Skip to content

moonlight-lupin/agent-skills / creative/image-studio

image-studio

Verified

Use when the user wants image generation or editing through the local fal.ai three-stage studio workflow — brainstorm a strong prompt, prototype cheaply and iterate on feedback, then produce a finalised image. Covers "generate an image", "make an image/picture/illustration/graphic of…", "create an AI image", "edit/change this image", "make a variation", "upscale this", a "production-ready image", "clean up / enhance a photo", "make this phone shot look professional", imagery "for the deck/post/website/newsletter", or explicit mentions of fal.ai or nano-banana. Do not use for Canva template designs, branded PowerPoint decks, data charts/dashboards, or flowcharts/diagrams. Video generation is out of scope.

examples/example-run.md

View on GitHub
# Worked example — a LinkedIn hero image

A fictional end-to-end run showing the three stages.

## The ask

> "I need a hero image for a LinkedIn post about our UK student-accommodation strategy. On-brand,
> 16:9, eye-catching but not cheesy."

## Stage 1 — Brainstorm (no API call, no egress)

Interviewed the user and agreed a brief:

- **Subject:** abstract architectural motif evoking modern student accommodation — no real building,
  no people.
- **Style:** clean, institutional, abstract-geometric with an architectural hint.
- **Composition:** focal motif left, generous negative space top-right for the headline.
- **Mood / palette:** navy blue + gold/cream accents, off-white ground.
- **Aspect:** 16:9. **Negatives:** no text, no watermark, no clutter.

Saved to `_workings/prompt-brief_pbsa-hero.md`. Confirmed with the user that we'll send this prompt
to fal.ai — **got the go-ahead.**

## Stage 2 — Prototype cheaply (FLUX schnell)

```bash
python scripts/falgen.py generate \
  --prompt "Abstract geometric architectural motif evoking modern student accommodation, deep navy and gold with soft cream accents on a clean off-white background, smooth gradients, modern elegant institutional aesthetic, generous negative space top-right, high detail, sharp focus — no text, no watermark, no clutter" \
  --aspect 16:9 --num 2 \
  --out-dir _workings --name image_pbsa-hero_v1
```

→ `_workings/image_pbsa-hero_v1_1.png`, `_workings/image_pbsa-hero_v1_2.png` (~$0.004 — two 0.59 MP images × $0.003/MP).

User liked v1_2's composition but wanted "warmer, less blue, a bit more depth." Targeted edit
with the cheap default editor (FLUX Kontext dev — holds the composition and dimensions, changes
only what was named):

```bash
python scripts/falgen.py edit \
  --prompt "make the palette warmer with golden amber tones, add subtle depth and shadow" \
  --image _workings/image_pbsa-hero_v1_2.png \
  --out-dir _workings --name image_pbsa-hero_v2
```

→ `_workings/image_pbsa-hero_v2.png` (a few tenths of a cent — Kontext dev is billed per
compute-second, so `falgen` flags it as time-billed rather than print a figure). User: **"That's the one."**

## Stage 3 — Produce the final (confirm the spend first)

Confirmed the production go-ahead. Re-rendered the approved concept faithfully at quality **and at
the final resolution (4K)** in one step — no separate upscale needed (16:9 4K is ample for the post):

```bash
python scripts/falgen.py edit \
  --prompt "same composition, refined to high fidelity, crisp clean edges, premium finish" \
  --image _workings/image_pbsa-hero_v2.png \
  --model fal-ai/nano-banana-pro/edit --aspect 16:9 \
  --arg resolution=4K \
  --out-dir . --name image_pbsa-hero_final
```

→ `image_pbsa-hero_final.png` at the work-folder root. The single **Nano Banana Pro edit (~$0.15)**
is essentially the whole cost of the run; everything before it was fractions of a cent.

## Run-log (appended)

| Stage | Model | Output | ~Cost |
|---|---|---|---|
| Prototype | `fal-ai/flux/schnell` | v1_1, v1_2 | ~$0.004 ($0.003/MP) |
| Edit | `fal-ai/flux-kontext/dev` | v2 | time-billed (~$0.00125/s) |
| Final (4K) | `fal-ai/nano-banana-pro/edit` | final | $0.15 (per image) |
| | | **Total** | **~$0.16** |

Handed to the user: *"`image_pbsa-hero_final.png` is ready — a draft asset for your review. It
hasn't been posted anywhere; place real headline text over the negative space in your post tool
when you're happy with it."*
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall