AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
Generates new images and edits existing ones through the desktop's built-in ImageGen and ImageEdit tools, with rules for choosing between them and writing the art-direction prompt.
Install Image Generation Tools
$ npx skills add NanmiCoder/cc-haha --skill imagegen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NanmiCoder/cc-haha imagegen --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NanmiCoder/cc-haha.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/skills/bundled/imagegen .claude/skills/imagegen && rm -rf skills-srcUse ~/.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/
Install the "imagegen" agent skill from https://github.com/NanmiCoder/cc-haha/tree/main/src/skills/bundled/imagegen into .claude/skills/imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "imagegen", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NanmiCoder/cc-haha/tree/main/src/skills/bundled/imagegenType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NanmiCoder/cc-haha --skill imagegen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NanmiCoder/cc-haha imagegen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NanmiCoder/cc-haha.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/skills/bundled/imagegen .agents/skills/imagegen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "imagegen" agent skill from https://github.com/NanmiCoder/cc-haha/tree/main/src/skills/bundled/imagegen into .agents/skills/imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "imagegen", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NanmiCoder/cc-haha --skill imagegen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NanmiCoder/cc-haha imagegen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NanmiCoder/cc-haha.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/skills/bundled/imagegen .cursor/skills/imagegen && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "imagegen" agent skill from https://github.com/NanmiCoder/cc-haha/tree/main/src/skills/bundled/imagegen into .cursor/skills/imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "imagegen", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NanmiCoder/cc-haha.git --path src/skills/bundled/imagegen--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NanmiCoder/cc-haha --skill imagegen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NanmiCoder/cc-haha imagegen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NanmiCoder/cc-haha.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/skills/bundled/imagegen .gemini/skills/imagegen && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "imagegen" agent skill from https://github.com/NanmiCoder/cc-haha/tree/main/src/skills/bundled/imagegen into .gemini/skills/imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "imagegen", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NanmiCoder/cc-haha imagegenInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NanmiCoder/cc-haha --skill imagegen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NanmiCoder/cc-haha.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/skills/bundled/imagegen .github/skills/imagegen && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "imagegen" agent skill from https://github.com/NanmiCoder/cc-haha/tree/main/src/skills/bundled/imagegen into .github/skills/imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "imagegen", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NanmiCoder/cc-haha --skill imagegen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NanmiCoder/cc-haha imagegen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NanmiCoder/cc-haha.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/skills/bundled/imagegen .opencode/skills/imagegen && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "imagegen" agent skill from https://github.com/NanmiCoder/cc-haha/tree/main/src/skills/bundled/imagegen into .opencode/skills/imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "imagegen", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
imagegen- GitHub stars
- 15k
- Token cost
- ~991 tokens
- SKILL.md length
- 576 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generates new images and edits existing ones through the desktop's built-in ImageGen and ImageEdit tools, with rules for choosing between them and writing the art-direction prompt.
- Creating an original illustration, product visual or diagram image from a description
- SKILL.md covers Decide the request shape, Build the prompt and Output options
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Changing one element of an image you attached while keeping the rest the same
What it does
The desktop host manages provider authentication, model routing, output storage and secrets, so the agent never asks you for an API key. A brand-new visual goes to `ImageGen`, which has no image-path argument. A request that keeps, combines or changes an existing picture goes to `ImageEdit`, which needs `referenced_image_paths` listing exact paths to images you supplied in the conversation or that an earlier generation returned. The agent must not invent or search for paths, and asks you to attach the image if it has none. One distinct prompt means one call, `count` is for variations of the same prompt, and a call takes at most three source images.
Multi-turn edits use the latest selected output as the next edit target and restate identity, layout, text and unchanged-region constraints each turn so the image does not drift. The prompt is built as an art-direction brief covering use case, subject, setting, composition, lighting and mood, style, palette, any exact text and things to avoid. If the provider returns an error the agent does not retry on its own and lets you decide.
When your agent uses it
- Creating an original illustration, product visual or diagram image from a description
- Changing one element of an image you attached while keeping the rest the same
- Producing several variations of one concept
Example prompts
- “Generate a flat-style poster of a lighthouse at dusk in teal and orange.”
- “Edit the attached product photo so the background is a plain light gray, keeping the bottle unchanged.”
- “Give me four variations of a minimalist logo mark for a bakery.”
Requirements
- A desktop host with an image provider configured
- Pre-approved tools (allowed-tools): ImageGen, ImageEdit
What it can do on your machine
Read from SKILL.md and the folder at commit 1c78154. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ImageGenImageEdit
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
Image Generation Tools loads about 991 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 576 words of instructions outside code blocks.
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 NanmiCoder/cc-haha at commit 1c78154, republished under its MIT licence (© NanmiCoder). 576 words, ~991 tokens.
Download SKILL.mdSave it as
.claude/skills/imagegen/SKILL.md (or your agent's skills folder).- name
- imagegen
- description
- Generate original images, artwork, product visuals, diagrams, or other raster assets with the desktop's configured image provider. Use whenever the user asks to create or generate an image.
- allowed-tools
- ImageGen, ImageEdit
Image generation
Use the built-in ImageGen and ImageEdit tools. Provider authentication, model routing, output storage, and secrets are managed by the desktop host; never ask the user to put an API key in this skill or in the prompt.
Decide the request shape
- Treat a brand-new visual as generation and call
ImageGen. Its schema intentionally has no image-path argument. - Treat a request that preserves, combines, or changes an existing visual as an edit and call
ImageEdit. - One distinct prompt equals one tool call.
- Use
countonly for multiple variations of the same prompt. For different concepts, make separate calls. ImageEditrequiresreferenced_image_paths: populate it with ordered, exact paths to images the user supplied in this conversation — a path surfaced by[Image source: ...], a file the user attached with@, or a path returned by an earlierImageGencall. Never invent, search for, or substitute another filesystem path, and never read an image off disk yourself to use it as an input; if the user means an image you have no path for, ask them to attach it. The first image is the primary canvas unless the user says otherwise.- For multi-turn editing, use the latest selected output as the next turn's
edit_target. Repeat all identity, layout, text, and unchanged-region constraints on every turn so edits do not drift. - To edit several images independently, make one call per image. Put multiple images in one call only when the user wants them combined or used together as references. A single call accepts at most three source images.
- Prefer a useful default composition when the user leaves details open. Do not invent branding, logos, or people they did not request.
- Provider and image model selection come from the current desktop session; do not add either to the tool arguments.
- If the provider returns an error, do not retry the image tool automatically. Explain the failure and let the user decide whether to retry or change providers.
Show full SKILL.md (254 more words)Show less
Build the prompt
Turn the request into a complete art-direction brief. Preserve all relevant user-specified detail.
- use case and image type
- subject, action, and important attributes
- environment and context
- composition, framing, and camera angle
- lighting and mood
- visual style or medium
- color palette
- exact text, only when text must appear in the image
- constraints and elements to avoid
For edits, start the prompt with each input's numbered role, then say change only X; keep Y unchanged. For a composite, specify which subject or visual property comes from each numbered image and preserve the requested identities. Do not rely on conversational pronouns such as "it" or "the previous one" inside the tool prompt.
Preserve the user's intent and wording for names or required on-image text. For diagrams, specify hierarchy, reading order, labels, and connections. For photorealistic work, describe lens, depth of field, lighting direction, and material detail when they matter.
Output options
- Use
aspect_ratiowhen the user describes a layout such as square, portrait, landscape, banner, or phone wallpaper. - Use
resolution: "2k"only when higher resolution is useful and supported. - Use transparent background only when requested or clearly needed for a reusable asset.
- The host displays one placeholder per requested image and replaces each slot as the saved image becomes available.
After a successful call, briefly summarize what was created or changed. The host card already displays and opens the saved images, so do not repeat, link, or embed the returned local paths in the final answer. Do not include base64 data in the conversation.
© NanmiCoder, 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 src/skills/bundled/imagegen of NanmiCoder/cc-haha.
Open the folder on GitHubat commit 1c78154
Compare with similar skills
Image Generation Tools 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Image Generation Tools this skillNanmiCoder/cc-haha | 15k | — | ~991 | Automated safety check: Pass | MIT | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Generate Imageynulihao/AgentSkillOS | 617 | 10 repos | ~1.7k | Automated safety check: Notes | None | |
| GPT Image Generation CLIwuyoscar/GPT-Image2-Skill | 5.6k | — | ~2.5k | Automated safety check: Notes | MIT | |
| NanobananaReScienceLab/opc-skills | 1.8k | 1 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Native Transparent ImagegenZSeven-W/craft-skills | 223 | 2 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
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.
Nanobanana
ReScienceLab/opc-skills
Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro).
Native Transparent Imagegen
ZSeven-W/craft-skills
Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery.
BlockRun Image Generation
BlockRunAI/ClawRouter
Generates or edits images through ClawRouter's local image API, with a choice of models and sizes and payment handled automatically through x402.
More from NanmiCoder/cc-haha
Release Announcement Poster
NanmiCoder/cc-haha
Turns the latest release notes into a short WeChat group message and a tall PNG poster, with contributor GitHub IDs checked and real avatars embedded.
Related
Categories
Questions about Image Generation Tools
What does Image Generation Tools do?
Generates new images and edits existing ones through the desktop's built-in ImageGen and ImageEdit tools, with rules for choosing between them and writing the art-direction prompt. The desktop host manages provider authentication, model routing, output storage and secrets, so the agent never asks you for an API key. A brand-new visual goes to `ImageGen`, which has no image-path argument.
When should I use Image Generation Tools?
Image Generation Tools fits situations like: creating an original illustration, product visual or diagram image from a description; changing one element of an image you attached while keeping the rest the same; producing several variations of one concept.
How do I install Image Generation Tools in Claude Code?
Run `npx skills add NanmiCoder/cc-haha --skill imagegen -a claude-code`. Or copy the skill folder (src/skills/bundled/imagegen in NanmiCoder/cc-haha) into .claude/skills/imagegen in your project. Claude Code loads it when a task matches its description.
How do I install Image Generation Tools in Codex?
Run `npx skills add NanmiCoder/cc-haha --skill imagegen -a codex`. Or copy the skill folder (src/skills/bundled/imagegen in NanmiCoder/cc-haha) into .agents/skills/imagegen in your project. Codex loads it when a task matches its description.
Can I use Image Generation Tools 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 NanmiCoder/cc-haha --skill imagegen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/imagegen, .gemini/skills/imagegen, .github/skills/imagegen and .opencode/skills/imagegen in your project.
What does Image Generation Tools need to run?
SKILL.md names no scripts, command-line tools or credentials: Image Generation Tools is instructions for the agent only. Our summary lists: A desktop host with an image provider configured. Its frontmatter pre-approves these tools: ImageGen, ImageEdit.
Does Image Generation Tools 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 Image Generation Tools 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 Image Generation Tools use?
Image Generation Tools 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 Image Generation Tools use?
About 991 tokens (SKILL.md is roughly 4k 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 Image Generation Tools?
Skills that share tags, products or a category with Image Generation Tools: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Generate Image (ynulihao/AgentSkillOS, 617 stars), GPT Image Generation CLI (wuyoscar/GPT-Image2-Skill, 5.6k stars) and Nanobanana (ReScienceLab/opc-skills, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Image Generation Tools?
NanmiCoder (a GitHub user) maintains it in NanmiCoder/cc-haha, which has 14,886 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 5, 2026.
Source: NanmiCoder/cc-haha on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.