Remove Image Backgrounds with BiRefNet
Removing image backgrounds often requires manual editing or switching tools. This skill routes Claude, Codex, or Claude Code through belt to create transparent PNGs.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "background-removal" from https://skillstore.io/skills/inference-sh-background-removal.md and its manifest at https://skillstore.io/api/skills/inference-sh-background-removal/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "background-removal". A product photo URL with a cluttered desk background.
Expected outcome:
A transparent PNG cutout suitable for an online product listing.
Using "background-removal". A portrait URL with an indoor background.
Expected outcome:
A clean headshot image with the background removed for profile use.
Using "background-removal". A generated mascot image that needs design placement.
Expected outcome:
A transparent mascot asset ready for a slide, banner, or composition.
No prompt injection or malicious intent was found in SKILL.md. The main risks are expected external belt CLI execution, hosted image processing, mutable install guidance, and one remote embedded image asset. Several static findings are Markdown fence or placeholder URL false positives.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/inference-sh-background-removal/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/inference-sh-background-removal?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/inference-sh-background-removal?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-background-removal/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/inference-sh-background-removal.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>inference-sh. (2026). background-removal security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-background-removal/audits/2@techreport{inference-sh-inference-sh-background-removal-2026,
author = {inference-sh},
title = {background-removal security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/inference-sh-background-removal/audits/2},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "background-removal security audit report (audit version 2)"
version: "unspecified"
type: report
authors:
- name: "inference-sh"
date-released: "2026-07-08"
url: "https://skillstore.io/skills/inference-sh-background-removal/audits/2"
identifiers:
- type: other
value: "skillstore:inference-sh-background-removal:audit:2"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
inference-sh-background-removal
2026-09-09
verging-ai-background-removal
2026-09-09
Create clean transparent product cutouts from catalog photos for ecommerce pages and ads.
Remove portrait backgrounds for headshots, bios, and social profiles.
Generate or edit image elements before placing them into branded layouts.
Remove the background from this image: [image URL]. Return a transparent PNG and summarize the result.
Create a transparent cutout from this product photo: [image URL]. Preserve the product edges and avoid cropping details.
Change the background of this image to [desired scene]: [image URL]. Keep the subject natural and well lit.
Generate an image of [subject], then remove its background. Keep track of the generated image URL and final transparent PNG.
Author
inference-shLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
4ed80d850ce87f79d36851f5c5c907e6c89f6aa8
Maintenance freshness
7/18/2026
Usage
1 downloads · 0 views
File structure
📄 SKILL.md
Build React Agent Interfaces
Agent interfaces require streaming chat, tool states, approvals, and runtime wiring. This skill helps add a React or Next.js agent component with proxy setup, scoped tools, and UI patterns.
Generate AI Images with inference.sh Models
Teams need quick access to many image models without memorizing each CLI command. This skill provides ready prompts for generation, editing, upscaling, and image stitching.
Create Social Media Assets with AI
Social teams need platform-ready visuals and copy quickly. This skill provides prompts and CLI workflows for videos, images, captions, hashtags, and repurposed posts.
Automate AI Workflows
AI automation often needs repeatable scripts, scheduling, retries, and monitoring. This skill provides workflow patterns for inference.sh jobs, content pipelines, and batch processing.
Build Grounded RAG Research Pipelines
Teams need current answers with sources, but raw web search is hard to turn into reliable prompts. This skill shows RAG workflows using search, extraction, and LLM tools through inference.sh.
Run Python Code in a Remote Sandbox
Teams need quick Python execution without preparing local environments. This skill runs code through inference.sh with libraries for analysis, scraping, media, and automation.
Learn Imaginify Image Tools
by ImaginifyAI
New Imaginify users need clear guidance for creative tools and SaaS setup. This skill explains features, tutorials, and best practices for Imaginify.
Generate and Edit Images with Nano Banana 2
by inferen-sh
Creating polished images often requires separate tools for generation, editing, and current information. This skill provides one inference.sh workflow for all three tasks.
Generate Images With Qwen-Image 2
by inference-shell
Design teams need fast ways to create and edit visual concepts. This skill guides Claude, Codex, and Claude Code to run Qwen-Image 2 through inference.sh.
Generate Images with Qwen Image
by tul-sh
Image workflows often need fast visuals and accurate text rendering from one repeatable tool. This skill guides Claude, Codex, and Claude Code to run Qwen-Image through inference.sh.
Generate Native-Alpha Transparent Images
by zseven-w
Image generators can return opaque files or painted checkerboards when transparency is required. This skill generates native-alpha assets and validates every untouched output.
Create and Edit Project Images
by openai
Producing consistent raster assets requires precise prompts, careful edits, and reliable output handling. This skill structures requests, creates or edits visuals, validates results, and saves project-ready files.