How do I install the Remove Scan Seam skill?

Run npx skillmds@latest add lzhzlw/remove-scan-seam in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Remove Scan Seam safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Remove Scan Seam?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Remove Scan Seam free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Remove Scan Seam?

lzhzlw (@lzhzlw) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Remove Scan Seam by lzhzlw — Agent Skill

Name: Remove Scan Seam
Rating: 4.5 (4 reviews)
Author: lzhzlw

Remove Scan Seam

Removes vertical center seam red lines from scanned book/atlas images and PDFs using OpenCV TELEA inpainting. Use when the user mentions 中缝版, scan seam, red line removal, gutter line, 红线, 扫描修复, or asks to fix scanned map/atlas pages.

lzhzlw Updated Sep 22, 2026

File contents

Remove Scan Seam Red Line

Remove the vertical red center seam from scanned "中缝版" (gutter edition) images or PDFs.

Prerequisites

Python 3.10+ with:

pip install -r scripts/requirements.txt

On this machine, Python is typically at: %LOCALAPPDATA%\Programs\Python\Python312\python.exe

Quick commands

Run from the skill directory or use absolute script path.

Single image:

python scripts/remove_seam.py --image "path/to/scan.jpg"

Folder of images (skips files already named *_已修复*):

python scripts/remove_seam.py --folder "path/to/folder"

PDF (renders each page, inpaints, rebuilds PDF):

python scripts/remove_seam.py --pdf "path/to/scan.pdf"
python scripts/remove_seam.py --pdf "path/to/scan.pdf" --dpi 300

Custom output path:

python scripts/remove_seam.py --image input.jpg --output output.jpg

Output naming

Input	Default output
`foo.jpg`	`foo_已修复.jpg`
`【中缝版】地图集.pdf`	`地图集_已修复.pdf`

Original files are never modified.

Method

Detect reddish pixels near horizontal center (red - max(g,b) > 42, r > 145)
Build a narrow vertical mask around the seam
OpenCV INPAINT_TELEA on a center strip only (not full-image linear interpolation)
Feather strip edges back into the original
For PDFs: render at 250 DPI (default), process each page, reassemble

Agent workflow

Confirm input path(s) — image, folder, or PDF
Verify Python + deps; install if missing
Run scripts/remove_seam.py with the right flag
Report output paths and page/file counts
Do not use wide linear interpolation — it smears the gutter worse than the red line

Limitations

Book gutter misalignment (left/right page offset) cannot be fully corrected by inpainting
PDF output is rasterized (image-based pages), not vector-preserving
Higher --dpi improves quality but increases time and file size

Skill location

Personal skill: ~/.cursor/skills/remove-scan-seam/

---name: remove-scan-seamdescription: Removes vertical center seam red lines from scanned book/atlas images and PDFs using OpenCV TELEA inpainting. Use when the user mentions 中缝版, scan seam, red line removal, gutter line, 红线, 扫描修复, or asks to fix scanned map/atlas pages.---# Remove Scan Seam Red LineRemove the vertical red center seam from scanned "中缝版" (gutter edition) images or PDFs.## PrerequisitesPython 3.10+ with:```bashpip install -r scripts/requirements.txt```On this machine, Python is typically at:`%LOCALAPPDATA%\Programs\Python\Python312\python.exe`## Quick commandsRun from the skill directory or use absolute script path.**Single image:**```bashpython scripts/remove_seam.py --image "path/to/scan.jpg"```**Folder of images** (skips files already named `*_已修复*`):```bashpython scripts/remove_seam.py --folder "path/to/folder"```**PDF** (renders each page, inpaints, rebuilds PDF):```bashpython scripts/remove_seam.py --pdf "path/to/scan.pdf"python scripts/remove_seam.py --pdf "path/to/scan.pdf" --dpi 300```**Custom output path:**```bashpython scripts/remove_seam.py --image input.jpg --output output.jpg```## Output naming| Input | Default output ||-------|----------------|| `foo.jpg` | `foo_已修复.jpg` || `【中缝版】地图集.pdf` | `地图集_已修复.pdf` |Original files are never modified.## Method1. Detect reddish pixels near horizontal center (`red - max(g,b) > 42`, `r > 145`)2. Build a narrow vertical mask around the seam3. OpenCV `INPAINT_TELEA` on a center strip only (not full-image linear interpolation)4. Feather strip edges back into the original5. For PDFs: render at 250 DPI (default), process each page, reassemble## Agent workflow1. Confirm input path(s) — image, folder, or PDF2. Verify Python + deps; install if missing3. Run `scripts/remove_seam.py` with the right flag4. Report output paths and page/file counts5. Do **not** use wide linear interpolation — it smears the gutter worse than the red line## Limitations- Book gutter misalignment (left/right page offset) cannot be fully corrected by inpainting- PDF output is rasterized (image-based pages), not vector-preserving- Higher `--dpi` improves quality but increases time and file size## Skill locationPersonal skill: `~/.cursor/skills/remove-scan-seam/`

Frequently asked questions