SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

image-useleeguooooo/image-use

Lets coding agents such as Claude Code call a ChatGPT subscription account to generate images,…

No ratings yet Rate this skill
Stars392
Forks45
Watchers392
Open Issues0

InstallOne-line install

Installable · 4 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add leeguooooo/image-use

4 more are not listed — run npx skills@latest add leeguooooo/image-use --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Lets coding agents such as Claude Code call a ChatGPT subscription account to generate images, with no separate OpenAI API key required. Key capabilities include: 1. Subscription-quota image generation: reuses an already logged-in ChatGPT Plus account to call gpt-image / DALL·E, turning subscription quota into a programmable image capability; 2. API-key-free operation: detects the local Codex login state (~/.codex/auth.json) to decide whether credentials are available, and gives a clear message instead of failing silently when not logged in; 3. Watermark and preview control: supports generating preview images with a visible watermark so composition and style can be confirmed before the final render; 4. Direct CLI output: submits prompts and writes image files from the terminal, making it easy to embed in scripts and automation. 2. Use Cases: Generating illustrations for docs, web pages and READMEs inside coding-agent sessions such as Claude Code; producing images when there is no OpenAI API key but a ChatGPT Plus subscription is available; reviewing a watermarked preview before committing to the final generation; scripting batch image generation. 3. Target Roles: AI / Algorithm Engineer, Full-stack / Indie Developer, Content Creator / Social Media Operator, UI/UX / Visual Designer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID2090
Data sourceGitHub
Repositoryleeguooooo/image-use
CategoryAI & Agent Skills / Image Generation & Multimodal
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1241959906
Node IDR_kgDOSgbN4g
Rank#1555 (position within the source ranking)
Site-wide popularity rank#1757 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01002003004002026-09-222026-10-112026-09-22 · 3782026-10-11 · 392
  • Now392
  • Previous point · 09-22 378
  • vs previous point +14
  • 2 data points 19 days
02040602026-09-222026-10-112026-09-22 · 452026-10-11 · 45
  • Now45
  • Previous point · 09-22 45
  • vs previous point ±0
  • 2 data points 19 days

TimelineTimeline

Repository created2026-05-18 02:16:046 months ago
Data last updated2026-10-26 12:16:1222 days ago
Last commit2026-10-09 05:42:491 months ago

CommitLatest commit

Version [v0.34.0] committed by leeguooooo. Update Category: Dependency Upgrades & CI Pipeline Maintenance. Commit details: ci(release): write release-notes headings in English. This update updates project dependencies and ensures reliable test automation.

7c41a3e v0.34.0 leeguooooo 2026-10-09

Next stepsNext steps