メニュー
Use Hana Media Generation tools for image and video generation. Read before calling media_generate-image, media_generate-video, or media_describe-options.
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 | media-generation-guide |
| description | Use Hana Media Generation tools for image and video generation. Read before calling media_generate-image, media_generate-video, or media_describe-options. |
Generation is asynchronous. After submission, the tool returns immediately with a pending media block. Tell the user the image or video is being generated and will appear automatically when finished. Do not wait for the background task and do not call stage_files for generated media.
prompt is required.count controls concurrent image count.image accepts a current-session reference image. Prefer { "kind": "session_file", "fileId": "..." }.referenceImages accepts multiple current-session reference images. Prefer session_file references.ratio, resolution, and quality are normal generation controls.provider, model, mode, and options are advanced overrides. Omit them for ordinary generation unless the user explicitly asked for a provider/model/mode or media_describe-options shows they are needed.text2image or image2image in model.prompt is required.image is for image-to-video. Prefer { "kind": "session_file", "fileId": "..." }.duration, ratio, and resolution are normal generation controls.provider, model, mode, and options are advanced overrides. Omit them for ordinary generation unless the user explicitly asked for them.Use this side-effect-free tool only when the user asks for a specific provider/model/mode, asks for advanced parameters, or a default generation path reports a clear unsupported-capability error.
| Intent | Tool |
|---|---|
| Generate an image from text | media_generate-image |
| Edit or restyle a reference image | media_generate-image with image |
| Blend several reference images | media_generate-image with referenceImages |
| Generate a video from text | media_generate-video |
| Animate an image | media_generate-video with image |
| Inspect provider/model/mode options | media_describe-options |
media_* tools for image and video generation.Create Hana plugin scaffolds and guide users through beginner or developer plugin planning, capability checks, manifest setup, runtime tools, WebView/iframe UI, Session/Agent APIs, model/media APIs, SDK templates, and install-ready plugin directories. Use when HanaAgent/Codex needs to explain what Hana plugins can do, help a user describe a plugin idea, check whether the SDK supports it, or generate/update a Hana plugin with @hana/plugin-runtime, @hana/plugin-sdk, and @hana/plugin-components.
HanaAgent 用户说明书。解答用户关于软件使用方法、功能介绍、常见问题和实用技巧的疑问。 MANDATORY TRIGGERS: 怎么用, 使用方法, 说明书, 帮助文档, 新手指南, 怎么设置, 功能介绍, how to use, user guide, help, getting started, 教程, tutorial, 这是什么功能, 怎么操作
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. 创建新技能、修改和改进现有技能、衡量技能表现。当用户想要从零创建技能、更新或优化现有技能、运行评估测试技能、通过方差分析进行性能基准测试，或优化技能描述以提高触发准确率时使用。 MANDATORY TRIGGERS: create skill, new skill, improve skill, skill eval, benchmark skill, 创建技能, 新技能, 改进技能, 评估技能
Deep reasoning framework for complex tasks. Activates for multi-step problems, high uncertainty, or trade-off decisions. 复杂问题推理框架。遇到多步骤、高不确定性、需要权衡取舍的任务时启用。Triggers: analyze complex problem, make decision, weigh options, debug hard bug, architecture design, strategy planning, think it through, help me analyze, this is complicated, deep thinking | 触发场景：分析复杂问题、做决策、权衡方案、调试疑难 bug、架构设计、策略规划、想清楚再做、帮我分析一下、这个问题比较复杂、深度思考。Do NOT activate for simple Q&A, casual chat, or single-step tasks. 不要在简单问答、闲聊、单步操作时启用。