Skip to main content
skill CX Codex

image-generation · sanky369 — Claude Code skill: what it does, how to install

image-generation turns loose visual ideas into structured prompt specifications and generates assets via FAL.ai using the nano-banana-pro model.

MIT 113 installs ★ 39 updated 2026-07-12

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add sanky369/vibe-building-skills --skill image-generation -a claude-code
Open on GitHub

What image-generation does

The skill turns vague image requests into precise prompt specifications for illustrations, hero banners, textures, and concept art. Each spec follows a strict structure covering the exact subject, material details, visual style, camera framing, lighting, and mood, accompanied by clear negative constraints.

Requests for commerce product photography, dedicated social graphics, or brand marks are handed off to sibling skills. The workflow infers aspect ratios from destinations, applying 16:9 for thumbnails or 9:16 for stories, and targets 2K resolution by default.

Generating actual image files requires a configured FAL_API_KEY or FAL_KEY environment variable for docs/creative_cli.py, which targets fal-ai/nano-banana-pro. If no key exists, the assistant produces the complete prompt spec block and the exact terminal command to run once credentials are in place.

What it helps with

  • create precise prompt specifications for hero banners and concept art
  • calculate appropriate aspect ratios and resolution based on asset destination
  • propose multiple distinct prompt variations for keeper assets
  • run CLI image generation via fal-ai/nano-banana-pro using FAL.ai

Example prompts for the agent

  • Create a hero image prompt for a developer tools landing page
  • Draft a prompt spec for an infographic about distributed databases
  • Generate a modern vector illustration for an article thumbnail

How to install image-generation

1Skills CLI (Vercel)

npx skills add sanky369/vibe-building-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/

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

Questions about image-generation

How to install image-generation in Claude Code?

Run npx skills add sanky369/vibe-building-skills --skill image-generation -a claude-code. The skill file is placed at ~/.claude/skills/image-generation/SKILL.md.

What happens if FAL_API_KEY is not configured?

The skill delivers the full prompt specification block and a ready-to-run CLI command, without attempting to fabricate generated images.

Which image model does this skill target?

The automation script specifically uses fal-ai/nano-banana-pro on FAL.ai through docs/creative_cli.py.

Source text

SKILL.md · MIT
---
name: image-generation
description: "Turns any request for an AI-generated image into precise, generation-ready prompt specs and — when the FAL.ai automation is configured — the generated files themselves, using the single model fal-ai/nano-banana-pro. Use whenever the user asks to 'generate an image', 'make a picture of X', 'create a thumbnail / hero image / illustration / infographic', 'write me a prompt for this image', or any visual that isn't specifically product photography, a social-platform graphic, or a brand mark (hand those to the sibling skills). Produces one prompt-spec block per asset (subject, style, composition, lighting, mood, aspect ratio, negative constraints) plus file-naming and variant conventions, and runs docs/creative_cli.py to generate when a FAL_API_KEY is available."
---

# Image Generation

Convert a fuzzy image request into prompt specs precise enough that any competent
image model — and specifically `fal-ai/nano-banana-pro` on FAL.ai, the one model
this repo's automation uses — renders what the user actually pictured. The prompt
spec is the deliverable; generated files are the bonus when the automation is
configured. **Prime rule: never generate from a vague prompt.** A weak prompt
costs a generation credit and teaches you nothing; a sharp spec is reusable
forever.

## When to use / when not to

Use for general-purpose images: hero images, illustrations, thumbnails,
infographics, textures, concept art, any one-off visual. Hand off instead when
the request is really:

- **Product shots for commerce/marketing** → `skills/creative/product-photography`
- **Platform-sized social content** → `skills/creative/social-graphics`
- **Logos, icons, patterns, brand marks** → `skills/creative/brand-asset`
- **No visual direction exists yet and consistency matters** → run
  `skills/creative/creative-strategist` first and consume its style block
- **A whole multi-asset campaign** → `skills/creative/orchestrator` routes it

## Intake

Ask in one batch, only what's missing:

1. **Subject** — what exactly is in the image? (object, scene, people, text?)
2. **Use** — where does it go? (this decides aspect ratio and resolution)
3. **Style anchor** — existing style guide / creative-strategist style block,
   reference images, or 3 adjectives for the mood?
4. **Automation** — is `FAL_API_KEY` set so you can generate, or deliver specs only?

Infer, don't ask: aspect ratio from the stated destination (thumbnail → `16:9`,
story → `9:16`, feed → `1:1` or `4:5`); resolution from stakes (`2K` default,
`4K` hero/print, `1K` drafts). **Don't stall:** if subject and use are clear,
state your assumptions for the rest and proceed.

## Workflow

1. **Check for a style block.** If the user has run
   `skills/creative/creative-strategist`, reuse its style block verbatim in every
   prompt. If not, and this is a one-off, derive a minimal one (style + palette +
   mood) from context and label it an assumption.
2. **Draft the prompt with the 5-part formula.** Every prompt contains, in order:
   **subject** (the main thing, specific: "a luxury leather watch with gold
   accents", never "a watch") → **descriptive detail** (materials, colors, text
   to render) → **style** ("professional product photography", "flat modern
   illustration", "photorealistic") → **technical treatment** (lighting,
   composition, focus, "4K, highly detailed") → **mood** ("warm and inviting").
   Add negative constraints as plain prohibitions ("no text overlay", "no
   watermark", "no busy background").
3. **Decide variant strategy.** If it's a throwaway draft → 1 image at `1K`. If
   it's a keeper asset → propose 3–4 genuinely distinct prompt specs (different
   composition or style angle, not synonym swaps), generate 1 of each or
   `num_images` 3–4 of the winner, and have the user pick. Never present one
   option for a hero asset.
4. **Generate or deliver.** If `FAL_API_KEY` (or `FAL_KEY`) is set:

   ```bash
   python docs/creative_cli.py custom \
     --category "<category>" --name "<asset-name>" \
     --prompt "<full prompt>" \
     --aspect-ratio 16:9 --resolution 2K --num-images 3
   ```

   Use `--web-search` only when the image must reflect current real-world data
   (e.g. "2026 trends infographic"). If no key is set, deliver the prompt-spec
   blocks and the exact command the user can run later — do not fake results or
   claim images were generated.
5. **Review and iterate.** Compare output to the spec's mood/style/negative
   constraints. Fix misses by editing the prompt (more specific subject, explicit
   lighting, stronger prohibitions) — there are no other model knobs. One
   iteration round maximum before checking in with the user.

Read `references/automation.md` before writing any generation command — it has
the full, verified parameter set, CLI flags, Python helpers, and output layout.

## Required output format

Deliver one block per asset (this exact structure, whether or not you generate):

```
## Prompt Spec — [asset name]
- **Use / destination:** [where it will live]
- **Subject:** [the main thing, concretely]
- **Style:** [artistic treatment]
- **Composition:** [framing — centered / rule of thirds / negative space / overhead]
- **Lighting:** [studio / natural golden hour / dramatic rim / high-key]
- **Mood:** [2–3 adjectives]
- **Aspect ratio:** [one of 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16] · **Resolution:** [1K/2K/4K] · **Format:** [png/jpeg/webp]
- **Negative constraints:** [what must NOT appear]
- **Prompt (final, paste-ready):**
  > [single flowing prompt assembled from the fields above]
- **Variants:** [n] — [what varies between them]
- **File naming:** assets/<category>/<asset-name>/<asset_name>_<n>_<timestamp>.png (automation default)
- **Generate with:** `python docs/creative_cli.py custom --category ... --name ... --prompt "..." --aspect-ratio ... --resolution ... --num-images n`
```

If images were generated, append the saved paths under **Results** and say which
variant you recommend and why (one line).

## Quality bar

Before delivering, verify every spec:

- [ ] Subject is concrete enough that two strangers would picture the same image
- [ ] Style, lighting, composition, and mood are each explicitly stated — none left to model default
- [ ] Aspect ratio matches the stated destination (no `1:1` "because default")
- [ ] Negative constraints listed (at minimum: no watermark; state text policy explicitly — models mangle long text)
- [ ] No invented parameters — only the ones in `references/automation.md`; the model is always `fal-ai/nano-banana-pro`
- [ ] Keeper assets got 3+ distinct variants, not one take
- [ ] If automation wasn't run, the deliverable says so and includes runnable commands

Hard don'ts: never claim an image was generated when it wasn't; never put brand
color hex codes in quotes and hope — name the colors in words too ("deep navy
#004E89"); never render paragraphs of text inside an image.

## Integration

- `skills/creative/creative-strategist` → feeds this skill its **style block**
  (paste into every prompt's style/mood/lighting fields).
- `skills/creative/product-photography`, `skills/creative/social-graphics`,
  `skills/creative/brand-asset` → specialized front-ends that produce their own
  prompt specs and use the same automation; route there when the request fits.
- `skills/creative/product-video` and `skills/creative/remotion-script-writer` →
  consume generated stills as source frames / assets.
- `references/automation.md` — full FAL.ai client, CLI, and Python-helper
  reference. Read it whenever you're about to run a generation command.

© sanky369 · MIT · sanky369/vibe-building-skills

Similar skills

All skills for Design →

image-generation by other authors comes first.

image-generation bytedance image-generation 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 image-generation is a Claude Code skill that writes prompts for DALL-E, Midjourney, and Stable Diffusion. It helps shape image requests around a chosen style or format. CX Codex +1 5,800installs image-generation zc277584121 The image-generation skill creates illustrations, diagrams, and other visuals for articles and docs. It chooses between Codex, OpenAI API, and Gemini paths. CX Codex +1 4,000installs image-generation PostPlusAI The image-generation Claude Code skill plans image creation and edits. It sorts the task, model, and reference rules before handing a ready request to the runner. CX Codex +1 709installs image-generation Devin-AXIS image-generation generates image assets through the iPolloWork service for slide decks and web pages. Operates directly in chat without opening Image Studio. CX Codex +1 ★ 7,523repo stars image-generation-gateways calesthio image-generation-gateways is a Claude Code skill for comparing and connecting image-generation gateways. It covers fal.ai, Replicate, and Together AI API work. CX Codex +1 137installs ai-image-generation prime-skills The ai-image-generation 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 +1 393,900installs qianwen-image-generation QianWen-AI qianwen-image-generation is a Claude Code skill for generating and editing images with Wan and Qwen Image models, including text-to-image, style transfer, multi-image composition, and interleaved text-image output. CX Codex +1 6,300installs eachlabs-image-generation eachlabs eachlabs-image-generation is a Claude Code skill that creates images from text prompts via the EachLabs Predictions API. It polls for completion and returns the output image URL. CX Codex +1 351installs NSFW Image Generation eachlabs The NSFW Image Generation skill sends adult image prompts through the each::sense API. Use it for artistic nude, glamour, boudoir, pin-up, fantasy, and fine-art work. CX Codex +1 262installs nanobanana-mcp-image-generation reason-machines The nanobanana-mcp-image-generation skill connects an agent to Gemini image generation and editing with model selection, 4K output, aspect ratios, and templates. Use it for visual assets from a coding workspace. CX Codex +1 172installs

From the same set10

The whole set →
direct-response-copy direct-response-copy is a Claude Code skill that writes persuasive copy around one target action. It covers landing pages, ads, sales pages, and promotional emails. CX Codex +1 415installs tweet-writer tweet-writer — a skill for X/Twitter that generates tweets and threads by researching what works in your niche right now, then offering multiple hook variants and a full thread with alternates to test. CX Codex +1 325installs typography-system typography-system is a Claude Code skill that audits and standardizes app typography, generating modular type scales, Tailwind tokens, and fluid headings based on product density. CX Codex +1 265installs remotion-script-writer The remotion-script-writer skill reads your app or concept and writes a Remotion script in JSON: timed scenes, visual elements, animations, voiceover text. Ready to render immediately. CX Codex +1 228installs product-video Plans animated product videos, creates beat-by-beat shot lists with exact timings, and writes keyframe prompts for fal-ai/nano-banana-pro. CX Codex +1 218installs color-system The color-system skill turns a project’s scattered colors into a token system and checks text contrast. Use it when shaping a palette, fixing contrast, or adding dark mode. CX Codex +1 156installs brand-asset brand-asset turns a brand brief into paste-ready prompt specs for logos, icon sheets, patterns and textures, then renders them through FAL.ai when a key is set. CX Codex +1 111installs product-photography The product-photography Claude Code skill plans product-photo prompts and can generate images through FAL.ai. It activates for product listings, landing pages, and marketing imagery. CX Codex +1 109installs

Project sponsors

Companies that keep this analytics open