skill CX Codex

image-generation · postplusai — Claude Code skill: plan image tasks

Q: How do I install image-generation in Claude?

Run `npx skills add PostPlusAI/postplus-skills --skill image-generation -a claude-code`. The skill lands at `~/.claude/skills/image-generation/SKILL.md`.

Q: How is image-generation different from image-batch-runner?

This skill plans and classifies; `image-batch-runner` executes a normalized request. If the request is already ready to run, use the runner.

Sorts an image request into a task class, picks the model and reference rules, then hands a ready brief to the runner.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add PostPlusAI/postplus-skills --skill image-generation -a claude-code

Open on GitHub

What image-generation does

This skill is a controller, not a generator. It never submits jobs. It reads the request, works out what kind of image is wanted and which references are binding, then writes the handoff for image-batch-runner. Useful when the input is a prompt, a product photo, a URL or a storyboard and you need a decision before spending anything.

Seven task classes are covered: text_to_image, image_edit, reference_image, product_image, banner_thumbnail, storyboard_image and batch_variant. Each one has its own input and handoff rules. Edits need a bound source image and an endpoint that can edit. Persona, product and brand identity count as binding references unless the user marks them inspiration-only. Benchmark clips and mood boards go the other way, as inspiration only. Excluded references stay out of the runner request.

Routing sends non-image work elsewhere: media understanding, reference decoding, video. The skill stops when user intent or source evidence is missing and a guess would change the result. Paid tasks draw on PostPlus credits after the price and balance are checked, and estimate-only requests do not run. Insufficient credits end the run.

What it helps with

classify an image request before any job is submitted
bind a source image to edit and preserve rules
separate binding references from inspiration-only ones
prepare storyboard panels ahead of execution
build a runner handoff with no guessed intent

Example prompts for the agent

I need a banner image, classify the request and hand it to image-batch-runner
here is the product photo and the change: keep identity, invent nothing
turn this panel plan into storyboard panels ready to run

How to install image-generation

1Skills CLI (Vercel)

npx skills add PostPlusAI/postplus-skills --skill image-generation -a claude-code

2Manually: put the files in place

~/.claude/skills/image-generation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/image-generation/

1Skills CLI (Vercel)

npx skills add PostPlusAI/postplus-skills --skill image-generation -a codex

2Manually: put the files in place

.agents/skills/image-generation/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add PostPlusAI/postplus-skills --skill image-generation -a cursor

2Manually: put the files in place

.cursor/skills/image-generation/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install PostPlusAI/postplus-skills image-generation

2Manually: put the files in place

.github/skills/image-generation/SKILL.md

1Skills CLI (Vercel)

npx skills add PostPlusAI/postplus-skills --skill image-generation -a gemini-cli

2Platform CLI

gemini skills install https://github.com/PostPlusAI/postplus-skills --path skills/10-routing/image-generation

Manually: put the files in place

.devin/skills/image-generation/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add PostPlusAI/postplus-skills --skill image-generation -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about image-generation

How do I install image-generation in Claude?

Run npx skills add PostPlusAI/postplus-skills --skill image-generation -a claude-code. The skill lands at ~/.claude/skills/image-generation/SKILL.md.

What does image-generation do?

It identifies the input type, classifies the image task, selects the model and reference rules, and produces the handoff for image-batch-runner. It does not submit jobs.

How is image-generation different from image-batch-runner?

This skill plans and classifies; image-batch-runner executes a normalized request. If the request is already ready to run, use the runner.

image-generation by other authors comes first.

image-generation bytedance Builds structured JSON prompts and executes a Python script to generate images with optional reference files. Useful for character design and complex scene rendering. CX Codex +1 2,900installs image-generation claude-office-skills Turns a rough visual idea into a working prompt for DALL-E, Midjourney or Stable Diffusion, shaped for the tool you actually use. CX Codex +1 5,600installs qwencloud-image-generation QwenCloud A skill that generates and edits images with Wan and Claude Image models from inside your agent: text-to-image, style transfer, reference photos. CX Codex +1 1,600installs ai-image-generation prime-skills This skill creates images from text and edits existing ones through the RunComfy CLI. It picks a model for the task, such as rendering poster text or making a photorealistic portrait. CX Codex +1 383,000installs stable-diffusion-image-generation Orchestra Research A skill that walks your agent through Stable Diffusion image generation with HuggingFace Diffusers: text-to-image, img2img, inpainting, ControlNet. CX Codex +1 1,000installs gpt-image-2 prime-skills Generates and edits images via OpenAI GPT Image 2 on RunComfy. Embeds text, logos, and multilingual typography accurately — for e-commerce, ads, and UI mockups. CX Codex +1 84,300installs physical-ai-defect-image-generation NVIDIA Prepares automated defect synthesis pipelines for optical quality inspection. Helps construct training sets for electronic boards, metal, and glass using Cosmos vision models. CX Codex +1 2,000installs p-image 101-skills Runs Pruna P-Image models from the terminal: text-to-image, editing existing pictures, LoRA style presets and compositing several images into one. CX Codex +1 12,400installs

From the same set6

tiktok-research The skill pulls public TikTok evidence — videos, comments, profiles, paid ads — for a marketing decision. It runs through the postplus CLI. CX Codex +1 1,100installs youtube-research This skill collects public YouTube channel facts, video metrics and comment samples, plus downloadable video records on request. Handy for content and audience research. CX Codex +1 1,100installs video-batch-runner Assembles Seedance 2.5 requests and runs one clip or a whole batch from a brief, image, audio or reference. CX Codex +1 1,000installs commercial-ad Designs or audits a product commercial around one visual mechanism, then returns a brief or a shot script with claim boundaries attached. CX Codex +1 478installs before-after-ad A Claude skill that turns a product brief into a before-and-after ad concept and shot script, with the comparison tied to approved claims. CX Codex +1 465installs