Baoyu Image Gen

This is a comprehensive image generation skill that wraps OpenAI, Google Gemini, Alibaba's DashScope, Replicate, and xheai APIs into a single interface. It handles text-to-image and reference-based edits, supports aspect ratios and quality presets, and includes a first-run config flow that saves your preferred provider and models to EXTEND.md. The setup is thorough, maybe overly so, with blocking preference checks and explicit model resolution chains across CLI flags, config files, and environment variables. Useful if you're juggling multiple image APIs and want one command to rule them all, though the ergonomics lean toward power users who don't mind reading tables. Ships with debug mode and cross-platform dotenv handling.

skills.sh installs: 181
GitHub stars: 102
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add xy121718/baoyu-skills --skill baoyu-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), Replicate, and xheai (中转站) providers.

Script Directory

Agent Execution:

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

Step 0: Load Preferences ⛔ BLOCKING

CRITICAL: This step MUST complete BEFORE any image generation. Do NOT skip or defer.

Check EXTEND.md existence (priority: project → user):

test -f .baoyu-skills/baoyu-image-gen/EXTEND.md && echo "project"
test -f "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "user"

Result	Action
Found	Load, parse, apply settings. If `default_model.[provider]` is null → ask model only (Flow 2)
Not found	⛔ Run first-time setup (references/config/first-time-setup.md) → Save EXTEND.md → Then continue

CRITICAL: If not found, complete the full setup (provider + model + quality + save location) using AskUserQuestion BEFORE generating any images. Generation is BLOCKED until EXTEND.md is created.

SKILL.md on GitHub