{"skill":{"slug":"huo15-img-test","displayName":"Huo15 Img Test","summary":"火一五文生图提示词 v2.3 — 文生图&视频六件套：(1) enhance_prompt.py 文生图：88 风格预设 + 混合预设 (-p A+B --mix 0.6) + 五锁一致性 + 角色设定图 + 系列批量 + basic/pro/master 三档；(2) enhance_video.py 视频提示...","tags":{"enhance":"1.0.0","latest":"2.3.0","prompt":"1.0.0","text-to-image":"1.0.0"},"stats":{"comments":0,"downloads":141,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":5},"createdAt":1776963273221,"updatedAt":1777213906549},"latestVersion":{"version":"2.3.0","createdAt":1777213580189,"changelog":"**v2.3 introduces Claude API smart polish and platform compliance rewriting.**\n\n- Added `claude_polish.py`: Use Claude API for intelligent prompt refinement and professional artistic rewrites.\n- Added `safety_lint.py`: Detects and rewrites prompts with terms easily blocked by SD/MJ/DALL-E for compliant artistic usage.\n- Now provides a \"six-in-one\" toolkit: prompt enhancement, video prompt, reference prompt reverse-engineering, direct image output, intelligent polish, and safety/compliance rewriting.\n- Supports new collaboration by chaining Claude/GPT/Gemini AI tools for improved prompt quality and compliance.\n- All core scripts and docs updated to integrate and describe the new polish and safety features.","license":"MIT-0"},"metadata":null,"owner":{"handle":"zhaobod1","userId":"s17f6q72skfgyjycm2frgdc8dn83v5mk","displayName":"Job Zhao","image":"https://avatars.githubusercontent.com/u/13188275?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.0","updatedAt":1777213906549}}