image-pipeline

Use this skill when generating images from markdown prompts, creating blog illustrations from text descriptions, or running an end-to-end image generation and optimization pipeline. Takes a markdown file with image prompts, generates via Gemini, uploads to Cloudinary, returns optimized URLs.

SKILL.md

---
name: image-pipeline
version: 1.0.0
description: Use this skill when generating images from markdown prompts, creating blog illustrations from text descriptions, or running an end-to-end image generation and optimization pipeline. Takes a markdown file with image prompts, generates via Gemini, uploads to Cloudinary, returns optimized URLs.
tags: [image-generation, gemini, cloudinary, pipeline, blog, illustrations, ai-images]
triggers:
  keywords:
    - generate blog images
    - image pipeline
    - generate images from markdown
    - create blog illustrations
    - image prompts to cloudinary
    - generate and upload images
  explicit:
    - /image-pipeline
    - /gen-images
tools:
  - Read
  - Task
composes:
  - gemini-api-dev
  - cloudinary
---

# Image Pipeline

Generate images from markdown prompts, upload to Cloudinary, and return optimized URLs. Composes `gemini-api-dev` for generation and `cloudinary` for CDN delivery.

## Behavioral Classification

**Type**: Guided Decision

**Directive**: ASK, THEN EXECUTE

Ask the user for the markdown file, article slug, style preferences, and output directory before executing the pipeline. Then run the full workflow autonomously.

## Execution

When triggered, **immediately**:

1. Read `~/.claude/skills/image-pipeline/agent-prompt.md`
2. Spawn a single Task with `subagent_type: "general-purpose"` passing the agent-prompt content as the prompt
3. Include in the prompt: the user's request, the markdown file path, article slug, any style/brand guide, and current working directory
4. Wait for the agent to complete
5. Present the agent's summary to the user (Cloudinary URLs and metadata)

Do NOT execute the pipeline workflow in this session. The subagent handles everything including Gemini API calls, file I/O, Cloudinary uploads, and URL generation.

## Environment Variables

| Variable | Required | Sensitive | Description |
|----------|----------|-----------|-------------|
| `GEMINI_API_KEY` | Yes | Yes | Google Gemini API key for image generation |
| `CLOUDINARY_URL` | Yes | Yes | Cloudinary connection string |

Both injected via `varlock run --`.

## Quick Reference

```bash
# Full pipeline: generate + upload + get URLs
/image-pipeline docs/articles/my-post.md --slug my-post

# With brand guide
/image-pipeline docs/articles/my-post.md --slug my-post --style brand-guide.md

# Generate only (no upload)
/image-pipeline docs/articles/my-post.md --generate-only --output ./tmp/images
```

## Changelog

### v1.0.0
- Initial release with thin dispatcher pattern
- Composes gemini-api-dev + cloudinary
- Supports IMAGE REQUIREMENT comment blocks in markdown
- Style/brand guide support