blog-polish-enus-imagesPolish a technical blog draft into an 1000–1200 word, 4-5 section en-US article, preserve technical terms/code, and generate consistent hero + per-section im...
Install via ClawdBot CLI:
clawdbot install j3ffyang/blog-polish-enus-imagesGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 3, 2026
A developer relations team maintains a pipeline that converts raw technical drafts into polished en-US articles with consistent image assets. They use this skill to rewrite drafts into 1000–1200 word posts, preserve code and technical terms, and generate hero plus section image prompts in parallel. This reduces the time from draft to publish and keeps visuals uniform across the blog.
A product documentation team writes internal notes in mixed languages and needs consistent English articles with diagrams. The skill is invoked to polish and restructure content into 4–5 sections while generating image prompts for each section. It ensures English consistency and provides a visual asset plan for documentation pages.
Online course creators draft lecture notes that must be converted into article-style lessons with matching illustrations. This skill polishes the draft to a target word count, segments it into topics, and generates image prompts for each lesson section. The result is a publish-ready course module with a coherent visual theme.
A newsletter editor receives technical submissions and needs to standardize them into a consistent format with images. The skill transforms drafts into en-US articles with a fixed structure and produces hero and section image prompts for the newsletter layout. This maintains brand consistency and speeds up issue preparation.
Open-source maintainers write release notes and deep-dive posts that require clean English and explanatory diagrams. This skill polishes the draft, preserves code snippets, and generates image prompts for the hero and each section. It helps maintainers produce professional blog content without needing a dedicated design team.
The core polishing and image prompt generation is offered for free with limited monthly runs. Advanced features like custom styles, unlimited runs, and priority support are available in a paid tier. This attracts individual bloggers while monetizing power users and teams.
Content agencies and marketing teams license the skill for internal use across multiple writers. The license includes team management, bulk processing, and integration with existing CMS platforms. It is priced annually based on seat count or volume of articles processed.
The skill is distributed as a plugin for popular blogging platforms (e.g., WordPress, Ghost) or AI agent marketplaces like ClawHub. Users pay a one-time fee or a small monthly charge to unlock the plugin inside their existing workflow. Revenue share agreements with platform providers generate distribution.
💬 Integration Tip
This skill requires no external dependencies and works on Linux and macOS; you can invoke it directly from an agent workflow by providing a draft path and optional style parameters. For best results, ensure the draft markdown has a clear H1 title and use consistent section headings, as the workflow counts H2 sections and dynamically generates image prompts based on that count.
Scored Apr 19, 2026
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。