imagegen

Included with Lifetime

$97 forever

Generate an image from a text prompt using the best available method, with automatic fallback (built-in image_gen → gpt-image-2 → nano-banana-pro → text-only scene sentence). Returns the image file path and the method used. Internal to `/wf-design`; not user-invocable.

Designscripts

What this skill does


Generate an image from a natural language prompt using the best available method.

## Usage

Called internally by the `wf-design` command. Resolves the best available image generation
method at runtime and produces a visual artifact, or returns a structured text fallback.

Arguments parsed from `$ARGUMENTS`:
- First positional: image prompt (required, or use `--skip-reason`)
- `--output <path>` — file path (default: `.ai/design-probes/<timestamp>.jpg`)
- `--resolution <1K|2K|4K>` — image resolution (default: 1K)
- `--count <1-4>` — number of images to generate (default: 1)
- `--skip-reason <text>` — if provided, skip generation and return this as the skip reason

## Step 0 — Parse and validate

1. Parse `$ARGUMENTS` for the prompt and all flags.
2. If `--skip-reason` is provided → skip all generation, go to Method 4 output format with `method=skipped`.
3. Set output path: if `--output` not provided, use `.ai/design-probes/<unix-timestamp>-<count>.jpg`.
4. Create `.ai/design-probes/` directory if it does not exist.

## Step 1 — Capability waterfall

Try each method in order. Stop at the first success.

### Method 1: Built-in `image_gen` tool

If the `image_gen` tool appears in the available tools list for this session:

1. Call `image_gen` with the prompt.
2. Save the returned image data to the output path.
3. If successful → return `IMAGEGEN_RESULT` with `method=image_gen`.
4. If the tool errors or returns no image → fall through to Method 2.

This is the preferred path. It requires no API key, no subprocess, and no external dependency.

### Method 2: gpt-image-2 via `codex exec`

Requires: `codex` CLI available in PATH.

```bash
bash "$(dirname "$0")/scripts/gen-gpt-image-2.sh" "$PROMPT" "$OUTPUT_PATH"
```

- Exit code 0 = success → return `IMAGEGEN_RESULT` with `method=gpt-image-2`.
- Exit code 1 = codex not found → fall through to Method 3.
- Any other exit code → fall through to Method 3.

### Method 3: nano-banana-pro via Gemini API

Requires: `GEMINI_API_KEY` environment variable.

```bash
python3 "$(dirname "$0")/scripts/gen-nano-banana-pro.py" "$PROMPT" --output "$OUTPUT_PATH" --resolution "$RESOLUTION"
```

- Exit code 0 = success → return `IMAGEGEN_RESULT` with `method=nano-banana-pro`.
- Exit code 1 = GEMINI_API_KEY not set → fall through to Method 4.
- Any other exit code → fall through to Method 4.

Note: nano-banana-pro returns JPEG bytes regardless of extension requested. The script
handles this automatically by adjusting the extension.

### Method 4: Text-only fallback

When no image generation method is available, return a structured scene description.
This is always available. It lets design work proceed and records the prompt for later generation.

## Output Format

**On image success:**

```
IMAGEGEN_RESULT:
  method: <image_gen|gpt-image-2|nano-banana-pro>
  file: <path to generated image>
  prompt: <exact prompt used>
  scene_sentence: <one evocative sentence describing the visual>
```

**On text-only fallback or skip:**

```
IMAGEGEN_RESULT:
  method: <text-only|skipped>
  file: none
  skip_reason: <why image generation was unavailable or skipped>
  prompt: <exact prompt that would have been used>
  scene_sentence: <one evocative sentence describing the visual>
  to_generate_later: |
    GEMINI_API_KEY=<key> python3 .claude/skills/imagegen/scripts/gen-nano-banana-pro.py "<prompt>"
```

The caller (`wf-design shape` or `wf-design craft`) records the result in the design artifact
and sets `image_gate=pass` (for image success) or `image_gate=skipped:<reason>` (for text-only).

## Multiple images (`--count > 1`)

When `--count` is 2, 3, or 4, run the selected method once per count with the same prompt.
Number the output files: `<path>-1.jpg`, `<path>-2.jpg`, etc.
Return one `IMAGEGEN_RESULT` block per image.

Files: 4

Size: 12.9 KB

Complexity: 41/100

Category: Design

Source: https://github.com/jayteealao/agent-skills/tree/main/plugins/sdlc-workflow/skills/imagegen

Related in Design

contribute

Included

Local-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".

Designscripts

architectural-analysis

Included

User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).

Designscripts

mcp

Included

Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.

Designscripts

react-native-skia

Included

Design, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.

Designscripts

plaid

Included

Product Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".

Designscripts

nextjs-framer-motion-animations

Included

Adds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.

Designscripts