Tag Optimization logo

Tag Optimization

Community
vivy-yi
tag-optimization

Use when optimizing hashtags and topic tags on Xiaohongshu posts to increase discoverability, improving search visibility, selecting relevant topic tags, or implementing hashtag strategy for better content distribution

Overview

Publishervivy-yi
Repositoryxiaohongshu-skills
Skill nametag-optimization
Stars
502
Forks
76
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by vivy-yi on GitHub. Read the source before you install it.

Installation

Install the Tag Optimization AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vivy-yi/xiaohongshu-skills/tree/main/skills/02-账号运营/tag-optimization
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Tag Optimization in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tag Optimization on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tag Optimization is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Tag Optimization (标签优化)

Overview

Tag optimization is the strategic selection and combination of hashtags, topic tags, and keywords to maximize Xiaohongshu content discoverability through search, topic pages, and algorithm recommendations, ensuring content reaches the target audience actively searching for relevant topics.

When to Use

Use when:

  • Publishing new content and need optimal hashtag selection
  • Content has low impressions from search/discovery
  • Starting a new account and need initial visibility
  • Targeting specific niche topics or communities
  • Participating in trending conversations
  • Improving content SEO for long-term discoverability

Do NOT use when:

  • Content has no real topic relevance (spammy tagging hurts reach)
  • Relying entirely on hashtags for visibility (content quality matters more)
  • Using trending hashtags irrelevant to content (algorithm penalizes this)

Core Pattern

Before (poor tag strategy):

❌ "Used #skincare #beauty #fashion on every post"
❌ "Why isn't my content appearing in search?"
❌ "Only getting 50 views per post, low discoverability"
❌ "No targeted traffic, just random discovery impressions"

After (optimized tag mix):

✅ "1 broad topic (#skincare) + 3 niche tags (#dryskincare #sensitiveskinroutine) + 1 branded tag (#mybrandchallenge)"
✅ "30% of traffic from search (vs 5% before)"
✅ "Content appearing in relevant topic feeds consistently"
✅ "Targeted audience finding content through search queries"
✅ "Long-term compounding: posts rank for keywords for months"

4 Tag Types Framework:

  1. Broad Topic Tags - High-volume, general categories (#skincare, #makeup)
  2. Niche Specific Tags - Targeted, specific topics (#dryskincare, #budgetmakeup)
  3. Trending/Event Tags - Timely, seasonal (#summerskincare, #newyearroutine)
  4. Branded/Custom Tags - Unique to account (#yourbrandchallenge, #yourtips)

Quick Reference

Tag TypePurposeQuantityExample
Broad TopicCategory exposure1-2#skincare, #makeup
Niche SpecificTargeted reach2-4#dryskincare, #budgetskincare
Trending/EventTimely boost0-2#summerskincare, #2024trends
Branded/CustomBrand identity1#mybrandchallenge

Optimal Mix: 5-8 total tags per post

Implementation

Step 1: Research Relevant Tags

Tag Discovery Process:

Xiaohongshu Tag Research:

1. Search Bar Suggestions
   - Type your main keyword in Xiaohongshu search
   - Note auto-complete suggestions (high search volume)
   - Example: Type "skincare" → "skincare routine", "skincare tips", "skincare for acne"

2. Competitor Tag Analysis
   - Find 5-10 successful accounts in your niche
   - Analyze their most popular posts (500+ likes)
   - Note which tags they use consistently
   - Identify: high-engagement tags, recurring tags, niche-specific tags

3. Topic Page Exploration
   - Browse topic pages related to your niche
   - Check trending tags within topics
   - Note: follower count of topic, post frequency, engagement levels

4. Third-Party Tools (Optional)
   - Qiangua (千瓜数据): Tag popularity metrics
   - Huitun Data (灰豚数据): Tag trends and competition
   - Use for: Tag volume, trending tags, competitive analysis

Tag Research Template:
Main Keyword: [skincare for dry skin]
Broad Tags: #skincare #dryskin
Niche Tags: #dryskincare #sensitiveskin #budgetskincare
Trending: #winterskincare #2024skincare
Branded: #mybrandchallenge

Step 2: Apply Optimal Tag Mix

Tag Combination Strategy:

Tag Selection Framework:

1. Start with 1 Broad Topic Tag
   Purpose: Category-level exposure
   Example: #skincare, #makeup, #fashion, #food

   Selection Criteria:
   - Directly describes your content category
   - High volume (10k+ posts using it)
   - Relevant to your target audience

2. Add 2-4 Niche Specific Tags
   Purpose: Targeted, high-intent audience
   Example: #dryskincare, #budgetskincareroutine, #sensitiveskin

   Selection Criteria:
   - Specific to your content topic
   - Medium volume (1k-10k posts)
   - Less competitive than broad tags
   - Higher follower conversion

3. Include 0-2 Trending/Event Tags
   Purpose: Timely traffic boost
   Example: #summerskincare, #newyearnewme, #2024trends

   Selection Criteria:
   - Currently trending (check topic page)
   - Relevant to content (don't force it)
   - Time-sensitive (only use when active)

4. Add 1 Branded/Custom Tag
   Purpose: Brand identity, UGC collection
   Example: #mybrandchallenge, #mytips, #[brand]routine

   Selection Criteria:
   - Unique to your account
   - Memorable and relevant
   - Encourage followers to use it

Optimized Tag Example:
Title: "7 Budget Skincare Tips for Dry Sensitive Skin"

Tags:
#skincare (broad category)
#dryskincare (niche specific)
#sensitiveskin (niche specific)
#budgetskincare (niche specific)
#budgetskincareroutine (niche specific)
#winterskincare (trending/seasonal)
#mybrandchallenge (branded)

Total: 7 tags (optimal range)

Step 3: Optimize Tag Placement

Tag Positioning Strategy:

Where to Place Tags:

1. In Content Description (Bottom)
   ✅ Add all tags at end of description
   ✅ Separate tags with spaces
   ✅ Mix tag types throughout

   Format:
   "Your content description here...

   #skincare #dryskincare #budgetskincare #winterskincare #mybrandchallenge"

2. In Post Title (Optional)
   ✅ Include 1-2 high-relevance tags naturally in title
   ❌ Don't stuff title with hashtags

   Good: "Dry Skincare Routine That Works #dryskincare"
   Bad: "#Skincare #DrySkin #Routine #That #Works"

3. In Content (Carousel Last Slide)
   ✅ Call-to-action: "Follow #[yourbrandedtag] for more tips"
   ✅ Challenge: "Use #[yourbrandedtag] to share your results"
   ✅ Community: "Tag friends in #[yourbrandedtag]"

Tag Placement Best Practices:
- Primary location: End of description
- Secondary location: Last slide of carousel
- Natural integration: 1-2 tags in title if relevant
- Never: Hashtag stuffing in title or body

Step 4: Test and Iterate Tags

A/B Testing Framework:

Tag Testing Methodology:

1. Control Variable Testing
   - Post similar content with different tag combinations
   - Keep content, title, cover image consistent
   - Only vary hashtags used
   - Measure: impressions, engagement, follower conversion

2. Test Framework
   Week 1: Test Tag Set A (5 broad tags)
   Week 2: Test Tag Set B (5 niche tags)
   Week 3: Test Tag Set C (3 broad + 2 niche + 1 branded)

   Compare metrics:
   - Impressions from discovery
   - Impressions from search
   - Engagement rate
   - Follower conversion rate

3. Identify Winning Patterns
   - Which tags drive most search traffic?
   - Which tags result in highest engagement?
   - Which tags bring most valuable followers?
   - Seasonal: Which tags work best in which months?

4. Document Learnings
   Create tag performance log:
   Tag | Impressions | Engagement | Conversion | Notes
   -----|------------|------------|-------------|-------
   #skincare | 5,000 | 8% | 2% | High volume, low conversion
   #dryskincare | 800 | 12% | 8% | Lower volume, high conversion
   #budgetskincare | 1,200 | 15% | 10% | Best performing niche tag

Optimization Actions:
- Double down on high-conversion niche tags
- Maintain broad tags for category exposure
- Retire low-performing tags
- Test new tags monthly

Step 5: Monitor Tag Performance

Tag Analytics Tracking:

Monthly Tag Analysis:

For each post, track:

1. Discovery Breakdown
   - Views from discovery (algorithm)
   - Views from search (tags/keywords)
   - Views from other sources
   - Goal: Search ≥20% of total views

2. Tag-Specific Metrics
   - Which topic pages featured content?
   - Which search terms brought traffic?
   - Follower conversion by tag

3. Competitive Tag Analysis
   - What tags are competitors using successfully?
   - Any new trending tags in niche?
   - Gap analysis: tags competitors use that you don't

Tag Performance Report Template:
Month: [January 2026]

Top Performing Tags:
1. #dryskincare - 2,500 views, 12% engagement, 8% conversion
2. #budgetskincare - 1,800 views, 15% engagement, 10% conversion
3. #sensitiveskin - 1,200 views, 10% engagement, 6% conversion

Underperforming Tags:
1. #skincare - 5,000 views, 3% engagement, 1% conversion
   Action: Reduce usage, too competitive

New Tags to Test:
1. #winterskincaretips
2. #2024skincareroutine

Actions:
✅ Increase use of high-conversion niche tags
✅ Maintain 1-2 broad tags for category exposure
✅ Test new trending tags monthly
✅ Retire consistently low-performing tags

Common Mistakes

MistakeWhy HappensFix
Using irrelevant trending tagsWant quick exposureOnly use tags relevant to content topic
Too many tags (10+)Fear of missing outUse 5-8 strategic tags, quality over quantity
Only broad tags, no niche tagsEasier to find broad tagsMix broad + niche for targeted reach
Same tags on every postLazy optimizationCustomize tags to each post's specific topic
No branded tagDon't think to create oneCreate unique branded tag for account identity
Ignoring tag performanceDon't track which tags workMonthly tag audit, double down on winners
Tag stuffing in titleThink more tags = betterKeep tags in description body, not title
Not testing new tagsStick to what's familiarTest 2-3 new tags monthly, measure results

Real-World Impact

Case Study: Tag Optimization Transformation

  • Before: Using 3 generic broad tags (#skincare, #beauty, #fashion), 5% search traffic, 100 impressions/post
  • After: Optimized mix (1 broad + 4 niche + 1 trending + 1 branded), 25% search traffic, 500 impressions/post
  • Result: 5x increase in search-driven traffic, higher follower conversion (10% vs 2%), consistent discoverability

Data-Backed Insights:

  • Posts with 5-8 relevant tags get 3x more search impressions than posts with 0-2 tags
  • Niche-specific tags have 2-3x higher follower conversion than broad tags
  • Branded tags used consistently increase UGC by 40%
  • Search traffic has 3x higher follower conversion than discovery traffic
  • Optimal tag mix: 1 broad (20% traffic) + 3-4 niche (60% traffic) + 1 branded (10%) + 1 trending (10%)
  • Tag testing monthly increases overall content performance by 25%
  • Content ranks for niche keywords for 6-12 months (long-term SEO benefit)

Related Skills

REQUIRED: Use content-planning (plan tag strategy for content calendar) REQUIRED: Use data-analytics (track tag performance)

Recommended for tag optimization:

  • hashtag-optimization (topic tag strategy for content creation)
  • keyword-analysis (identify high-value keywords to use as tags)
  • competitor-analysis (analyze competitor tag strategies)
  • content-calendar (plan tag mix across content calendar)

Use tag-optimization WITH:

  • publishing-timing (tags + timing = maximum discoverability)
  • content-planning (integrate tags into content strategy)
  • seo-optimization (tags are part of broader SEO strategy)

Frequently asked questions

What does the Tag Optimization AI skill do?

Use when optimizing hashtags and topic tags on Xiaohongshu posts to increase discoverability, improving search visibility, selecting relevant topic tags, or implementing hashtag strategy for better content distribution

Why use Tag Optimization on TypingMind?

Because you install it once and use it with any model. Tag Optimization is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tag Optimization in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vivy-yi/xiaohongshu-skills/tree/main/skills/02-账号运营/tag-optimization. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tag Optimization?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tag Optimization?

As many as you like. As long as a model supports skills, you can use Tag Optimization with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tag Optimization AI skill free?

It is published on GitHub by vivy-yi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇