Loading...
Loading...
Found 34 Skills
Apparel Image Generation (for models/clothing). Supports single images or image sets: white background images (invisible model), model images, lifestyle marketing images, selling point images, A+ images, size chart images. Direct generation for single image of a single type; automatic orchestration and planning for multiple images of multiple types. Triggered when users upload model images or apparel images (topwear, bottomwear, dresses, outerwear, shoes & hats, etc.) and request actions like "create an image set", "make a model image", "make a lifestyle marketing image", "make a selling point image", "make an A+ image", "make a size chart image", "make a white background apparel image". Pure image editing operations go through linkfox-aigc-imagegen.
Atomic Skill for Brand Gene Style Extraction. Based on product images and user-provided brand gene parameters (main color, font, platform, region, language), extract a unified brand visual language (Brand DNA) and output structured brandGeneJson for consumption by downstream atomic skills. Keywords: brand gene extraction, brand gene extract, brand DNA, brand visual definition, brand tone extraction, brand style extraction, visual identity extraction. Called by the image layout layer (linkfox-aigc-imagegen-cloth / product image layout path) in Step 3; triggered when the user says "extract brand gene", "define brand style", "brand gene", or "brand visual".
Product Image Generation (Non-apparel Category). Supports single images or image sets: white background main images, scene images, close-up images, selling point layout images, A+ detail page images. Single image of a single type is generated directly; multiple images of multiple types are automatically arranged and planned. Triggered when the user says "create an image set", "create a white background image", "create a scene image", "create a selling point image", "create an A+ image", "create a close-up image". Pure image editing operations go through linkfox-aigc-imagegen.
Multi-reference Image to Video Tool: Generate videos based on multiple reference images and prompts. Supports models KLING (Keling), SEED (Doubao), SEED_FAST, HAPPY_HORSE (Bailian). It supports controls for duration, Pro mode, audio, aspect ratio, etc. Triggered when keywords such as "generate video", "multi-image video", "multiple images to video", "multi-reference image to video", "multi image video", "multiple images to video" are used.
AI Video Generation Tool (First/Last Frame/Single Image Mode) generates videos based on the original image and prompts, with optional last frame image support to control the ending scene. Supported models include KLING, WAN, SEED (Doubao), SEED_FAST, and HAILUO. Triggered when users use phrases like "generate video", "AI video", "image-to-video", "make a video", "video generation", "generate video", "image to video", "dynamic video".
AI Image Generation Tool that generates images based on prompts and reference images. Supports multiple models (BANANA/BANANA_2/BANANA_PRO/GPT_2_IMAGE/AIDRAW_EDIT/WAN2_7/SEEDREAM5), with controllable resolution, aspect ratio, and output quantity. Triggered when users say phrases like "generate image", "AI drawing", "AI image generation", "help me draw", "image generation", "image generation", "generate image", "draw a picture", "make a picture", "image-to-image".
AI Text Generation Tool: Uses large language models to generate text content based on prompts, supporting combined understanding of images/videos/text. Available models include GEM_3_FLASH (fast response) and GEM_3_1_PRO (high-quality complex analysis). Triggered when users mention phrases like "AI text generation", "AI writing", "text generation", "help me write a paragraph", "text generation", "generate text", "write with AI", "AI analyze image content", "image recognition", "video analysis".
Turn papers, technical articles, or knowledge content into highly realistic AIGC slides. First create a narrative structure and page-by-page visual direction, then call an image generation model to produce a 16:9 slide image for each page, and finally synthesize into PPTX/PDF. Suitable for paper presentations, group meetings, open courses, technical sharing, and commercial research presentations; use this skill when users mention "paper PPT", "AI-generated PPT", "PPT that doesn't look like AI", "high-quality slides", or "page-by-page AI-generated PPT".
Use when the user needs to turn a real software engineering / computer science project and an existing thesis draft into a submission-ready undergraduate thesis manuscript. Trigger for requests such as "根据项目把论文改成定稿", "按学校模板排版成最终版", "复制初稿后生成定稿 Word", "为定稿降查重", "根据PaperPass报告降AIGC", "继续在手改初稿上改", "恢复原来的图表和数据库说明", or when academic-paper-strategist has already produced an evidence-backed rewrite plan. Outputs a cleaned manuscript, final DOCX workflow, and a separate rework report.
Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.
Autonomous novel writing CLI agent - use for creative fiction writing, novel generation, style imitation, chapter continuation/import, EPUB export, and AIGC detection. Supports Chinese web novel genres (xuanhuan, xianxia, urban, horror, other) with multi-agent pipeline, two-phase writer (creative + settlement), 33-dimension auditing, token usage analytics, creative brief input, structured logging (JSON Lines), and custom OpenAI-compatible provider support.
Guide to Chinese Writing Skills for Generating High-Quality Weekly Newsletters, Blogs, and Tech News Articles