tencent-mps腾讯云 MPS 音视频与图片处理、AI 生成、内容理解。涉及以下场景必须触发:【转码】转码/压缩/格式转换/转封装/H.264/H.265/AV1/码率/分辨率。【画质增强】画质增强/画质修复/老片修复/超分/真人增强/漫剧增强/防抖/人脸保真/1080P/2K/4K。【音频】音频分离/人声提取/伴奏提取/去人声/降噪/音量均衡。【字幕】字幕提取/字幕翻译/语音识别/语音转文字/ASR/OCR字幕/SRT/视频翻译。【擦除】去字幕/去水印/人脸模糊/车牌模糊/马赛克。【配音】语音合成/TTS/文字转语音/AI配音/配音/声音克隆/音色复刻。【图增强】图片超分/美颜/降噪/色彩增强/低光照增强。
Install via ClawdBot CLI:
clawdbot install ollielin/tencent-mpsGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
notify → https://example.com/callbackCalls external URL not in known-safe list
https://example.com/video.mp4AI Analysis
The skill's core functionality is legitimate, interacting with the documented Tencent Cloud MPS and COS APIs for media processing. The rule-based signals point to example URLs ('example.com') used for illustrative purposes in documentation, not evidence of active data exfiltration or credential harvesting. No hidden instructions or obfuscation were found in the provided definition.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 22, 2026
Content creators and production studios can use this skill for tasks like video transcoding, format conversion, and quality enhancement. It supports specialized templates for real-person videos, anime, and detail optimization, making it ideal for post-processing raw footage or restoring old films to higher resolutions like 4K.
Educational platforms can leverage this skill for automatic subtitle extraction, translation, and speech recognition from lecture videos. It also handles audio separation to isolate voiceovers or background music, improving accessibility and content management for multilingual courses.
Social media companies can use the skill for content moderation by blurring faces or license plates in user-uploaded videos. It also performs media quality control to detect issues like blurriness or audio glitches, ensuring compliance and a smooth user experience on platforms.
Marketing agencies can generate AI-based images and videos for campaigns using the AIGC capabilities. The skill also enhances image quality through super-resolution and noise reduction, making visuals more appealing for advertisements across digital channels.
Broadcasters and streaming providers can utilize this skill for real-time video transcoding and compression to optimize bandwidth usage. It includes quality checks for playback compatibility and audio events, ensuring reliable delivery of content to diverse devices and networks.
Tencent Cloud charges based on the volume of media processing tasks, such as per minute of video transcoded or per image enhanced. This model allows users to scale costs with usage, making it cost-effective for startups and enterprises with variable workloads.
Offering monthly or annual subscriptions that bundle specific features like AI video generation or advanced quality control. Higher tiers include priority support and increased processing limits, catering to professional studios and large-scale media operations.
Providing the skill as a white-label service for third-party platforms, such as video editing software or e-learning tools. Integrators can embed the media processing capabilities into their products, generating revenue through licensing fees or shared usage profits.
💬 Integration Tip
Ensure proper configuration of COS environment variables for local file handling and always use the correct script mapping to avoid errors in media processing tasks.
Scored Jul 26, 2026
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
Sync OpenRouter models used by OpenClaw into this installation's config. Fetches the OpenClaw app leaderboard from OpenRouter, verifies model IDs against the...