---
title: "Reconstructed Slides: Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic"
category: "slides"
video_id: "TqC1qOfiVcQ"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic

## Source Video
[Claude Agent SDK (Full Workshop) — Thariq Shihipar, Anthropic](https://www.youtube.com/watch?v=TqC1qOfiVcQ)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `163.79`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `164.75`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.79`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `172.29`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.88`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.68`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `168.39`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.02`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `169.37`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.87`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `172.97`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `171.27`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `173.03`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.41`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.59`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `163.45`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.82`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-018.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `165.33`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-019.jpg]]

- Source frame: `slide-020.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `162.65`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-020.jpg]]

- Source frame: `slide-021.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `173.05`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-021.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `165.43`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-022.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.44`
![[assets/reconstructed-slides/TqC1qOfiVcQ/slide-023.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `168.66`
## Dense Scene-Detected Slide Candidates
- [[youtube-TqC1qOfiVcQ-dense-slides]]