Agent skill

Gradient Screenshot Repair

by OpenAIPay in OpenAIPay/openaipay

Repair native-looking mobile screenshot backgrounds by erasing localized UI content and reconstructing nearby gradients from sampled pixels.

No licenceAuto-check passed

Install Gradient Screenshot Repair

skills CLI
$ npx skills add OpenAIPay/openaipay --skill gradient-screenshot-repair -a claude-code

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

GitHub CLI
$ gh skill install OpenAIPay/openaipay gradient-screenshot-repair --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/OpenAIPay/openaipay.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gradient-screenshot-repair .claude/skills/gradient-screenshot-repair && 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
gradient-screenshot-repair
GitHub stars
129
Token cost
~922 tokens
SKILL.md length
452 words
Files
4 (incl. scripts, references)
Skills in repo
3
Repo updated
First seen
Licence
None found

At a glance

Repair native-looking mobile screenshot backgrounds by erasing localized UI content and reconstructing nearby gradients from sampled pixels.

  • Codex must remove status-bar items
  • SKILL.md covers Overview, Workflow, Rules and Tuning, plus 1 more section
  • Runs Python scripts from its folder; calls python3
  • Overlay text from app screenshots without visible seams

What it does

Gradient Screenshot Repair is an agent skill from OpenAIPay/openaipay. Repair native-looking mobile screenshot backgrounds by erasing localized UI content and reconstructing nearby gradients from sampled pixels. Use when Codex must remove status-bar items, avatars, nicknames, labels, chips, or overlay text from app screenshots without visible seams, flat fills, or color mismatches. Also use for Chinese requests like 擦除顶部、补渐变、抹掉头像、抹掉昵称、保留原图底色、不要白块、不要假遮罩.

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/gradient-repair-playbook.md` and `scripts/sample_surface_patch.py`).

When your agent uses it

  • Codex must remove status-bar items
  • Overlay text from app screenshots without visible seams
  • Color mismatches
  • Chinese requests like 擦除顶部、补渐变、抹掉头像、抹掉昵称、保留原图底色、不要白块、不要假遮罩

Example prompts

  • “/gradient-screenshot-repair”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 78e5e07. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Gradient Screenshot Repair loads about 922 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 452 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~922
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 452 words (~922 tokens).

“Use this skill to clean a bounded region inside a mobile screenshot while keeping the original page surface believable. Prefer rebuilding the background from nearby sampled pixels instead of drawing flat color blocks, blur overlays, or fake replacement panels.”

— opening of SKILL.md by OpenAIPay
name
gradient-screenshot-repair

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (scripts, references) in skills/gradient-screenshot-repair of OpenAIPay/openaipay.

  • SKILL.md
  • agents/openai.yaml
  • references/gradient-repair-playbook.md
  • scripts/sample_surface_patch.py

Open the folder on GitHubat commit 78e5e07

Compare with similar skills

Gradient Screenshot Repair 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.

Gradient Screenshot Repair compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gradient Screenshot Repair this skillOpenAIPay/openaipay129—~922Automated safety check: PassNone
Screenshotnexu-io/open-design100k—~291Automated safety check: PassApache-2.0
Tabler Screenshot Makertabler/tabler42k—~1.3kAutomated safety check: PassMIT
Python Background Jobswshobson/agents40k—~1.8kAutomated safety check: PassMIT
Openclaw Repair Sweepopenclaw/openclaw392k—~1.8kAutomated safety check: PassMIT
Screenshots Marketingnexu-io/open-design100k—~301Automated safety check: PassApache-2.0

Similar skills

  • Screenshot

    nexu-io/open-design

    Capture desktop, app windows, or pixel regions across OS platforms.

    100k GitHub stars~291 tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Makes reproducible screenshots of Tabler components and screens for release notes, the website and social posts, using the repository's screenshots app.

    42k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Python Background Jobs

    wshobson/agents

    Python background job patterns including task queues, workers, and event-driven architecture.

    40k GitHub stars~1.8k tokensUpdated 6 days ago
    Backend & APIsAuto-check passed
  • Openclaw Repair Sweep

    openclaw/openclaw

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    392k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Screenshots Marketing

    nexu-io/open-design

    Generate marketing screenshots with Playwright. An agent skill from nexu-io/open-design.

    100k GitHub stars~301 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Gradient

    bergside/awesome-design-skills

    Smooth color transitions and gradient-rich surfaces for modern, playful interfaces with visual depth.

    3.1k GitHub starsUsed in 1 repo~868 tokens
    Frontend & DesignAuto-check passed

More from OpenAIPay/openaipay

  • Capture the current page from my USB-connected iPhone on this Mac using the proven OpenAiPay real-device RSD chain: first run the repo capture tool as the current user with pre-warmed sudo and…

    129 GitHub stars~830 tokensUpdated 5 mo ago
    Auto-check: notes
  • Aipay Frontend Theme

    OpenAIPay/openaipay

    A skill your agent uses when changing AiPay iOS frontend color style, replacing blue UI to purple, updating screenshot-based Reference pages, or enforcing component theme consistency across parallel…

    129 GitHub stars~386 tokensUpdated 5 mo ago
    Auto-check passed

Questions about Gradient Screenshot Repair

What does Gradient Screenshot Repair do?

Repair native-looking mobile screenshot backgrounds by erasing localized UI content and reconstructing nearby gradients from sampled pixels. Gradient Screenshot Repair is an agent skill from OpenAIPay/openaipay. Repair native-looking mobile screenshot backgrounds by erasing localized UI content and reconstructing nearby gradients from sampled pixels.

When should I use Gradient Screenshot Repair?

Gradient Screenshot Repair fits situations like: Codex must remove status-bar items; overlay text from app screenshots without visible seams; color mismatches; chinese requests like 擦除顶部、补渐变、抹掉头像、抹掉昵称、保留原图底色、不要白块、不要假遮罩.

How do I install Gradient Screenshot Repair in Claude Code?

Run `npx skills add OpenAIPay/openaipay --skill gradient-screenshot-repair -a claude-code`. Or copy the skill folder (skills/gradient-screenshot-repair in OpenAIPay/openaipay) into .claude/skills/gradient-screenshot-repair in your project. Claude Code loads it when a task matches its description.

How do I install Gradient Screenshot Repair in Codex?

Run `npx skills add OpenAIPay/openaipay --skill gradient-screenshot-repair -a codex`. Or copy the skill folder (skills/gradient-screenshot-repair in OpenAIPay/openaipay) into .agents/skills/gradient-screenshot-repair in your project. Codex loads it when a task matches its description.

Can I use Gradient Screenshot Repair 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 OpenAIPay/openaipay --skill gradient-screenshot-repair -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gradient-screenshot-repair, .gemini/skills/gradient-screenshot-repair, .github/skills/gradient-screenshot-repair and .opencode/skills/gradient-screenshot-repair in your project.

What does Gradient Screenshot Repair need to run?

Going by SKILL.md and its folder, Gradient Screenshot Repair needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Gradient Screenshot Repair 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 Gradient Screenshot Repair 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Gradient Screenshot Repair use?

No licence was found for Gradient Screenshot Repair or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Gradient Screenshot Repair use?

About 922 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 885 tokens, read only when the agent opens those files.

What are the alternatives to Gradient Screenshot Repair?

Skills that share tags, products or a category with Gradient Screenshot Repair: Screenshot (nexu-io/open-design, 100k stars), Tabler Screenshot Maker (tabler/tabler, 42k stars), Python Background Jobs (wshobson/agents, 40k stars) and Openclaw Repair Sweep (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gradient Screenshot Repair?

OpenAIPay (a GitHub user) maintains it in OpenAIPay/openaipay, which has 129 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on April 21, 2026.

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