
xingtu-tool
Use when editing photos for Xiaohongshu, creating image-based posts, designing cover images, retouching product photos, or adding text overlays to images
- Installs
- 205
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/vivy-yi/xiaohongshu-skills --skill xingtu-tool- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads xingtu-tool automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Xingtu Tool (醒图工具)
Overview
Xingtu is a powerful mobile photo editing app designed for social media content. It provides professional retouching, filters, text, and design features optimized for creating Xiaohongshu-worthy image content.
When to Use
Use when:
- Editing photos for Xiaohongshu posts
- Creating cover images (thumbnails)
- Retouching product photos or selfies
- Adding text overlays to images
- Creating before-and-after comparisons
- Designing simple promotional graphics
Do NOT use when:
- Need complex graphic design (use Canva)
- Editing RAW photos professionally (use Lightroom)
- Creating vector graphics (use Illustrator)
Core Pattern
Before (raw, unedited photos):
❌ Dull lighting, flat colors
❌ No text or context
❌ Unretouched skin or product flaws
❌ No visual hierarchy
After (professionally edited):
✅ Bright, vibrant, eye-catching
✅ Clear text overlays with key info
✅ Polished skin or product presentation
✅ Strong visual hierarchy
7 Core Editing Features:
- Retouch - Skin smoothing, blemish removal, body shaping
- Filters - One-tap color grading and mood
- Adjustments - Brightness, contrast, saturation, etc.
- Text - Add titles, subtitles, captions
- Stickers - Decorative elements and graphics
- Templates - Pre-designed layouts
- Beauty - Natural enhancement tools
Quick Reference
| Feature | When to Use | Key Settings |
|---|---|---|
| Retouch | Portraits, product photos | Intensity 30-50% (natural) |
| Filters | Set mood, color grade | "Fresh", "Bright", "Warm" |
| Text | Titles, subtitles, prices | Bold fonts, high contrast |
| Adjustments | Fix exposure, color | Brightness +10, Contrast +15 |
| Templates | Quick designs | Choose Xiaohongshu-optimized |
| Stickers | Add decoration, branding | Use sparingly (3-5 max) |
| Beauty | Selflies, portraits | Natural look (avoid over-smooth) |
Implementation
Step 1: Import Photo
Open Xingtu:
- Download Xingtu app (App Store or Google Play)
- Tap "Edit" (编辑) or big "+" button
- Select photo from camera roll
- Photo loads into editor
Pro tip: Use highest resolution photo available (at least 1080x1080 pixels for Xiaohongshu).
Step 2: Apply Basic Adjustments
Tap "Adjust" (调节):
Essential adjustments (most photos need):
- Brightness (亮度): +5 to +15 (brighten slightly)
- Contrast (对比度): +10 to +20 (add depth)
- Saturation (饱和度): +5 to +15 (vibrant colors)
- Sharpness (锐化): +10 to +20 (crisp details)
Advanced adjustments (if needed):
- Highlights (高光): -10 to -20 (recover blown-out areas)
- Shadows (阴影): +10 to +20 (brighten dark areas)
- Warmth (色温): -5 to +5 (adjust color temperature)
- Vignette (暗角): -5 to -10 (subtle focus on center)
Pro tip: Adjust slider, then tap original/edited comparison to avoid over-editing.
Step 3: Apply Filters (Optional)
Tap "Filters" (滤镜):
Filter selection strategy:
- Skincare/beauty: "Fresh" (清新), "Bright" (明亮), "Soft" (柔和)
- Fashion: "Contrast" (对比), "Vintage" (复古), "Cool" (冷色调)
- Food: "Warm" (温暖), "Appetite" (食欲), "Sunny" (阳光)
- Lifestyle: "Natural" (自然), "Daily" (日常), "Cozy" (温馨)
Filter intensity:
- Apply filter
- Tap filter again to adjust intensity slider
- Set to 50-70% (subtle, natural)
Pro tip: Less is more. Heavy filters look artificial and hurt credibility.
Step 4: Retouch Portraits (If Applicable)
Tap "Retouch" (修图):
Skin (skin smoothing):
- Tap "Skin" (磨皮)
- Choose brush size
- Paint over skin areas
- Set intensity 30-50% (natural, not plastic)
Blemish removal:
- Tap "Remove" (消除)
- Zoom in on blemish
- Tap to remove
- Repeat for each blemish
Body shaping (use caution - ethical concerns):
- Tap "Body" (美体)
- Choose tool (slim, tall, smooth)
- Adjust intensity 10-30% maximum (subtle enhancement)
- Avoid unrealistic reshaping
Pro tip: Retouch sparingly. Some texture looks more authentic than perfectly smooth skin.
Step 5: Retouch Product Photos (If Applicable)
Tap "Retouch":
Product polishing:
- Dodge/Burn: Brighten product areas, darken shadows
- Clarity (清晰度): +10 to +20 (enhance details)
- Sharpness (锐化): +15 to +25 (crisp edges)
- Vignette: -5 to -10 (focus on product center)
Color accuracy (important for products):
- Avoid heavy filters that distort colors
- Use "Adjustments" more than "Filters"
- Ensure product color matches reality
Step 6: Add Text Overlays
Tap "Text" (文字):
Add title:
- Tap "Add Text" (添加文字)
- Choose font: bold, clean fonts (sans-serif recommended)
- Type title text
- Set color: white or black with high contrast
- Add shadow or outline for readability
Text placement best practices:
- Top third: Title or main message
- Bottom third: Caption, price, or CTA
- Avoid center: Don't cover focal point
- Keep edges: Leave margin (don't put text at very edge)
Text hierarchy:
- Large: Main title (draws attention)
- Medium: Subtitle or key info
- Small: Details or captions
Step 7: Add Stickers (Optional)
Tap "Stickers" (贴纸):
Use stickers for:
- Brand elements (logo, watermark)
- Decorative accents (arrows, shapes)
- Icons (hearts, stars, arrows)
- Labels (sale, new, limited)
Sticker best practices:
- Use 3-5 stickers maximum (don't clutter)
- Place in corners or edges (don't cover content)
- Match brand colors (cohesive look)
- Purposeful only (avoid random decoration)
Step 8: Use Templates (Optional Time-Saver)
Tap "Templates" (模板):
Template advantages:
- Pre-designed layouts
- Xiaohongshu-optimized dimensions
- Professional design elements
- Fast editing (1-2 minutes)
How to use:
- Browse categories (fashion, beauty, food, lifestyle)
- Select template matching your content
- Replace placeholder images with your photos
- Edit text to match your message
- Adjust colors to match brand
Pro tip: Templates are great for beginners, but customize to avoid generic look.
Step 9: Save and Export
Final review:
- Pinch to zoom, check all areas
- Tap original/edited comparison
- Ensure text is readable
- Check colors are accurate (especially for products)
Export settings:
- Tap "Save" (保存) or download icon
- Resolution: Maximum (1080p or higher)
- Quality: High (don't compress)
- Save to camera roll
Upload to Xiaohongshu:
- Open Xiaohongshu app
- Tap "+" → select photo from camera roll
- Add filter in Xiaohongshu (optional, usually skip)
- Add title, description, hashtags
- Post!
Common Mistakes
| Mistake | Why Happens | Fix |
|---|---|---|
| Over-smoothing skin | "Perfection" look | Keep texture, intensity 30-50% |
| Too many stickers | Fun to add | Use 3-5 max, purposeful placement |
| Heavy filters | Want "look" | Intensity 50-70%, mix with adjustments |
| Poor text contrast | Aesthetic choice | White text on dark, black on light |
| Unrealistic body shaping | Insecurity | Avoid or keep minimal (10-20% intensity) |
Real-World Impact
Well-edited photos (real examples):
- Bright skincare product photo → 50K views (professional, trustworthy)
- Natural portrait retouching → 30K likes (authentic, relatable)
- Clean minimalist design → 20K saves (aesthetic, shareable)
Poorly edited photos:
- Heavy filter, unnatural colors → 500 views (low trust)
- Too many stickers, cluttered → 300 views (hard to focus)
- Over-smoothed skin → 200 views (inauthentic, "plastic" look)
Key metric: Professionally edited photos get 3-5x more engagement than unedited ones.
Related Skills:
- REQUIRED: graphic-content-creation (complete image content creation)
- REQUIRED: cover-design (design effective cover images)
- photo-editing (advanced photo editing techniques)
- canva-tool (graphic design for layouts)
- meituxiuxiu-tool (alternative photo editing app)
FAQ
What does the xingtu-tool skill do?
Use when editing photos for Xiaohongshu, creating image-based posts, designing cover images, retouching product photos, or adding text overlays to images
How do I install xingtu-tool?
Run npx skills add https://github.com/vivy-yi/xiaohongshu-skills --skill xingtu-tool in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/xingtu-tool/ (personal) or .claude/skills/xingtu-tool/ (project).
Which AI agents can use xingtu-tool?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is xingtu-tool safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains xingtu-tool?
It is published by vivy-yi in vivy-yi/xiaohongshu-skills. It has 205 recorded installs.
More from vivy-yi/xiaohongshu-skills
short-video-production
vivy-yi/xiaohongshu-skills
Use when creating video content for Xiaohongshu, filming vlogs or tutorials, editing short-form vertical video, or optimizing video for mobile viewing
copywriting-skills
vivy-yi/xiaohongshu-skills
Use when writing Xiaohongshu post content body, creating engaging captions, developing brand voice, or writing product descriptions and recommendations
image-editing
vivy-yi/xiaohongshu-skills
Use when editing and enhancing images for Xiaohongshu content, improving photo quality with filters and adjustments, creating visually appealing images, or preparing images for carousel posts
viral-creation
vivy-yi/xiaohongshu-skills
Open the skill to read its SKILL.md instructions.
traffic-acquisition
vivy-yi/xiaohongshu-skills
Open the skill to read its SKILL.md instructions.
jiaying-tool
vivy-yi/xiaohongshu-skills
Use when editing videos for Xiaohongshu, creating short video content, adding effects and transitions to videos, or needing to add subtitles and music to video clips
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image