内蒙古养老保险补缴计算工具。用于计算内蒙古地区养老保险补缴金额，包括本金、利息（按月复利计息）、滞纳金等明细。 **触发关键词**：社保补缴、社保补费、补缴、补费、养老保险补缴、社保欠费计算 **使用场景**： 1. 计算历史欠缴养老保险的补缴金额 2. 估算补缴本金、利息、滞纳金明细 3. 对比不同缴费档次（60%/80%/100%/150%/200%/300%）的补缴金额 4. 计算无滞纳金情况下的补缴金额 **输入参数**： - 补缴起止年月（必填） - 缴费档次比例（可选，默认60%，支持--all计算全部档次） - 补缴时间（可选，默认当前时间） - 自定义月缴费基数（可选，设置后忽略档次比例和社平工资） **输出结果**： - 个人本金、单位本金 - 个人利息、单位利息（按月复利计算） - 个人滞纳金、单位滞纳金 - 有滞纳金和无滞纳金分别汇总 - 支持六档对比：60%、80%、100%、150%、200%、300%

Image generation with IMA Open API using only Nano Banana series: Nano Banana, Nano Banana Pro, Nano Banana 2. Budget (Nano Banana2 512px), balanced (Nano Banana2/Pro), premium (Nano Banana Pro 4K). Native aspect_ratio (1:1, 16:9, 9:16, 4:3, 3:4). Requires ima_* API key. Bundled script: scripts/ima_image_create.py.

AI image generation with SeeDream 4.5, Midjourney, Nano Banana 2, Nano Banana Pro. Text-to-image, image-to-image with intelligent model selection and knowledge base support. BEFORE using: READ ima-knowledge-ai skill for aesthetics and best practices. Use for: AI art, product photos, character design, logo design, poster creation, social media graphics. Supports 1K/2K/4K resolution. Requires IMA API key.

Top-tier AI music generation with models: Suno sonic v4, Suno sonic v5, DouBao BGM (GenBGM), DouBao Song (GenSong). One-stop text-to-music with custom mode, lyrics, vocal control, and style tags. Requires IMA API key. Optional: ima-knowledge-ai for workflow and model guidance when installed. Use for: music generation, text-to-music, background music, songs with lyrics, soundtrack, jingles, ambient music, vocal and instrumental tracks. Output: MP3/WAV.

Use when generating speech from text (text-to-speech) via IMA Open API. Use for: voice synthesis, TTS,朗读, 语音合成, 配音, 有声内容. Output: audio URL (mp3/wav). Flow: query products → create task → poll until done. Requires IMA API key. This skill targets seed-tts-2.0 only (seed-tts-1.1 is not supported). Default model is seed-tts-2.0.

Image OCR Reader

Extract and break down content from web documents, PDFs, images, and URLs into structured markdown notes stored locally and synced to Obsidian. Use when the user shares a URL, PDF, screenshot, or document and wants the content converted to organized notes with proper tagging and categorization.

图像生成辅助。支持通过 OpenRouter 直接调用各种生图模型（如 Seedream），为 OpenClaw 优化，支持提示词、尺寸等参数配置。目前仅限 OpenRouter provider。

评估图像生成模型的效果。对指定模型进行全面的文生图、图生图测试，包括不同参数、不同提示词、人物一致性等测试项，生成详细的HTML测试报告。当用户想要测试、评估、对比图像模型效果时使用此 skill。

Nuclear-grade image metadata cleanser. Strip ALL EXIF/GPS/camera data, re-encode with noise injection. Forensically untraceable, reverse image search resistant.

Extend and expand images beyond their original boundaries using each::sense AI. Create panoramic views, convert aspect ratios, add backgrounds, and uncrop photos intelligently.

基于五层拆解法的AI图片提示词生成器。将模糊的创意想法转化为结构严谨、可执行的图像生成规格书，支持多种风格预设和目标工具适配。

Relight photos and images using each::sense AI. Transform lighting conditions, add studio lighting, golden hour effects, dramatic shadows, neon glows, and match lighting to any environment.

Generate professional AI image prompts for any platform and niche — Instagram, LinkedIn, blog headers, YouTube thumbnails, brand visuals, and ads. Works with DALL-E, Midjourney, Stable Diffusion, and Ideogram. Includes style guides and platform sizing specs.

Extract data from construction images using AI Vision. Analyze site photos, scanned documents, drawings.

Turn a source image (or multi-color mask image) into a 3D-printable bas-relief STL by mapping colors (or grayscale) to heights. Use when you have an image from an image-gen skill (nano-banana-pro, etc.) and want a real, printable model (STL) via a deterministic pipeline.

使用智谱AI的GLM-4V-Flash免费多模态API理解图片内容。当用户需要理解图片内容、描述图片、识别图中物体时使用此skill。

Classic image manipulation with Python Pillow - resize, crop, composite, format conversion, watermarks, brightness/contrast adjustments, and web optimization. Use this skill when post-processing AI-generated images, preparing images for web delivery, batch processing image directories, creating responsive image variants, or performing any deterministic pixel-level image operation. Works standalone or alongside bria-ai for post-processing generated images.

Generate AI images with any model using ImageRouter API (requires API key).

Generate AI images via ImaginePro API (Midjourney, Flux, Nano Banana, Lumi Girl, video)

Virtual Imam that leads the five daily Islamic prayers via voice, delivers Friday Jumu'ah khutbahs, and interacts with mussalis in multiple languages.

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

Send iMessages via macOS Messages app using AppleScript. Use when user wants to send a text message/SMS to a phone number. Supports Chinese and English messages. Phone numbers should include +1 prefix for US numbers.