subtitle-refiner智能优化 SRT 字幕,去除语气词并修正 ASR 错误,保持时间戳不变,输出优化文件并发送飞书通知及 token 报告。
Install via ClawdBot CLI:
clawdbot install truetechlabs/subtitle-refinerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://api.siliconflow.cn/v1/chat/completions`Audited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
Content creators and educators use this skill to refine subtitles for online courses or tutorial videos, removing filler words and correcting ASR errors to enhance clarity and professionalism. It ensures subtitles remain synchronized with video timestamps, improving accessibility and viewer comprehension.
Companies apply this skill to optimize subtitles from recorded training sessions or meetings, cleaning up spoken language for formal documentation. It helps maintain accurate records by fixing speech recognition mistakes while preserving original timing for reference.
Production studios and media teams use the skill to polish subtitles for films, TV shows, or streaming content, ensuring high-quality captions by eliminating informal speech and ASR inaccuracies. This enhances viewer experience without altering video synchronization.
Organizations focused on accessibility leverage this skill to refine subtitles for deaf or hard-of-hearing audiences, improving readability by removing distractions like filler words and correcting errors. It supports compliance with accessibility standards while keeping timestamps intact.
Localization agencies use the skill to pre-process subtitles before translation, cleaning up source language subtitles to reduce noise and errors. This streamlines the localization workflow, ensuring accurate translations and consistent timing across different language versions.
Offer the skill as part of a monthly or annual subscription for content creators and businesses, providing unlimited subtitle refinements with token usage tracking. Revenue is generated through tiered pricing based on usage volume or additional features like priority support.
Monetize the skill by exposing its core functionality as an API, charging users per subtitle file processed based on token consumption. This model targets developers and enterprises needing scalable, on-demand subtitle optimization without upfront costs.
Sell customized licenses to large organizations such as media companies or educational institutions, including integration support, enhanced security, and bulk processing capabilities. Revenue comes from one-time licensing fees or annual contracts with maintenance.
💬 Integration Tip
Ensure the SILICONFLOW_API_KEY is properly set in the environment and test network connectivity to the API endpoint before deployment to avoid processing delays.
Scored Jun 19, 2026
视频自动剪辑助手。基于 FFmpeg 自动提取精彩片段、生成字幕、裁剪时长、制作短视视频,支持多平台导出。当用户需要:自动剪辑视频、提取关键词片段、生成字幕并烧录、导出短视频、提取视频精华、生成视频摘要时使用此技能。
Perform video editing tasks with ffmpeg, including cutting, merging, converting formats, extracting audio, adding subtitles, resizing, cropping, adjusting sp...
When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "reg...
Use when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a time-aligned TTS voice dub. Routes by...
Download videos, extract transcripts, capture frames. Analyze YouTube, tutorials, DD videos with yt-dlp + Whisper + ffmpeg.
Extract frames or short clips from videos using ffmpeg.