Agent skill

Photoshop Background Cutout

by THU-SAGE in THU-SAGE/syll

Removes an image background and exports a transparent PNG by driving the real Adobe Photoshop app on a macOS host, after asking your permission to take over the screen.

MITAuto-check passedMedia & Creative

Install Photoshop Background Cutout

skills CLI
$ npx skills add THU-SAGE/syll --skill photoshop-cutout -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install THU-SAGE/syll photoshop-cutout --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/THU-SAGE/syll.git skills-src && mkdir -p .claude/skills && cp -r skills-src/syll/skills/photoshop-cutout .claude/skills/photoshop-cutout && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
photoshop-cutout
GitHub stars
303
Token cost
~1.2k tokens
SKILL.md length
621 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Removes an image background and exports a transparent PNG by driving the real Adobe Photoshop app on a macOS host, after asking your permission to take over the screen.

  • Works in 4 steps: You call photoshop_cutout with the path… → The tool launches / focuses Adobe… → The tool measures the result (how much… → …
  • Removing the background from a product photo to get a transparent PNG
  • SKILL.md covers When To Reach For This, How It Works, Confirm Before Control and Honesty Protocol, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill calls a photoshop_cutout tool that is not a filter running in the agent's own process. It launches or focuses Adobe Photoshop on a macOS host, opens the image, performs a subject-selection cutout and exports a transparent PNG. The tool then measures the result, including how much background was removed and whether a clean alpha channel exists, and returns a verdict while the before and after images show inline.

Because the tool takes over the host's mouse and keyboard, the first call must use confirmed=false, which only returns a consent question. The agent shows that question, waits for a clear yes, and only then calls again with confirmed=true. Silence, ambiguity or a maybe does not count. Reports must stick to the measured verdict: PASS means the alpha checks passed and the background was removed, while REVIEW means the file was exported but not every transparency check passed.

It recognizes English and Chinese phrasing for the intent, for example remove the background, cut out the product, make a transparent PNG, and the Chinese terms 抠图 and 去背景. Adobe Photoshop must be available on the macOS host.

When your agent uses it

  • Removing the background from a product photo to get a transparent PNG
  • Cutting a person or logo out of an image
  • Chinese-language requests such as 抠图, 去背景 or 做透明 PNG

Example prompts

  • “Remove the background from ./photos/sneaker.jpg and give me a transparent PNG.”
  • “Cut out the person in ./team/headshot.png.”
  • “帮我把 ./logo/brand.png 去背景,做成透明 PNG。”

Requirements

  • Adobe Photoshop on a macOS host
  • The photoshop_cutout tool
  • Your explicit permission for the agent to control the mouse and keyboard

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. You call photoshop_cutout with the path to the source image.
  2. The tool launches / focuses Adobe Photoshop, opens the image, performs the
  3. The tool measures the result (how much background was actually removed,
  4. The before image and the after PNG render inline automatically — you do not

What it can do on your machine

Read from SKILL.md and the folder at commit 3741347. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Photoshop Background Cutout loads about 1.2k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 621 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from THU-SAGE/syll at commit 3741347, republished under its MIT licence (© THU-SAGE). 621 words, ~1,176 tokens.

Download SKILL.mdSave it as .claude/skills/photoshop-cutout/SKILL.md (or your agent's skills folder).
name
photoshop-cutout
description
Remove the background from an image and produce a transparent PNG by driving the real Adobe Photoshop app on a macOS host. Triggers: remove background, cut out, knock out the subject, isolate the subject, make a transparent PNG, transparent background, delete background. 中文触发词:抠图、扣图、去背景、去掉背景、扣出主体、透明背景、做透明 PNG。

Photoshop Cutout

Use the photoshop_cutout tool to remove the background from an image and deliver a transparent PNG. This is not a filter that runs in this process — it drives the real Adobe Photoshop application on a macOS host, opens the image, runs the cutout, and exports the result.

When To Reach For This

The user wants a subject lifted off its background. Recognize the intent from phrases like:

  • English: "remove the background", "cut out the person/product/logo", "knock out the subject", "isolate this", "make it a transparent PNG", "give me a PNG with no background".
  • 中文:「抠图」「扣图」「帮我去背景」「去掉背景」「把主体扣出来」「要透明背景」「做成透明 PNG」。

How It Works

  1. You call photoshop_cutout with the path to the source image.
  2. The tool launches / focuses Adobe Photoshop, opens the image, performs the subject-selection cutout, and exports a transparent PNG.
  3. The tool measures the result (how much background was actually removed, whether a clean alpha channel was produced) and returns a verdict.
  4. The before image and the after PNG render inline automatically — you do not need to attach or describe them yourself.

Confirm Before Control

This tool seizes the mouse and keyboard of the host machine. It MUST NOT take over the screen without the user's explicit permission.

  1. First call — confirmed=false. Always make the first call with confirmed=false. The tool will return a takeover-consent question (it does not touch the mouse/keyboard yet). Surface that question to the user.
  2. Wait for an explicit yes. Only proceed once the user clearly agrees — a "yes", "go ahead", "do it", "确认", "可以" in the conversation counts. Silence, ambiguity, or "maybe" does not count.
  3. Second call — confirmed=true. Only then call again with confirmed=true. This is the call that actually takes over the host.

Never set confirmed=true on the first call, and never assume consent.

Honesty Protocol

Report only what the tool's measured verdict supports. Do not embellish.

The tool returns a Markdown report whose first line is either **Verdict**: PASS … or **Verdict**: REVIEW …, followed by measured numbers (transparent %, subject %, whether an alpha channel is present).

  • PASS — the alpha checks passed: you may say the background was removed and a transparent PNG was produced.
  • REVIEW — the file was exported but not all transparency checks passed. Say the cutout needs review / is not fully clean — do not claim the background was removed. Offer to retry or refine.
  • Export failed (the verdict text says the cutout PNG was not created, shown as REVIEW) — say it failed and offer to retry or try a different image.

Never claim "done", "cut out", or "transparent" beyond what the verdict and the measured ratios support. The user trusts the numbers, not your optimism.

Show full SKILL.md (185 more words)Show less

Usage Protocol

When the user asks for a cutout:

  1. Confirm the source. Make sure you have the path to the image the user wants processed.
  2. First call, confirmed=false. Relay the takeover-consent question.
  3. Get explicit consent. Wait for the user's "go ahead".
  4. Second call, confirmed=true. Run the real cutout.
  5. Report the verdict honestly. State the outcome exactly as measured. The before/after images render inline on their own.

Example

User: "帮我把这张产品图抠图,要透明背景"

  • First, call photoshop_cutout(image_path="/path/to/product.jpg", confirmed=false).
  • The tool replies with a consent question; relay it: "This will take over the mouse and keyboard on the Mac to run Photoshop. Shall I go ahead?"
  • User: "可以,去吧"
  • Then call photoshop_cutout(image_path="/path/to/product.jpg", confirmed=true).
  • Tool returns **Verdict**: PASS. You report: "背景已去除,导出了透明 PNG(结果已通过校验)。" The before/after images appear inline. If it returns REVIEW instead, say the cutout needs another look rather than claiming success.

Do Not

  • Do not drive gui_action directly to attempt the cutout — use this dedicated tool, which knows the Photoshop workflow and measures the result.
  • Do not call with confirmed=true before the user agrees.
  • Do not overstate the result. A REVIEW verdict is not a clean cutout.

© THU-SAGE, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in syll/skills/photoshop-cutout of THU-SAGE/syll.

Open the folder on GitHubat commit 3741347

Compare with similar skills

Photoshop Background Cutout next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Photoshop Background Cutout compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Photoshop Background Cutout this skillTHU-SAGE/syll303—~1.2kAutomated safety check: PassMIT
Open Editveedstudio/open-edit1.6k—~1.8kAutomated safety check: PassApache-2.0
Zipicokooo5km/Skills4U183—~2.2kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
Generate Imageynulihao/AgentSkillOS61810 repos~1.7kAutomated safety check: NotesNone
GPT Image Generation CLIwuyoscar/GPT-Image2-Skill5.7k—~2.5kAutomated safety check: NotesMIT

Similar skills

  • Open Edit

    veedstudio/open-edit

    Video work with VEED's hosted services and a CLI toolkit — word-timed transcription, cutting, background removal, AI presenters, lipsync, any fal model, sound mixing, and a Chrome renderer for HTML…

    1.6k GitHub stars~1.8k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed
  • Zipic

    okooo5km/Skills4U

    Local image compression and Zipic-app expert for macOS and native Windows.

    183 GitHub stars~2.2k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed
  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Generate Image

    ynulihao/AgentSkillOS

    Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.

    618 GitHub starsUsed in 10 repos~1.7k tokens
    Media & CreativeAuto-check: notes
  • GPT Image Generation CLI

    wuyoscar/GPT-Image2-Skill

    Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.

    5.7k GitHub stars~2.5k tokensUpdated 11 days ago
    Media & CreativeAuto-check: notes
  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    60k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed

More from THU-SAGE/syll

All 8 skills in this repo
  • Cleans a voice recording by driving Adobe Audition on a macOS host to reduce hiss, hum, background noise and sibilance, after asking for your consent.

    303 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • File Retrieval

    THU-SAGE/syll

    Finds a file on the local machine, shows previews of the candidates, and sends the one you pick back through the current chat channel after confirmation.

    303 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Desktop GUI Agent

    THU-SAGE/syll

    Controls desktop applications through screenshots: a vision model reads the screen and returns click, type and scroll actions that pyautogui then performs.

    303 GitHub stars~662 tokensUpdated 4 mo ago
    Auto-check passed
  • Builds a short spoken morning news briefing from a few web searches and turns it into one audio clip, on request or on a schedule.

    303 GitHub stars~533 tokensUpdated 4 mo ago
    Auto-check passed
  • Produces a clearly labeled, research-based stand-in for a Genshin Impact or Honkai: Star Rail daily check-in when no real sign-in can be run.

    303 GitHub stars~551 tokensUpdated 4 mo ago
    Auto-check passed
  • Local Mail Sim

    THU-SAGE/syll

    Simulate an overnight local mail summary when there is no real local mailbox integration or recorded GUI workflow available.

    303 GitHub stars~355 tokensUpdated 4 mo ago
    Auto-check passed

Works with

Questions about Photoshop Background Cutout

What does Photoshop Background Cutout do?

Removes an image background and exports a transparent PNG by driving the real Adobe Photoshop app on a macOS host, after asking your permission to take over the screen. The skill calls a photoshop_cutout tool that is not a filter running in the agent's own process. It launches or focuses Adobe Photoshop on a macOS host, opens the image, performs a subject-selection cutout and exports a transparent PNG.

When should I use Photoshop Background Cutout?

Photoshop Background Cutout fits situations like: removing the background from a product photo to get a transparent PNG; cutting a person or logo out of an image; chinese-language requests such as 抠图, 去背景 or 做透明 PNG.

How do I install Photoshop Background Cutout in Claude Code?

Run `npx skills add THU-SAGE/syll --skill photoshop-cutout -a claude-code`. Or copy the skill folder (syll/skills/photoshop-cutout in THU-SAGE/syll) into .claude/skills/photoshop-cutout in your project. Claude Code loads it when a task matches its description.

How do I install Photoshop Background Cutout in Codex?

Run `npx skills add THU-SAGE/syll --skill photoshop-cutout -a codex`. Or copy the skill folder (syll/skills/photoshop-cutout in THU-SAGE/syll) into .agents/skills/photoshop-cutout in your project. Codex loads it when a task matches its description.

Can I use Photoshop Background Cutout in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add THU-SAGE/syll --skill photoshop-cutout -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/photoshop-cutout, .gemini/skills/photoshop-cutout, .github/skills/photoshop-cutout and .opencode/skills/photoshop-cutout in your project.

What does Photoshop Background Cutout need to run?

SKILL.md names no scripts, command-line tools or credentials: Photoshop Background Cutout is instructions for the agent only. Our summary lists: Adobe Photoshop on a macOS host; The photoshop_cutout tool; Your explicit permission for the agent to control the mouse and keyboard.

Does Photoshop Background Cutout access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Photoshop Background Cutout safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Photoshop Background Cutout use?

Photoshop Background Cutout is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Photoshop Background Cutout use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Photoshop Background Cutout?

Skills that share tags, products or a category with Photoshop Background Cutout: Open Edit (veedstudio/open-edit, 1.6k stars), Zipic (okooo5km/Skills4U, 183 stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars) and Generate Image (ynulihao/AgentSkillOS, 618 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Photoshop Background Cutout?

THU-SAGE (a GitHub organization) maintains it in THU-SAGE/syll, which has 303 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on June 9, 2026.

Source: THU-SAGE/syll on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.