extracting-structure
Pull structured data from videos you've already watched: titled chapters with timestamps for long content, pinpointed bug reports with error frames and OCR text, or opening-hook analysis scored across attention, pacing, visuals, and on-screen text. All answers come straight from the persistent index with no extra model calls.
Extracting Structure pulls chapters, bug reports, and hook analysis from watched videos with exact timestamps and frame data.
AI-generated summary based on this skill's SKILL.md
Install
oxbshw/watch-skill/extracting-structure · repository language: Python
git clone https://github.com/oxbshw/watch-skill
cp -r watch-skill/adapters/claude-skill/skills/extracting-structure ~/.claude/skills/extracting-structurenpx skillfed install oxbshw/watch-skill/extracting-structureFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I extract chapters from video with timestamps?
extracting-structure pulls titled chapters with exact timestamps directly from videos you've already watched. The skill indexes your content and returns structured chapter data without requiring re-processing. Use this to organize long-form videos into navigable segments for viewers or your own reference.
Can extracting-structure turn screen recordings into bug reports?
Yes. extracting-structure analyzes screen recordings to locate bugs, pinpoint exact frames where errors occur, and extract on-screen error text via OCR. It then structures this data into a fileable bug report complete with reproduction steps, so you can hand it directly to developers without manual transcription.
Where does the bug appear in this recording?
extracting-structure identifies the exact frame and location where bugs surface in your screen recording. It captures error messages visible on screen and timestamps the moment the issue occurs, giving you precise coordinates to reference when filing reports or communicating with your team.
How does extracting-structure score video intro quality?
extracting-structure analyzes your opening sequence across multiple axes: attention capture, pacing, visual composition, and on-screen text effectiveness. It delivers actionable critiques on hook strength so you can refine your intro performance and improve viewer retention from the first frames.
Does extracting-structure require re-watching videos?
No. extracting-structure works from a persistent index of videos you've already watched, so all answers—chapters, bug locations, hook scores—come straight from that index with no extra model calls or re-processing needed. Results are instant and consistent.
What license does extracting-structure use?
extracting-structure is released under the MIT license, allowing you to use, modify, and distribute it freely within the terms of that license.
SKILL.md
rendered from the published skill — quoted content, verbatim
Extracting structure
Three extractors turn an already-watched video into something structured.
All of them answer straight from the persistent index — deterministic, no
extra model calls. The video must be watched first (see watching-videos).
Chapters
watch-skill extract chapters <video_id-or-source>
Titled chapters with start/end timestamps, built from scene changes plus transcript topic shifts. Good for long tutorials, lectures, meetings — give the user the chapter list with timestamps, not a prose summary.
Bug report from a screen recording
watch-skill extract bug-report <video_id-or-source>
Pinpoints where an error appears: timestamp, the exact frame,
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
adapters/claude-skill/skills/extracting-structure/SKILL.md