seahi/baoyu-skills
1
0
Fork 0
mirror of https://github.com/JimLiu/baoyu-skills.git synced 2026-07-19 00:49:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(baoyu-image-gen): clarify model resolution priority and add model display requirement

Browse Source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Jim Liu 宝玉
2026-02-28 01:38:10 -06:00
parent 2188160418
commit cc016f3b16
1 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/baoyu-image-gen/SKILL.md
+14 -6
View File
@@ -110,14 +110,22 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provi
**Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env` **Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`
## Replicate Model Configuration ## Model Resolution
When using `--provider replicate`, the model can be configured in the following ways (highest priority first): Model priority (highest → lowest), applies to all providers:
1. CLI flag: `--model <owner/name>` 1. CLI flag: `--model <id>`
2. EXTEND.md: `default_model.replicate` 2. EXTEND.md: `default_model.[provider]`
3. Env var: `REPLICATE_IMAGE_MODEL` 3. Env var: `<PROVIDER>_IMAGE_MODEL` (e.g., `GOOGLE_IMAGE_MODEL`)
4. Built-in default: `google/nano-banana-pro` 4. Built-in default
**EXTEND.md overrides env vars**. If both EXTEND.md `default_model.google: "gemini-3-pro-image-preview"` and env var `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview` exist, EXTEND.md wins.
**Agent MUST display model info** before each generation:
- Show: `Using [provider] / [model]`
- Show switch hint: `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`
### Replicate Models
Supported model formats: Supported model formats: