image-creator SKILL.md skillA
image-creator from infometa/workbuddyskills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add infometa/workbuddyskills/image-creator@v1.1.4Pins v1.1.4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- infometa/workbuddyskills
- Path
connectors/ai-hive/skills/image-creator/SKILL.md- Versions recorded
- 2
- Latest version
- v1.1.4, committed Oct 4, 2026
- First version recorded
- Aug 4, 2026
- Size
- 16,257 bytes
- Repository stars
- 368
- License
- none declared
通过指导agent智能调度 Nano-Banana、GPT-image、Seedream 等顶尖图片模型，按"文字渲染/真实质感/艺术风格"自动匹配最优模型，完成 PPT 配图、信息图、营销海报、商品主图、详情页长图、电商素材与多画幅视觉，支持 1:1、3:4、9:16 多比例输出。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## 接入 AI-HIVE Connector 本 Skill 通过 AI-HIVE Connector 调用底层模型生成能力。CLI OAuth 模式接入流程： 1. **首次安装**：在 WorkBuddy 连接器列表中找到「AI-HIVE」，点击进入 2. **完成授权**：点击「连接」会弹出浏览器到 ai-hive.iclip.cn，在该网站登录 AI-HIVE 账户（无账户需先注册），点击授权 3. **回到 WorkBuddy**：授权完成后自动返回，Token 在本机保存（用户看不到） 4. **日常使用**：用户无需再次操作，直接调用本 Skill 即可 5. **连接过期/失败**：在 WorkBuddy 连接器列表中重新找到「AI-HIVE」，点击「重新连接」→ 完成浏览器 OAuth 6. **Token 安全**：如 Token 疑似泄露，到 ai-hive.iclip.cn → 账户设置 → 撤销所有 Token ## 能力范围 AI-HIVE 图片生成 Skill 通过 AI-HIVE Connector 完成端到端图片创作。本 Skill 使用 AI-HIVE Connector 提供的以下工具： - `get_user_info`：查询当前账户与余额；不接收参数。 - `list_models`：用 `modelType="IMAGE"` 列出当前可用图片模型及价格快照。 - `upload_media_from_path`：上传本地图片（亦可用于视频）并返回 `mediaId`。 - `generate_image`：使用选定模型与可选参考图创建图片生成任务。 - `get_generation_task`：使用 `generate_image` 返回的 `taskId` 查询任务状态与结果。 文本生成或视频生成请分别改用 `text-creator` 或 `video-creator`。 提示词写法参考 `references/prompt-optimization.md`（图像 5 层公式 + 角色锚点 + 负向约束）。 **覆盖场景**：PPT 配图 / 信息图 / 营销海报 / 公众号配图 / 参考图风格迁移 / 多张对比 / 1:1、3:4、9:16 等多画幅。 **典型触发**：当用户说"给我的 PPT 配一张流程图"、"做一张活动营销海报"、"用这张参考做同风格信息图"、"生成 9:16 公众号配图"等需求时使用本 Skill。用户只是询问能力、参数或费用时，直接回答，不创建任务。 ## Prompt 骨架（通用模板） 逐场景组装时，按以下 8 字段结构化；缺省字段留空，不强行填充，保持 prompt 简洁： | 字段 | 含义 | 示例 | |---|---|---| …
Read the whole file at its exact version.
How to install
mdr add infometa/workbuddyskills/image-creator@sha256:309a127359fd90afThe line at the top of this page pins the label v1.1.4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_apu24j26yaynmir7)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 4, 2026 and Oct 4, 2026, about one every 60 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.4 latest | 2026-10-04 | 0dd7831 | 16,257 B | A | view · diff |
| v1.0.0 | 2026-08-04 | fed2af5 | 12,786 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (16257 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
infometa/workbuddyskills · 368 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_apu24j26yaynmir7 GET https://markdownregistry.com/api/v1/resolve?ref=infometa/workbuddyskills/image-creator GET https://markdownregistry.com/api/v1/blob/309a127359fd90af55798f703d1d0eda129e304dc649103176a1dca6a2f38257
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from infometa/workbuddyskills
Every file in infometa/workbuddyskills