video-frame-understanding
Skill4 starsChanged 5 months agoNo licenceView on GitHub
Understand a local video by extracting frames at a fixed interval and using a local Ollama vision-language model to produce faithful screen-content understanding for each frame. Use when an agent needs faithful frame-level understanding of a local video file, especially technology conference videos, product launch videos, cloud summit recordings, demos, lectures, screen recordings, or presentation-heavy videos. Typical triggers include "analyze this conference video by frames", "把这个发布会视频按帧理解", "从这个产品发布视频里抽帧并解读画面", and "summarize visible slide content from this local video". The skill writes extracted frames, one compact script-generated JSON file per frame, a JSONL aggregate, and a faithful Chinese Markdown summary. Do not use for audio transcription, subtitle generation, dubbing, creative commentary, opinionated analysis, SWOT, strategy reports, or PPT generation.
- Installs packages
In this repository11 other files it gives its agents.
- agent-skill-collection-evaluatorSkill
- generate-and-process-subtitlesSkill
- infographic-prompt-builderSkill
- infographic-to-editable-pptSkill
- python-design-patternsSkill
- slide-infographic-reviewerSkill
- web-content-fetcherSkill
- x-daily-analystSkill
- x-scraperSkill
- youtube-scraperSkill
- youtube-to-bilingual-videoSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
37 rules. About 0 are common, 22 are distinctive, and 15 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈22
Distinctive · estimate
This author's own choices. Worth a look.
15
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.