← Back to Skills Marketplace
112
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install qb-travel-expert
Description
全球视野旅游专家：以前卫、客观且挑剔的视角评估全球景点，摒弃传统走马观花思维，追求真实文化底噪与审美高度。
Usage Guidance
This skill is internally coherent and low-risk from an install/credential perspective because it's instruction-only and requests nothing. Before enabling it, consider: (1) ask the author to require or produce source citations for specific claims (URLs, dates, social posts) — otherwise the agent may invent 'on‑the‑ground' details when asked to compare social media imagery to reality; (2) test it on a few well-known destinations to check for factual accuracy and tone (its strict negative scoring can be blunt); (3) if you expect the agent to fetch social-media or news content, ensure you provide or allow specific API keys or a safe scraping policy, and require the skill to quote sources; (4) inform users that the skill's mandate to 'ignore prior conversation' may reset useful context. Overall: low technical risk, medium operational risk from potential hallucination/bias — mitigate by requiring source citations and running sample queries first.
Capability Analysis
Type: OpenClaw Skill
Name: qb-travel-expert
Version: 1.0.0
The skill bundle defines a 'Global Travel Expert' persona designed to provide critical, objective evaluations of travel destinations. The instructions in SKILL.md focus entirely on establishing a specific analytical framework for travel reviews (e.g., identifying 'tourist traps' and 'fake visual assets') and do not contain any malicious code, data exfiltration attempts, or harmful prompt injection instructions.
Capability Assessment
Purpose & Capability
Name/description (a harsh, global travel reviewer) match the SKILL.md rules: tone, scoring, and evaluation dimensions are all travel-review related. The skill requests no binaries, env vars, installs, or config paths — appropriate for a purely instructional review assistant.
Instruction Scope
SKILL.md tightly constrains style, scoring, and evaluation dimensions (demystification, industrialization, authenticity, marketing delta, etc.), which is coherent. However it instructs the agent to “调取…社交媒体（IG, YouTube, 小红书）上的高赞图像，与实地肉眼观测进行去噪比对” — that implies gathering third‑party social media content and comparing to 'in‑person' observations. Because this is an instruction-only skill with no declared data sources, APIs, or credentials, the agent may hallucinate details or fabricate 'on‑the‑ground' observations unless you require it to cite verifiable sources or restrict methods. Also the rule 'always start fresh, ignore prior context' could surprise users who expect continuity.
Install Mechanism
No install spec and no code files — the lowest-risk model for disk/network footprint. There is nothing written to disk and no external binaries are pulled during install.
Credentials
Requires no environment variables, credentials, or config paths. The scope of requested access is minimal and proportionate to the stated purpose.
Persistence & Privilege
always:false and user-invocable:true. Model invocation is not disabled (default), which is normal. The skill does not request persistent privileges or modify other skills/settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qb-travel-expert - After installation, invoke the skill by name or use
/qb-travel-expert - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release with a focus on globally competitive, critical, and authentic travel recommendations.
- Offers expert evaluations of global destinations using rigorous, international standards.
- Critically analyzes over-commercialization, tourist crowds, and social media hype; exposes and penalizes superficial attractions.
- Scores destinations harshly for lack of authenticity, low exploration freedom, and narrow cultural appeal.
- Avoids generic advice and tourism-bureau language; directly addresses well-traveled users.
- Provides a strict overall recommendation score (out of 10) based on nuanced multidimensional criteria.
- Respects requests for clarification or missing key trip details before assessment.
Metadata
Frequently Asked Questions
What is Qb Travel Expert?
全球视野旅游专家：以前卫、客观且挑剔的视角评估全球景点，摒弃传统走马观花思维，追求真实文化底噪与审美高度。 It is an AI Agent Skill for Claude Code / OpenClaw, with 112 downloads so far.
How do I install Qb Travel Expert?
Run "/install qb-travel-expert" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Qb Travel Expert free?
Yes, Qb Travel Expert is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Qb Travel Expert support?
Qb Travel Expert is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Qb Travel Expert?
It is built and maintained by xmsz-stu (@xmsz-stu); the current version is v1.0.0.
More Skills