メニュー
调用 Agnes AI 免费 API 生成图片/视频。从 AGNES_API_KEY 环境变量读取密钥。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | Agnes画影 |
| version | 1.1.0 |
| description | 调用 Agnes AI 免费 API 生成图片/视频。从 AGNES_API_KEY 环境变量读取密钥。 |
| allowed-tools | ["Read","Write","Bash","AskUserQuestion"] |
| metadata | {"slug":"agnespaint","trigger":"Agnes、画影、生成图片、生成视频、Agnes AI、agnes画影"} |
多模态生成、图片生成、视频生成、Agnes AI、API 调用
调用 Agnes AI 免费全模态 API，据用户描述生成图片或视频，返回结果 URL。
AGNES_API_KEY 环境变量（运行时自动侦测 OS 与 shell，见下方配置步骤）https://apihub.agnes-ai.com/v1| 步骤 | 操作 |
|---|---|
| 1 | 打开 platform.agnes-ai.com，注册/登录 |
| 2 | 左侧导航 → API Keys → Create API Key |
| 3 | 复制生成的 sk- 开头密钥 |
| 4a | 侦测环境：uname -s 判 OS，echo $SHELL 判 shell |
| 4b | 配置命令（据上一步结果选择）： • Linux/macOS + zsh → echo 'export AGNES_API_KEY="sk-..."' >> ~/.zshrc && source ~/.zshrc• Linux + bash → echo 'export AGNES_API_KEY="sk-..."' >> ~/.bashrc && source ~/.bashrc• macOS + bash → echo 'export AGNES_API_KEY="sk-..."' >> ~/.bash_profile && source ~/.bash_profile• Windows + PowerShell → Add-Content -Path $PROFILE -Value '$env:AGNES_API_KEY="sk-..."'• 其他环境 → 询问用户其 shell 配置文件名 |
| 5 | 验证：curl -s https://apihub.agnes-ai.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer $AGNES_API_KEY" -d '{"model":"agnes-2.0-flash","messages":[{"role":"user","content":"hi"}]}'，返回含 choices 即成功 |
| 用户说 | → 操作 |
|---|---|
| "画/生成图片/做张图……" | 图片 |
| "生成视频/短片/短视频……" | 视频 |
| 未明确 | 默认图片，可反问确认 |
向用户展示你要发送的描述文字，确认后再调 API。
详细参数与 curl 示例见 modules/01-api-reference.md。
快速参考：
| 能力 | 端点 | 模型名 |
|---|---|---|
| 图片 | POST /v1/images/generations | agnes-image-2.0-flash |
| 视频 | POST /v1/video/generations | agnes-video-v2.0（带 v） |
.data[0].url 取 URL.data.status 至 completed，从 .data.remixed_from_video_id 取 URL展示 URL，问用户"还要再生成吗？"
用户：画一只在云朵上睡觉的柴犬，治愈风
→ 确认 Prompt → 调图片 API → 返回图片 URL
用户：做一段赛博朋克城市夜景，5 秒
→ 确认 Prompt → 调视频 API → 轮询至完成 → 返回视频 URL
Use when users ask to design a logo, create a wordmark, generate typographic logo, make text-based brand identity, or request AI image prompts for logo design where the text itself forms the graphic. Triggers: "logo", "wordmark", "字标", "文字logo", "创意logo", "LOGO设计", "AI生图生成logo", "文字图形logo".
📋 GESP试卷处理：从官网下载PDF→提取全文→检查流程图→创建标准化文件(.md/.json/答案.md) | 触发：GESP、真题、试卷处理、gesp真题
Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/pause/resume/delete/run, and always pass --agent-id explicitly.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Generate AI-implementable product requirement documents (PRDs) from one-line product ideas, vague app/site/tool requests, or feature concepts. Use when the user asks for PRD, 产品需求文档, 需求文档, AI 可执行 PRD, 产品规格, MVP 方案, app/site/tool planning, or developer handoff docs for AI coding assistants.
为GESP等级考试生成作业卷子，包含选择/判断/编程题。知识点定制，答案随机分布防猜测。