skills

Generates Xiaohongshu (Little Red Book) infographic series with 11 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.

Enterprise markdown-to-html renderer via API service. Sends markdown to api.tentacle.pro and writes returned html locally.

Enterprise WeChat draft publisher via api.tentacle.pro. Uses API_KEY, server-side credential mapping, token caching/refresh, cover upload, inline image upload, and draft/add.

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links. Use when user asks for "markdown to html", "convert md to html", "md转html", "微信外链转底部引用", or needs styled HTML output from markdown.

Initializes an Obsidian vault with a best-practice directory structure, templates, and AI Agent guardrails optimized for text and image content creators. Use when a user asks to set up a new Obsidian vault, organize a messy vault for AI-assisted content creation, or scaffold the creator folder structures and agent rules/standards. Triggers: "initialize vault", "setup obsidian for creator", "scaffold vault", "create creator structure", "init vault".

AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.

Posts content to WeChat Official Account draft box via official API. Supports HTML/Markdown input, cover image upload, inline image upload, and draft saving. Use when user asks to publish article draft to WeChat.

将图文/视频内容自动发布到小红书（XHS）。 支持三类任务：发布图文、发布视频、仅启动测试浏览器（不发布）。

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".

Generates professional infographics with 21 layout types and 20 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".

Adapt, repair, and environment-proof Agent Skills so they run correctly in this vault. Use this skill when: (1) A downloaded or third-party skill needs to be installed/adapted to this vault's runtime (uv/bun), folder conventions, and path rules. (2) An existing skill fails or errors at runtime due to environment issues—wrong Python/TS runner, broken paths, missing inline dependencies, incorrect execution commands, or artefacts written to the wrong location. (3) A skill's shipped docs (AGENTS.md / SKILL.md) conflict with this vault's standards and need to be reconciled. Triggers: "wash this skill", "fix this skill", "this skill is broken", "adapt skill from", "install skill", "skill throws an error", "skill can't find", "update skill to work here".

Compresses images to JPEG/WebP/PNG using an automated multi-platform CLI (sips, cwebp, sharp). Washed for Obsidian Creator Vault: defaults to JPEG at 65 quality (for <1MB output), and auto-archives original files.