removebg-api

Remove image backgrounds using the remove.bg API with API-key auth and transparent PNG output. Use when high-quality cutouts are needed and cloud processing is acceptable.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "removebg-api" with this command: npx skills add rolandkakonyi/removebg-api

removebg-api

Use remove.bg for high-quality background removal.

API key setup

  1. Create/sign in at https://www.remove.bg/dashboard#api-key
  2. Create an API key
  3. Configure REMOVE_BG_API_KEY in OpenClaw config (openclaw.json) so it is present in runtime environment.

Important

  • Skill metadata (requires.env) declares that REMOVE_BG_API_KEY is required.
  • Metadata does not auto-load shell env files.
  • Preferred: provide key via OpenClaw config-managed environment.

Usage (preferred: uv)

Run from the skill directory:

uv run scripts/removebg_api.py --input /path/in.jpg --output /path/out.png

Options:

  • --size auto|preview|full|4k (default: auto)

  • --format png|jpg|zip (default: png) Security defaults:

  • --input must be a real image file inside the OpenClaw workspace.

  • Allowed input types: .png, .jpg, .jpeg, .webp (extension + magic-byte validation).

  • --output must be under outputs/removebg-api/ inside the workspace.

  • Large/abusive files are rejected (size + dimension limits).

  • This prevents arbitrary file read/write outside normal skill boundaries.

Example:

uv run scripts/removebg_api.py --input ./input.jpg --output ./output.png --size auto --format png

Fallback (without uv)

python3 scripts/removebg_api.py --input ./input.jpg --output ./output.png

Output

  • Writes result file to --output
  • Prints MEDIA: line for chat workflows

Notes

  • API usage may consume free credits / paid quota.
  • No absolute-path requirement for skill docs; use local paths in examples.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Fitbit Tracker

Personal Fitbit integration for daily health tracking with adaptive sleep and activity reporting

Registry SourceRecently Updated
General

Ollama Load Balancer

Ollama load balancer for Llama, Qwen, DeepSeek, and Mistral inference across multiple machines. Load balancing with auto-discovery via mDNS, health checks, q...

Registry SourceRecently Updated
General

Google Merchant Center

Google Merchant Center integration. Manage Accounts. Use when the user wants to interact with Google Merchant Center data.

Registry SourceRecently Updated
General

Twitter/X All-in-One — Search, Monitor & Publish Text & Media Posts

Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts, likes/unlike...

Registry SourceRecently Updated