PaperTool

T

hc 3533e15995 fix(agent): require explicit image file reading in paper-image-extractor

The subagent was only reading text descriptions about images instead of
actually using the read tool on image files. This caused poor quality
reproductions based on guessed data rather than visual analysis.

Changes:
- Add CRITICAL instruction to use read tool on each image file
- Add Step 4: Verification step to compare generated vs original
- Add 'Extracting Data from Images' section with specific guidance
- Update guidelines to emphasize visual over textual extraction
- Allow scipy dependency for interpolation

2026-03-31 20:29:04 +08:00

.opencode

fix(agent): require explicit image file reading in paper-image-extractor

2026-03-31 20:29:04 +08:00

docs/superpowers

Initial commit: design spec and implementation plan

2026-03-31 17:29:53 +08:00

workspace

feat: add workspace directory for paper replication projects

2026-03-31 17:45:21 +08:00

opencode.json

feat: add opencode.json project configuration

2026-03-31 17:45:16 +08:00