sketch-image-prompt

Transforms article content or summaries into minimalist hand-drawn style JSON prompts for AI image generation tools. Use this skill whenever the user wants to create any kind of visual from text content — including banners, article illustrations, inline diagrams, infographics, or concept visuals. Trigger on requests like "turn this into a visual", "create an image prompt", "make an illustration for this", "generate a diagram from this article", "I need a sketch for this section", or any request combining content analysis with image/visual prompt generation. Always use this skill when the user provides text content and wants an AI-ready image prompt output.

跳到安装

仓库: okooo5km/Skills4U
最近来源活动: 2026年5月4日 06:26
检测到的 SKILL.md 语言: 中文
星标: 152
分支: 29

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/okooo5km/Skills4U --skill sketch-image-prompt

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

zipic

macOS image compression and Zipic-app expert. Drives the local Zipic.app via its `zipic` CLI (Zipic >= 1.9.5) — structured JSON results, per-file `saved_pct`, exit codes. Falls back to the URL Scheme on older builds. Supports JPEG, PNG, WebP, HEIC, AVIF, TIFF, ICNS, PDF, GIF, JPEG-XL, SVG. Batch, format conversion, resize, presets, compression history. MUST use this skill when the user mentions: compress / optimize / shrink image, image too large, batch compress, convert to WebP/AVIF/HEIC/JXL, reduce image size, optimize SVG, minify SVG, preset, compression history. Also: "compress these" / "these images are too big" with image files (incl. SVG) attached. ALSO use for Zipic-usage Q&A: pricing, Pro features, activation, free-tier limits, troubleshooting, vs ImageOptim/TinyPNG/Squoosh, CLI install, format support, Raycast/Shortcuts integration. macOS only. Requires Zipic.app.

2026-08-24

orchard

Use the local Orchard app to interact with macOS Apple apps and services: Calendar, Reminders, Clock, Mail, Contacts, Notes, Music, Weather, Messages, Location/Maps, and Apple Shortcuts. Two execution paths reach the same running Orchard.app: the `orchard` CLI (default — use this if you have a Bash/shell tool, e.g. Claude Code, Codex CLI, Cursor) and a stdio MCP server, `orchard mcp`, exposed as prefixed MCP tools (fallback for sandboxes that cannot run the macOS CLI, e.g. Claude Cowork, bridged through Claude Desktop). Use when a task asks to read or manage local calendar events, reminders, Apple Mail, contacts, notes, iMessage/SMS, Apple Music playback/library, weather, current time/timezones, geocoding, routes, current location, or local Shortcuts.

2026-08-09

chatwoot

Use the official Chatwoot CLI to inspect and operate Chatwoot conversations, messages, contacts, inboxes, labels, teams, help center articles, webhooks, reports, and raw Application API paths. Use when Codex needs to call Chatwoot APIs, work with a self-hosted Chatwoot domain, fetch customer feedback, summarize recent conversations, send replies or private notes, assign/label/close conversations, or guide a user through installing and authenticating the Chatwoot CLI.

2026-06-12

查看这个仓库的全部 Skills

name	sketch-image-prompt
description	Transforms article content or summaries into minimalist hand-drawn style JSON prompts for AI image generation tools. Use this skill whenever the user wants to create any kind of visual from text content — including banners, article illustrations, inline diagrams, infographics, or concept visuals. Trigger on requests like "turn this into a visual", "create an image prompt", "make an illustration for this", "generate a diagram from this article", "I need a sketch for this section", or any request combining content analysis with image/visual prompt generation. Always use this skill when the user provides text content and wants an AI-ready image prompt output.
license	MIT
allowed-tools	visualize:show_widget, visualize:read_me
compatibility	Requires visualize tools for color palette widget display. Compatible with Midjourney, Stable Diffusion, and any AI image generation tool that accepts natural language prompts.
metadata	{"version":"1.3.0","created":"2026-03-01","updated":"2026-05-04","author":"Boss","changelog":[{"version":"1.3.0","date":"2026-05-04","changes":"Hardened layout rules to prevent single-axis compression. Added prominent warning, decision tree, and pre-generation self-check. Demoted linear flow layouts to require ≥4 elements with strong sequence. Template now mandates explicit spatial positioning per element and enforces 'elements distributed across full canvas, NOT a single line' clause."},{"version":"1.2.1","date":"2026-05-04","changes":"Fully purged mint green tones — removed 嫩草 #F1F8E9 from the palette (visually a pale mint) and fixed the leftover '薄荷绿背景' example in the design summary template. Palette reduced from 14 to 13 backgrounds."},{"version":"1.2.0","date":"2026-03-19","changes":"Expanded layout system from single linear flow to 5 spatial modes per ratio (linear, satellite, zone, diagonal, quadrant). Added layout selection principles to prevent vertical whitespace waste."},{"version":"1.1.0","date":"2026-03-18","changes":"Removed mint green preset. Expanded color palette to 14 backgrounds covering tech, business, creative, education, nature, and brand themes."},{"version":"1.0.0","date":"2026-03-01","changes":"Initial release. Minimalist hand-drawn prompt generator with aspect ratio selection and 5 color presets."}]}