.), (3) Need speech-to-text for any media file, (4) Working with douyin/tiktok video transcription workflows. Supports automatic audio extraction, format conversion, and multiple Whisper models.

|

抖音视频转录工作流编排。从抖音链接下载视频、转录语音、分析内容，输出结构化成果。编排调用 douyin-fetcher、douyin-transcriber、douyin-analyzer 三个独立模块。

抖音视频获取模块。从抖音链接下载视频文件，支持短视频和 DASH 格式长视频。