mcpField
E
extracting-structure

extracting-structure

github.com/oxbshwCreative & media533531 installsUpdated 7w ago
Repository

About extracting-structure

extracting-structure provides commands for deriving chapters, bug reports, and opening-hook analyses from videos already indexed by watch-skill. It is for people reviewing long recordings, screen-recorded errors, or creator videos; results come from the persistent index without additional model calls.

Key features

  1. 01Chapters with titles and timestamps
  2. 02Bug location, frame, and OCR text
  3. 03Failure steps from preceding activity
  4. 04Hook scoring across four measured axes
  5. 05Deterministic extraction without model calls

Use cases

  1. 01Create timestamped chapters for a lecture
  2. 02Prepare a bug report from a screen recording
  3. 03Review the opening of a creator video

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/oxbshw/watch-skill --skill extracting-structure

After installing, type/extracting-structurein Claude Code to confirm it loaded.

Details

From the project README

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, the on-screen error text as OCR read it, and the steps that led up to it (from the transcript/actions preceding the failure). Returns found: false honestly when no error signal exists — report that as "no error found in the recording", not as an error.

Paste the output into the user's issue tracker format when they ask for a fileable report; the frame path is the attachment.

Hook analysis (creators)

watch-skill extract hook <video_id-or-source> [--seconds 15]

Scores the opening seconds on four measured axes — attention trigger in the opening line, speech pacing, visual change rate, on-screen text — each with an actionable critique, plus a 0–100 score and verdict. Give the user the per-axis critiques; the number alone helps nobody.

Comments

Markdown supported