media-qc
Skill0 starsChanged 20 days agoMITView on GitHub
对粗样片或成片做媒体技术检查，并记录绑定实际视频版本、带时间码的视听审稿观察与局部返修建议。适用于制作中和交付前审查；工具不自动看片听音，技术通过不代替人工接受。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- badgids/Story-Film-Skillstheir own version, first seen Aug 19, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- badgids/Story-Film-Skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- asset-scoutSkill
- audio-postSkill
- auto-subtitleSkill
- content-directorSkill
- daily-ai-newsSkill
- humanizerSkill
- narrationSkill
- pptSkill
- publishSkill
- video-motionSkill
- web-captureSkill
The file
Files
成片审查
运行 node skills/media-qc/scripts/check.mjs --project <项目> --video render/video.mp4。依赖 FFmpeg/ffprobe，不需要 npm 包；可选 --srt captions.srt、--require-audio、--allow-preview。输出项目 qa/media-report.json 和抽帧图。
项目可提供 qc.json，设置 width/height/fps/duration、字幕阅读速度、响度范围和真峰值上限。这些是项目交付参数，不声称是所有平台的统一标准。
检查容器/编码/帧率/时长、完整解码、全黑片、静止区间、字幕顺序/越界/阅读速度和音频响度。读取同名渲染报告时拒绝把部分渲染当全片，报告 DOM 溢出。静止镜头和短黑场先标记人工检查，不单凭像素判定叙事质量。
机器报告为 technical-pass-needs-human-review 或 failed。人工必须看：手机尺寸可读性、画面主体与事实一致、进出镜节奏、旁白同步、音乐是否盖人声、封面及平台控件遮挡。记录看片者和结论；没有人工记录就保留 pending。
产品演示额外对照导演的演示安排，看起点、关键操作与对应结果是否真实连续，鼠标/圈注是否指向当时对象。系列内容按系列一致性对照本期与实际系列样例，检查字幕、封面及声音；这两项属于实际观察，现有技术检查不会自动判断。
只对已知制作输入做修复；字幕识别问题交 auto-subtitle，画面设计交 content-director，来源问题回事实材料核查。不要为了绿色报告放宽目标或自动填入人工通过。
实际看片/听音后按视听审稿与返修记录观察：node scripts/studio.mjs inspect --project <项目>。技术报告附 videoSha256，审稿需绑定实际已查看版本；只记录已查看的区间，未听音就标未审听。再次使用结果用 inspect --verify 校验媒体版本，改片后受影响部分需重审。这个工具负责记录和一致性检查，不生成审美判断或人类批准。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.