JimLiu

Provides a universal release workflow that auto-detects version files and changelogs for various projects. Use it for managing releases, creating new versions, or backfilling historical releases.

Compresses images to WebP (default) or PNG with automatic tool selection. Use when the user asks to compress image, optimize image, convert to webp, or reduce image file size.

Analyzes article structure, identifies positions requiring visual aids, and generates illustrations using a Type × Style × Palette three-dimensional approach. This skill is activated when the user requests to illustrate article, add images, generate images for article, or 为文章配图.

Extracts resources and JavaScript from Electron apps (.asar bundles), restoring original sources from .js.map or formatting minified code with Prettier. Use to extract, decompile, or inspect the source code of Electron apps.

AI image generation with APIs including OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate. It supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files, offering sequential or parallel processing for multiple prompts.

Create professional, dark-themed SVG diagrams for various technical and conceptual visualizations, such as architecture, flowcharts, and system processes.

Posts content and articles to X (Twitter), including regular posts with images/videos and long-form X Articles in Markdown. Use this skill when asked to 'post to X', 'tweet', or 'publish to Twitter'.

Formats plain text or markdown files including frontmatter, titles, summaries, headings, bold text, lists, and code blocks. Use this skill to format markdown, beautify articles, add formatting, or improve article layout, outputting to {filename}-formatted.md.

Generates professional slide deck images from content by creating outlines with style instructions for individual slides. Use this skill when the user asks to 'create slides', 'make a presentation', 'generate deck', 'slide deck', or 'PPT'.

Converts X (Twitter) tweets and articles to markdown with YAML front matter, using a reverse-engineered API that requires user consent. Activate this skill when the user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion.

Fetches any URL and converts it to markdown using the baoyu-fetch CLI, which includes adapters for sites like X/Twitter and YouTube. It handles login/CAPTCHA, making it ideal for saving webpages as markdown.

Downloads YouTube video transcripts/subtitles and cover images using a URL or video ID. It supports multiple languages, translation, chapters, and speaker identification, caching data for quick re-formatting.

Generates images and text via a reverse-engineered Gemini Web API, supporting text and image generation from prompts, vision input with reference images, and multi-turn conversations. Use it when other skills need an image generation backend, or for user requests like 'generate image with Gemini', 'Gemini text generation', or vision-capable AI generation.

A knowledge comic creator supporting multiple art styles and tones. It generates original educational comics with detailed panel layouts and batch image generation.

This skill summarizes WeChat group chat highlights into a structured digest using the wx-cli binary. It generates a normal digest by default, with an optional "roast" version, and maintains per-group history and user profiles with built-in privacy.

Posts content to WeChat Official Accounts (微信公众号) via API or Chrome CDP. It supports articles (HTML, markdown, plain text) and image-text posts (贴图) with multiple images.

Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics.

Converts Markdown to styled HTML with WeChat-compatible themes. It supports code highlighting, math, Mermaid, PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links.

Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. It breaks content into 1-10 cartoon-style image cards optimized for social media engagement.

Translates articles and documents between languages using three modes: quick (direct), normal (analyze then translate), and refined (analyze, translate, review, polish). It supports custom glossaries and terminology consistency via EXTEND.md.

Posts content to Weibo, supporting regular posts with text, images, and videos, as well as headline articles with Markdown input via Chrome CDP.

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood), combining 11 color palettes and 7 rendering styles. It supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when the user asks to generate a cover image, create an article cover, or make a cover.