Development · SKILL.md

asr

asr

Unified ASR (Speech Recognition) skill with pluggable providers (strategy pattern). Supports: SiliconFlow (TeleAI/TeleSpeechASR). Use for transcribing audio/video files to text. Trigger: "转录", "识别语音", "语音转文字", "ASR", "transcribe", "语音识别". Auto-extracts audio from video files via ffmpeg.

Independent GitHub snapshot · Automated classification · Original documentation governs

Hhwj123hwj / custom-skillsNOASSERTION

Skill documentation

GitHub

Loading documentation from the source…

MAKE IT PART OF YOUR WORKFLOW

Install skill

TERMINAL

npx skills add hwj123hwj/custom-skills --skill asr

Run the command in your terminal. Review the code and license before installing.

Check the original repository for this skill’s terms and download options.

Source code

Repository stars: Not synced
License: NOASSERTION
Version / branch: HEAD · 0d687374
Repository updated: Not synced

Review scripts and permissions before installing.

Source code

asr

Skill documentation

More skills to explore

brainstorming

systematic-debugging

test-driven-development