Agent Brush
Image editing toolkit for AI agents. Use when processing, editing, or validating images. Background removal, compositing, text overlays, resizing, format conversion, and spec validation against presets (social media, icons, thumbnails).
Install
npx skills add ultrathink-art/agentbrush --skill agent-brushgit clone --depth 1 https://github.com/ultrathink-art/agentbrush.git /tmp/agentbrush
mkdir -p ~/.claude/skills
cp -r /tmp/agentbrush/skill/agent-brush ~/.claude/skills/agent-brushPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AgentBrush — Image Editing for AI Agents Image processing toolkit with background removal, green screen processing, border cleanup, text rendering, compositing, resizing, validation, and format conversion. ## Quick Reference All commands follow: `agentbrush <command> <input> <output> [options]` ### Background Removal (edge-based flood fill — NEVER threshold-based) ```bash # Remove black background agentbrush remove-bg input.png output.png --color black --threshold 25 # Remove white background with edge smoothing agentbrush remove-bg input.png output.png --color white --smooth # Remove custom color background agentbrush remove-bg input.png output.png --color "24,242,41" --threshold 40 ``` ### Green Screen Removal (multi-pass pipeline) ```bash # Standard green screen removal agentbrush greenscreen input.png output.png # With upscale + halo cleanup agentbrush greenscreen input.png output.png --upscale 3 --halo-passes 20 ``` Exits 1 when green survives **enclosed by artwork** (a see-through slit, a gap between two limbs, a window in a prop). Edge flood fill can only reach the field connected to the border, so an enclosed pocket structurally cannot be removed — it prints as a coloured bar inside the artwork. The error names its bbox and pixel count; the output file is still written so it can be repaired.
Details
- Skill name
agent-brush- Repository
- ultrathink-art/agentbrush
- Path
skill/agent-brush/SKILL.md- License
- MIT
- Repo updated
- 27 July 2026
FAQ
What does the Agent Brush skill do?
Image editing toolkit for AI agents. Use when processing, editing, or validating images. Background removal, compositing, text overlays, resizing, format conversion, and spec validation against presets (social media, icons, thumbnails).
How do I install the Agent Brush skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ultrathink-art/agentbrush --skill agent-brush. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agent Brush popular?
It lives in ultrathink-art/agentbrush, which has 9 GitHub stars and 1 forks.
Related skills
Agents Correct
23jpoehnelt/skills
Find the mistakes agents keep repeating in a repo and make each one impossible, trying architecture first, then types, lint, tests, and docs last. Use when the operator keeps correcting the same mistake, or for /agents-correct.
Zendesk
8andmarios/zendesk-skill
Interact with Zendesk Support via CLI - search tickets, view details, analyze metrics, manage users/organizations, and update tickets. All responses are saved locally for efficient jq querying. All Zendesk content is screened for prompt injection (regex, semantic, and LLM-based) and wrapped with security markers before reaching the LLM.
Agents Create Verification Skill
23jpoehnelt/skills
Generate a project-local verify skill that drives the app like a user through a browser with Playwright, a CLI, or HTTP. Use for /agents-create-verification-skill, "make a verify skill for this repo", or when a project has no scripted way to prove UI, CLI, or service behavior.
Alterlab Nmc Digital Ethics
21AlterLab-IEU/AlterLab-FC-Skills
This skill should be used when the user asks about "digital ethics", "media ethics", "AI ethics", "platform governance", "misinformation", "disinformation analysis", "act as a digital ethics advisor", "digital ethics mode", "algorithmic bias", "data privacy", "content moderation", "ethical framework", "deepfake", "surveillance", "fact-checking tools", "verification workflow", "platform audit", "ethics stress test", "algorithmic accountability", "informed consent", "digital rights", "tech regulation", or needs expertise in analyzing ethical dilemmas in digital media, AI, and platform ecosystems
Agents Reflect
23jpoehnelt/skills
After a work session, review what went wrong and right and turn each lesson into a concrete edit to an existing skill or AGENTS.md line. Use when the user says "reflect" or /agents-reflect.
AI Avatar Critique
39lionelsimai/claude-skills-collection
Ruthlessly critique an AI video avatar before it ships, with a verdict, scored dimensions and a timestamped fix list. Use when the user says 'critique this avatar', 'review my avatar video', 'avatar QC', or asks why an avatar looks fake.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.