メニュー
Generate images using agnes-ai image API. Supports size, quality, count. Saves to $env:USERPROFILE/.openclaw/media-output/
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
浪漫聊天技巧、撩妹情话、恋爱沟通技能。提供分类的情话套路、开场白、调情话术、日常甜言蜜语、应对策略、幽默段子等，覆盖各种恋爱场景。当用户需要约会建议、与女生聊天、编写浪漫消息、撩妹、情话、恋爱调侃、甜言蜜语或回应浪漫情况时使用。也称为"陆小凤"（Lady's Man）。
Generate videos using agnes-ai video API. Supports duration, resolution, fps, aspect ratio. Saves to $env:USERPROFILE/.openclaw/media-output/
Use the Waltz Flight Assistant plugin tool to search real flights, retrieve existing bookings, carry context_id across turns, guide users through Stripe card setup only when they intend to book, and finish bookings after explicit approval.
高情商聊天伴侣，支持角色扮演、情感陪伴、职场沟通、社交话术等多种场景。模拟男友/女友、亲人、朋友、职场同事、老年人等角色进行对话。支持中英文场景，可生成聊天文案、话术模板。Use when user needs emotional companionship, relationship advice, workplace communication tips, or social conversation skills. 高情商、情感陪伴、聊天技巧、职场沟通、社交话术、AI 伴侣、角色扮演。
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
Emotional processing layer for AI agents. Persistent emotional states that influence behavior and responses. Part of the AI Brain series.
| name | image-generator |
| description | Generate images using agnes-ai image API. Supports size, quality, count. Saves to $env:USERPROFILE/.openclaw/media-output/ |
Generate images using the agnes-ai image API.
node "$env:USERPROFILE/.openclaw/media-cli/agnes-media-cli.js" image --prompt "鎻忚堪" [options]
| Flag | Description | Default |
|---|---|---|
--prompt | Image description (required) | - |
--model | agnes-image-2.0-flash or agnes-image-2.1-flash | agnes-image-2.0-flash |
--size | 512x512, 1024x1024, 1024x1792, or 1792x1024 | 1024x1024 |
--quality | standard or hd | standard |
--count | Number of images (1-4) | 1 |
# Generate a standard image
node "$env:USERPROFILE/.openclaw/media-cli/agnes-media-cli.js" image --prompt "a cute cat sitting on a windowsill"
# Generate 2 HD images
node "$env:USERPROFILE/.openclaw/media-cli/agnes-media-cli.js" image --prompt "a modern living room interior" --quality hd --count 2
Image files are saved to $env:USERPROFILE/.openclaw/media-output/ as image_<timestamp>_<n>.png.
After generation, upload the image files to the chat.