mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-06-06 05:50:41 +08:00

Files

xyx 4f7037a6b6 fix: replace hardcoded ~/.desirecore paths with ${DESIRECORE_ROOT} variable (#16 )

## Summary

- 将所有技能文件中的硬编码 `~/.desirecore/` 和 `$HOME/.desirecore/` 路径替换为
`${DESIRECORE_ROOT}/` 变量
- 递增 manifest.json version 至 1.2.1

## Why

dev 模式下 `DESIRECORE_HOME=~/.desirecore-dev`，硬编码路径导致技能读取错误的端口文件和目录。主仓库的
`variable-substitutor.ts` 会在运行时将 `${DESIRECORE_ROOT}` 替换为实际根目录。

## Test plan

- [ ] `npm run dev` 启动后触发任意技能，确认端口路径解析为
`~/.desirecore-dev/agent-service.port`
- [ ] prod 模式确认路径为 `~/.desirecore/agent-service.port`

🤖 Generated with [Claude Code](https://claude.com/claude-code)

2026-05-29 15:36:19 +08:00

5.1 KiB

Raw Permalink Blame History

name, description, license, version, type, risk_level, status, disable-model-invocation, provider, tags, requires, metadata, market

name

description

license

version

type

risk_level

status

disable-model-invocation

provider

tags

requires

metadata

market

minimax-image-gen

Use this skill when the user wants to generate images using MiniMax's image-01 model. Supports text-to-image and subject reference for character consistency. Use when 用户提到生成图片、画图、文生图、创建图片、 AI 绘画、生成插图、画一张、帮我画、设计图片、MiniMax 画图。

Complete terms in LICENSE.txt

1.3.1

procedural

low

enabled

true

minimax

media

image

generation

minimax

tools

Bash

author

updated_at

i18n

desirecore

2026-04-25

default_locale

source_locale

locales

zh-CN

en-US

zh-CN

en-US

name	short_desc	description	body	source_hash	translated_by
MiniMax 文生图	基于 MiniMax image-01 的文本生成图片技能	Use this skill when the user wants to generate images using MiniMax's image-01 model. Supports text-to-image and subject reference for character consistency. Use when 用户提到生成图片、画图、文生图、创建图片、 AI 绘画、生成插图、画一张、帮我画、设计图片、MiniMax 画图。	./SKILL.zh-CN.md	sha256:4630268ef3bd4e23	human

name	short_desc	description	body	source_hash	translated_by	translated_at
MiniMax Image Generation	Text-to-image generation skill powered by MiniMax image-01	Use this skill when the user wants to generate images using MiniMax's image-01 model. Supports text-to-image and subject reference for character consistency. Use when the user mentions generate images, draw a picture, text-to-image, create an image, AI painting, generate illustration, draw one for me, help me draw, design an image, MiniMax drawing.	./SKILL.md	sha256:4630268ef3bd4e23	human	2026-05-03

icon

minimax-image-gen Skill

Mandatory Rules (violations will cause feature failure)

Must use "response_format": "url" — "base64" is forbidden, base64 will cause output truncation
Must access agent-service over HTTPS — https://127.0.0.1:${PORT} with -k to skip certificate verification
Must upload to media-store via /api/media/upload — saving to local paths is forbidden
Must use the dc-media:// protocol to display images — the only way the frontend can render correctly
Use Bash curl throughout — do not use the HttpRequest tool or Python

Complete Execution Flow (strictly follow these three steps)

Step 1: Call the API to generate the image

PORT=$(cat ${DESIRECORE_ROOT}/agent-service.port)
curl -sk -X POST "https://127.0.0.1:${PORT}/api/media-proxy" \
  -H "Content-Type: application/json" \
  -d '{
    "providerId": "provider-minimax-media-001",
    "endpoint": "/image_generation",
    "body": {
      "model": "image-01",
      "prompt": "这里替换为英文图片描述",
      "aspect_ratio": "1:1",
      "response_format": "url",
      "n": 1
    },
    "responseType": "json"
  }'

Extract data.data.image_urls[0] from the JSON response to obtain the image URL.

Step 2: Download and upload to media-store

PORT=$(cat ${DESIRECORE_ROOT}/agent-service.port)
IMAGE_URL="第一步拿到的图片URL"
curl -sL "$IMAGE_URL" -o /tmp/minimax-gen.png && \
curl -sk -X POST "https://127.0.0.1:${PORT}/api/media/upload" \
  -F "file=@/tmp/minimax-gen.png;type=image/png"

Extract the mediaId field from the JSON response (format like xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx.png).

Step 3: Display the image with the dc-media protocol

Write Markdown image syntax directly in your reply text:

![图片描述](dc-media://这里替换为mediaId)

For example: ![白色的猫坐在书桌上](dc-media://a1b2c3d4-e5f6-47a8-b9c0-d1e2f3a4b5c6.png)

The frontend will automatically convert dc-media:// into an accessible image URL and render it.

Parameter Mapping

User Intent	aspect_ratio
Square / avatar	"1:1"
Landscape / scenery / wallpaper	"16:9"
Portrait / phone / poster	"9:16"
Standard photo	"4:3"
Portrait photo	"3:4"

Subject Reference (character consistency)

Add subject_reference in the body:

"subject_reference": [
  { "type": "character", "image_file": { "url": "参考图片URL" } }
]

Error Handling

"error": "未找到匹配的供应商": MiniMax Media Provider not configured
statusCode: 401: Invalid API Key
statusCode: 429: Rate limited, retry later

5.1 KiB Raw Permalink Blame History