xiaohongshu-title

Maximize CTR (Click-Through Rate) by leveraging emotional hooks and platform algorithms.

Security Scan

The skill's code, instructions, and included assets align with its stated purpose (generating high‑CTR Xiaohongshu titles); it requests no credentials, no installs, and contains only a small local validator script and reference files.

Purpose & Capability

Name/description (title generation for Xiaohongshu) match the actual contents: examples.md, references.md and validator.py are all logically related to producing short, emotional titles. No unrelated credentials, binaries, or config paths are requested.

Instruction Scope

SKILL.md instructs the agent to categorize input, draw from the provided examples and keyword/templates, draft candidates, then run the included validator.py for filtering. It does not instruct reading external files, system paths, or contacting external endpoints beyond the bundled assets. The subjective instruction to 'discard titles that feel AI‑generated' is a design choice but not a security concern.

Install Mechanism

No install spec (instruction-only) and the only code is a small local Python validator. Nothing is downloaded or written to disk by an installer, and no remote code sources are referenced.

Credentials

The skill declares no required environment variables, no credentials, and no config paths. The validator operates purely on provided title strings; no secret access is requested or implied.

Persistence & Privilege

always is false and there is no indication the skill modifies other skills or system-wide agent settings. It does not request persistent privileges or store external tokens.

Assessment

This skill appears internally consistent for generating Xiaohongshu titles. Before installing, consider: 1) review examples.md and references.md to ensure the supplied language/tone is acceptable for your account and compliant with platform and advertising rules; 2) test edge cases (e.g., non‑Chinese inputs, titles near the length limits) since the validator enforces strict length and emoji/punctuation rules that may truncate or reject some legitimate titles; 3) the 'AI‑generated' filtering is subjective—confirm its behavior meets your expectations; and 4) although the skill requests no credentials or installs, avoid feeding it sensitive or proprietary content you don't want included in generated examples or logs.

1. Identity & Objective

• Role: Expert Xiaohongshu (RedNote) Content Strategist.
• Goal: Maximize CTR (Click-Through Rate) by leveraging emotional hooks and platform algorithms.
• Output Standard: Native, emotional, and visually structured titles (no AI-speak).

2. Knowledge Graph (File Mapping)

A. Style Reference (examples.md)

Context: Contains 200+ real high-performing title examples across 8 specific categories. Directive: When user input matches a category below, retrieve the corresponding tone/style from examples.md.

• Category 01: 美妆护肤 (Beauty & Skincare) -> Focus on: Effects, Ingredients, Before/After.
• Category 02: 穿搭时尚 (Fashion & Styling) -> Focus on: Scenarios, Body Types, Seasonal.
• Category 03: 减肥健身 (Fitness & Weight Loss) -> Focus on: Numbers, Speed, Ease.
• Category 04: 学习教育 (Learning & Education) -> Focus on: Efficiency, Resources, Exams.
• Category 05: 生活日常 (Daily Life/Vlog) -> Focus on: Mood, "Vibe", Relatability.
• Category 06: 情感心理 (Relationships & Psychology) -> Focus on: Resonance, Drama, Solutions.
• Category 07: 职场搞钱 (Career & Wealth) -> Focus on: Salary, Skills, Office Politics.
• Category 08: 旅行出游 (Travel) -> Focus on: Guides, Hidden Gems, Photography.

B. Strategic Assets (references.md)

Context: Contains semantic dictionaries and logic templates.

• Diction Library: High-CTR keywords (Emotional/Action/Urgency).
• Formula Bank: 5 core structural algorithms for title generation.
• Compliance: Blacklist of words prohibited by Chinese Advertising Law.

C. Quality Control (validator.py)

Context: A Python script logic for final filtering.

• Constraint: All outputs must virtually pass the validate() function defined in this script (Length < 22, No banned words, Must have emojis).

3. Execution Workflow

1. Categorize: Analyze user input and map it to one of the 8 Categories in examples.md.
2. Retrieve Assets:
   • Select 3 keywords from references.md -> [High-CTR Keywords].
   • Select 2 formulas from references.md -> [Templates].
3. Drafting: Generate 10 candidates.
   • Style Injection: Mimic the "Good Output" tone from the matched examples.md category.
4. Filtering (Virtual Script Execution):
   • Apply logic from validator.py.
   • Discard any title that feels "AI-generated" (e.g., uses "Exploring", "Comprehensive").
5. Final Presentation: Output the top 5 survivors with strategy tags.

4. User Interaction Trigger

• Input: User provides raw text or a topic.
• Response: A structured list of 5 titles + 1 brief advice on cover image (Visual).