Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
gemini-watermark-remover - Skill - OpenSmartRoute
Skillv1.0.0
gemini-watermark-remover
Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the…
Imported from rookie-ricardo/erduo-skills (skills/gemini-watermark-remover/SKILL.md) via skills.sh. Install upstream with npx skills add rookie-ricardo/erduo-skills --skill gemini-watermark-remover. Copyright stays with the author.
Gemini Watermark Remover
Dependencies
Python 3.9+
Pillow (install with pip install -r requirements.txt)
Quick start
Install dependencies in the scripts folder:
cd skills/gemini-watermark-remover/scripts && pip install -r requirements.txt
references/algorithm.md: Math, detection rules, and limits.
Workflow
Use remove_watermark.py for one-off processing.
If you need to adjust detection rules or alpha logic, read references/algorithm.md.
Notes
The script uses Pillow for image IO and per-pixel edits.
Output format is inferred from the output file extension by Pillow.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
Installed into a catalogue, chosen by a router
Install gemini-watermark-remover and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "rookie-ricardo-erduo-skills-gemini-watermark-remover",
"kind": "skill",
"name": "gemini-watermark-remover",
"description": "Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components.",
"publisher": "rookie-ricardo",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"math"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/rookie-ricardo/erduo-skills",
"path": "skills/gemini-watermark-remover/SKILL.md",
"ref": "HEAD",
"url": "https://www.skills.sh/rookie-ricardo/erduo-skills/gemini-watermark-remover",
"key": "rookie-ricardo/erduo-skills/skills/gemini-watermark-remover/SKILL.md"
}
},
"instructions": "# Gemini Watermark Remover\n\n## Dependencies\n\n- Python 3.9+\n- Pillow (install with `pip install -r requirements.txt`)\n\n## Quick start\n\n1) Install dependencies in the scripts folder:\n - `cd skills/gemini-watermark-remover/scripts && pip install -r requirements.txt`\n2) Run the CLI:\n - `python remove_watermark.py <input-image> <output-image>`\n\n## CLI usage\n\n- Parameters:\n - `input-image`: path to the Gemini watermarked image\n - `output-image`: path for the cleaned image (format inferred from extension)\n\nExample:\n\n```\npython remove_watermark.py ./in.png ./out.png\n```\n\n## What this skill provides\n\n- `scripts/remove_watermark.py`: CLI entry point and core algorithm.\n- `assets/bg_48.png`, `assets/bg_96.png`: Pre-captured watermark alpha maps.\n- `references/algorithm.md`: Math, detection rules, and limits.\n\n## Workflow\n\n1) Use `remove_watermark.py` for one-off processing.\n2) If you need to adjust detection rules or alpha logic, read `references/algorithm.md`.\n\n## Notes\n\n- The script uses Pillow for image IO and per-pixel edits.\n- Output format is inferred from the output file extension by Pillow.",
"cost": {
"context_tokens": 277
}
}
Fetch it by URL: GET /api/v1/registry/rookie-ricardo-erduo-skills-gemini-watermark-remover/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.