Canghe Image Gen

Generates images through OpenAI, Google, DashScope, and Canghe APIs with support for text-to-image, reference images, and aspect ratios. Ships with sensible defaults (2K quality, Google provider) but you can override everything through CLI flags or EXTEND.md preferences. Reference image support is the standout feature here, working across Google's multimodal models, OpenAI's GPT Image edits, and Canghe. Runs sequential by default, which is the right call for stability, but switches to parallel generation when you actually need it. The quality presets and aspect ratio handling save you from looking up provider-specific parameters every time.

skills.sh installs: 598
GitHub stars: 474
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add freestylefly/canghe-skills --skill canghe-image-gen --agent claude-code

Installs into .claude/skills of the current project.

Files

Image Generation (AI SDK)

Official API-based image generation. Supports OpenAI, Google, DashScope (阿里通义万象), and Canghe providers.

Script Directory

Agent Execution:

SKILL_DIR = this SKILL.md file's directory
Script path = ${SKILL_DIR}/scripts/main.ts

Preferences (EXTEND.md)

Use Bash to check EXTEND.md existence (priority order):

# Check project-level first
test -f .canghe-skills/canghe-image-gen/EXTEND.md && echo "project"

# Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
test -f "$HOME/.canghe-skills/canghe-image-gen/EXTEND.md" && echo "user"

┌──────────────────────────────────────────────────┬───────────────────┐ │ Path │ Location │ ├──────────────────────────────────────────────────┼───────────────────┤ │ .canghe-skills/canghe-image-gen/EXTEND.md │ Project directory │ ├──────────────────────────────────────────────────┼───────────────────┤ │ $HOME/.canghe-skills/canghe-image-gen/EXTEND.md │ User home │ └──────────────────────────────────────────────────┴───────────────────┘

SKILL.md on GitHub