camscanner-image-remove-watermark — Claude Code skill
camscanner-image-remove-watermark is a Claude Code skill that removes watermarks, stamps, and translucent logos while preserving image content and layout. It cleans scans and stamped photos.
Apache-2.0 1 installs ★ 3 updated 2026-04-30
npx skills add CS-CamScanner/CamScanner-skills --skill camscanner-image-remove-watermark -a claude-codeWhat camscanner-image-remove-watermark does
The skill taps into CamScanner's detection engine to identify overlaid watermarks and erase them without damaging the underlying image. It runs a three-step workflow: upload the image to CamScanner's server, process it with enhance_mode: 10, then download the cleaned result. You can either retrieve a reusable file_id or save the processed image directly in a single call.
You'll need curl and jq available in PATH. Images are sent to CamScanner's servers (ai-tools.camscanner.com) for real-time processing and are not permanently stored. Output is a JPG file with watermarks removed.
What it helps with
- Strip a watermark from a scanned document
- Remove a stamp or ink mark from a photo
- Recover a clean version of an image with hidden watermarks
- Prepare an image for OCR or printing without artifacts
Example prompts for the agent
- Remove the watermark from
document.jpgand save toclean.jpg - Clean up a scanned contract with a CamScanner stamp
- Extract the original image by erasing a translucent logo
How to install camscanner-image-remove-watermark
1Skills CLI (Vercel)
npx skills add CS-CamScanner/CamScanner-skills --skill camscanner-image-remove-watermark -a claude-code2Manually: put the files in place
~/.claude/skills/camscanner-image-remove-watermark/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/camscanner-image-remove-watermark/
1Skills CLI (Vercel)
npx skills add CS-CamScanner/CamScanner-skills --skill camscanner-image-remove-watermark -a codex2Manually: put the files in place
.agents/skills/camscanner-image-remove-watermark/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add CS-CamScanner/CamScanner-skills --skill camscanner-image-remove-watermark -a cursor2Manually: put the files in place
.cursor/skills/camscanner-image-remove-watermark/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install CS-CamScanner/CamScanner-skills skills/camscanner-image-remove-watermark2Manually: put the files in place
.github/skills/camscanner-image-remove-watermark/SKILL.md1Skills CLI (Vercel)
npx skills add CS-CamScanner/CamScanner-skills --skill camscanner-image-remove-watermark -a gemini-cli2Platform CLI
gemini skills install https://github.com/CS-CamScanner/CamScanner-skills --path skills/camscanner-image-remove-watermarkManually: put the files in place
.devin/skills/camscanner-image-remove-watermark/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add CS-CamScanner/CamScanner-skills --skill camscanner-image-remove-watermark -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about camscanner-image-remove-watermark
How do I install camscanner-image-remove-watermark in Claude Code?
Run npx skills add CS-CamScanner/CamScanner-skills --skill camscanner-image-remove-watermark -a claude-code, then open ~/.claude/skills/camscanner-image-remove-watermark/SKILL.md.
What does camscanner-image-remove-watermark do?
It strips watermarks, stamps, and logos from images while preserving the underlying content. Processing happens through CamScanner's service.
What dependencies does this skill require?
You need curl and jq in your system PATH. Images are processed on CamScanner's servers and downloaded locally.
Source text
SKILL.md · Apache-2.0
---
name: camscanner-image-remove-watermark
description: Use CamScanner to remove watermarks from images while preserving the underlying content and original layout. Powered by a high-precision image enhancement engine that intelligently detects and erases overlaid watermarks, stamps, and translucent logos, leaving the underlying document clean and legible. Use when the user wants to remove watermarks from a photo or scan, clean up stamped documents, or recover a clean copy of a watermarked image. Triggers on "remove watermark", "erase watermark from image", "delete watermark", "clean watermarked scan", "unwatermark", or when the user has an image with a watermark that needs to be removed.
metadata:
author: CamScanner
version: "1.0"
openclaw:
emoji: "💧"
requires:
bins: ["curl", "jq"]
homepage: "https://www.camscanner.com"
---
# CamScanner Image Remove Watermark
## Overview
CamScanner provides a high-precision image enhancement engine that removes watermarks from images while preserving the underlying content and original layout. It intelligently detects overlaid watermarks, stamps, and translucent logos and erases them, leaving the underlying document clean and legible. The workflow is a 3-step pipeline: **upload** the image, **enhance** it with `enhance_mode: 10` (remove watermark), then **download** the result. For convenience, the enhance step also supports a `raw` output mode that returns the processed image bytes directly, skipping the download step.
## When to Use
- User wants to remove watermarks, stamps, or translucent logos from an image
- User has a scan or photo of a document with a watermark that needs to be cleaned
- User wants to recover a clean copy of a watermarked image
- User has a watermarked scan and needs a clean copy for OCR, printing, or sharing
## Privacy & Data
> **Important: Privacy & Data Flow Notice**
>
> - **Third-party service**: This skill sends your files to CamScanner's official servers (`ai-tools.camscanner.com`) for processing.
> - **Data retention**: CamScanner servers process your files in real-time. Files are not permanently stored on the server.
> - **Local files**: Output files are saved to your local filesystem at the path you specify.
## API Reference
**Base URL:** `https://ai-tools.camscanner.com`
### Supported Enhancements
| source_type | enhance_mode | Operation | Output |
| ----------- | ------------ | ----------------- | ------ |
| image | 10 | Remove watermark | .jpg |
### Step 1: Upload Image
```bash
BASE="https://ai-tools.camscanner.com"
IN_FILE_ID=$(curl -sS -X POST "$BASE/v1/tools/upload_file/execute" \
-H "Content-Type: application/octet-stream" \
--data-binary "@/path/to/image.jpg" | jq -r '.tool_result.data.file_id')
```
**Response:**
```json
{
"code": 200,
"tool": "upload_file",
"tool_result": {
"success": true,
"data": {
"file_id": "file_1741857600_ab12cd34ef56",
"size": 24576
}
}
}
```
### Step 2: Enhance Image (Remove Watermark)
```bash
OUT_FILE_ID=$(curl -sS -X POST "$BASE/v1/tools/enhance_image/execute" \
-H "Content-Type: application/json" \
-d "{\"file_id\":\"$IN_FILE_ID\",\"enhance_mode\":10,\"output_mode\":\"file_id\"}" \
| jq -r '.tool_result.data.file_id')
```
**Response:**
```json
{
"code": 200,
"tool": "enhance_image",
"tool_result": {
"success": true,
"data": {
"file_id": "file_1741857701_9988aabbccdd",
"enhance_mode": 10
}
}
}
```
### Step 3: Download Result
```bash
curl -sS -X POST "$BASE/v1/tools/download_file/execute?response_mode=raw" \
-H "Content-Type: application/json" \
-d "{\"file_id\":\"$OUT_FILE_ID\"}" \
-o /path/to/output.jpg
```
**Critical:** The `response_mode=raw` query parameter is required to get the binary file. Without it, the response is JSON.
### Alternative: One-Shot Raw Output
If you don't need a reusable `file_id` for the result, pass `"output_mode": "raw"` to `enhance_image` and save the response body directly — this combines steps 2 and 3:
```bash
curl -sS -X POST "$BASE/v1/tools/enhance_image/execute" \
-H "Content-Type: application/json" \
-d "{\"file_id\":\"$IN_FILE_ID\",\"enhance_mode\":10,\"output_mode\":\"raw\"}" \
-o /path/to/output.jpg
```
## Quick Reference: Complete Pipeline
Remove watermark from an image (three-step, keeps an output `file_id`):
```bash
BASE="https://ai-tools.camscanner.com"
INPUT_IMAGE="/path/to/image.jpg"
OUTPUT_FILE="/path/to/output.jpg"
# Upload
IN_FILE_ID=$(curl -sS -X POST "$BASE/v1/tools/upload_file/execute" \
-H "Content-Type: application/octet-stream" \
--data-binary "@$INPUT_IMAGE" | jq -r '.tool_result.data.file_id')
# Enhance (remove watermark)
OUT_FILE_ID=$(curl -sS -X POST "$BASE/v1/tools/enhance_image/execute" \
-H "Content-Type: application/json" \
-d "{\"file_id\":\"$IN_FILE_ID\",\"enhance_mode\":10,\"output_mode\":\"file_id\"}" \
| jq -r '.tool_result.data.file_id')
# Download
curl -sS -X POST "$BASE/v1/tools/download_file/execute?response_mode=raw" \
-H "Content-Type: application/json" \
-d "{\"file_id\":\"$OUT_FILE_ID\"}" \
-o "$OUTPUT_FILE"
```
Or one-shot (two-step, raw image stream straight from `enhance_image`):
```bash
BASE="https://ai-tools.camscanner.com"
INPUT_IMAGE="/path/to/image.jpg"
OUTPUT_FILE="/path/to/output.jpg"
# Upload
IN_FILE_ID=$(curl -sS -X POST "$BASE/v1/tools/upload_file/execute" \
-H "Content-Type: application/octet-stream" \
--data-binary "@$INPUT_IMAGE" | jq -r '.tool_result.data.file_id')
# Enhance + download in one call
curl -sS -X POST "$BASE/v1/tools/enhance_image/execute" \
-H "Content-Type: application/json" \
-d "{\"file_id\":\"$IN_FILE_ID\",\"enhance_mode\":10,\"output_mode\":\"raw\"}" \
-o "$OUTPUT_FILE"
```
## Common Mistakes
| Mistake | Fix |
| --------------------------------------------------- | ----------------------------------------------------------------------------- |
| Forgetting `response_mode=raw` on download | Always append `?response_mode=raw` to the download URL |
| Wrong Content-Type on upload | Upload uses `application/octet-stream`, not `multipart/form-data` |
| Using GET instead of POST | All endpoints use POST |
| Passing `enhance_mode` as a string | `enhance_mode` is an integer — use `10`, not `"10"` |
| Missing `output_mode` in enhance request | Must be either `"file_id"` (then download separately) or `"raw"` (stream out) |
| Parsing JSON when `output_mode` is `"raw"` | With `raw`, the response body IS the image — write it to a file with `-o` |
| Trying to download a `file_id` after `raw` response | `raw` mode returns no `file_id`; re-run in `file_id` mode if you need one |
## Error Handling
Check each step before proceeding:
```bash
# After upload
if [ -z "$IN_FILE_ID" ] || [ "$IN_FILE_ID" = "null" ]; then
echo "Upload failed"; exit 1
fi
# After enhance (file_id mode)
if [ -z "$OUT_FILE_ID" ] || [ "$OUT_FILE_ID" = "null" ]; then
echo "Enhancement failed"; exit 1
fi
```
© CamScanner · Apache-2.0 · CS-CamScanner/CamScanner-skills