title — 技能工具
v1.0.0Maximize CTR (Click-Through Rate) by leveraging emotional hooks and platform algorithms.
0· 24·0 当前·0 累计
by 安全扫描
OpenClaw
安全
high confidenceThe skill's files, instructions, and requirements are consistent with its stated purpose (generating high‑CTR Xiaohongshu titles); it doesn't request credentials, installs, or hidden endpoints.
评估建议
This skill is internally coherent and appears to do what it claims: generate attention-grabbing Xiaohongshu titles using the included examples, keyword dictionary, templates, and a local Python validator. Before installing, consider: (1) provenance — the owner and homepage are unknown, so treat it as unverified third‑party content; (2) runtime — the agent may execute the bundled validator.py locally, so ensure your agent environment permits executing small Python scripts and that you are comfort...详细分析 ▾
✓ 用途与能力
Name/description (maximize CTR for Xiaohongshu) align with the provided assets: examples.md (style examples), references.md (keywords/templates/blacklist), and validator.py (final filtering rules). No unrelated env vars, binaries, or config paths are requested.
✓ 指令范围
SKILL.md instructs the agent to categorize input, pull examples/templates/keywords from included files, draft candidates, and apply the local validator.py filter. It does not instruct reading unrelated system files, contacting external endpoints, or exfiltrating data. The only file access is to the bundled reference files and validator.
✓ 安装机制
This is an instruction-only skill (no install spec). The only code is a small local Python validator script; there are no downloads, third‑party package installs, or archive extraction. Risk from install mechanism is low.
✓ 凭证需求
The skill requires no environment variables, credentials, or config paths. All required inputs are user-provided text and bundled reference files; requested access is proportionate to the purpose.
✓ 持久化与权限
always is false and there is no request for persistent or cross-skill configuration. The skill does not ask to modify other skills or system-wide settings.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/16
- Initial release of the xiaohongshu-title skill. - Provides expert title generation for Xiaohongshu, focused on maximizing CTR with emotional hooks and platform algorithm insights. - Integrates a style reference with 200+ high-performing real titles across 8 categories. - Uses strategic asset files containing keyword dictionaries, title formulas, and compliance checks. - Includes a Python-based quality control script ensuring all outputs are emoji-rich, concise (<22 characters), and compliant. - Defines a workflow for categorization, keyword/formula selection, style injection, virtual validation, and presents 5 top titles with cover image advice.
● Pending
安装命令
点击复制官方npx clawhub@latest install godfery-title
镜像加速npx clawhub@latest install godfery-title --registry https://cn.longxiaskill.com 镜像可用
技能文档
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 fromexamples.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
- Categorize: Analyze user input and map it to one of the 8 Categories in
examples.md. - Retrieve Assets:
references.md -> [High-CTR Keywords].
- Select 2 formulas from references.md -> [Templates].
- Drafting: Generate 10 candidates.
examples.md category.
- Filtering (Virtual Script Execution):
validator.py.
- Discard any title that feels "AI-generated" (e.g., uses "Exploring", "Comprehensive").
- 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).