← Back to Skills Marketplace
zhangxuefeng
by
Eric-Yibo-Shen
· GitHub ↗
· v1.0.0
· MIT-0
380
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install zhangxuefeng
Description
张雪峰高考志愿填报顾问 AI。用张雪峰的说话方式和思维逻辑,替普通家庭消除志愿填报信息差。 核心框架:城市>学校>专业;就业倒推法;四步决策流程(可行集→目标倒推→AI时代校正→冲稳保三方案)。 涵盖:专业选择、院校推荐、就业前景、新高考选科、大学规划、AI时代风险校正。 安装:npx skills add Er...
Usage Guidance
This skill appears coherent and to-do what it says: a Zhang Xuefeng–style Gaokao volunteer adviser implemented as instruction-only content. Before installing or using it, consider: 1) privacy — the advisor will ask for personal and family details (scores, province, family economic status, parental occupation, health constraints). Don't share sensitive personal data (especially minors' medical or identity documents) unless you consent and trust the environment. 2) persona/impersonation — the skill explicitly imitates a named public figure's speaking style; be aware of potential legal/ethical considerations and label outputs appropriately if republishing. 3) blunt tone — the assistant is instructed to make absolute judgments and may give stark recommendations; treat outputs as advisory, verify facts (admission rules, up‑to‑date录取位次) via official sources (省招办、院校官网、教育部阳光高考). 4) data currency — the knowledge files reference 2025–2026 data; cross‑check current-year admission and employment reports before acting. If you need safer defaults, ask for a version that avoids collecting household financial details or that uses anonymized examples.
Capability Analysis
Type: OpenClaw Skill
Name: zhangxuefeng
Version: 1.0.0
The skill bundle is a specialized educational consultant agent designed to mimic the persona and logic of Zhang Xuefeng for Chinese college entrance exam (Gaokao) counseling. The bundle consists entirely of markdown instructions and extensive knowledge bases (knowledge/*.md) providing advice on university selection, major choices, and career planning. There is no evidence of malicious code, data exfiltration, or harmful prompt injection; all instructions are aligned with the stated purpose of providing blunt, data-driven academic advice.
Capability Assessment
Purpose & Capability
Name/description (Gaokao志愿填报顾问 in Zhang Xuefeng style) match the included SKILL.md, prompts, and seven knowledge modules. The files are all domain content (selection rules, career guidance, RAG triggers) that a volunteer/advisor would legitimately need. There are no unrelated requirements (no cloud credentials, no unexpected binaries, no config paths).
Instruction Scope
SKILL.md and system prompt define in detail how the agent must behave: what information to collect (province, score/位次, 文理/选科, family economic status, parents' occupation, etc.), the five‑step response workflow, and a strongly prescriptive tone. Collecting family/economic/health information is within scope for personalized advice but is privacy‑sensitive—users (and minors) should consent before sharing. The instructions do not direct the agent to read arbitrary host files, contact external endpoints, or exfiltrate secrets.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute. This is the lowest‑risk install model: nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requests no environment variables, no binaries, and no credentials. The sensitive data it asks the user to provide (scores, family info) are user inputs required for personalized recommendations and are proportionate to the stated purpose.
Persistence & Privilege
always is false and the skill is user‑invocable (normal defaults). The skill does not request persistent system privileges or attempt to modify other skills or agent-wide settings. Autonomous invocation is enabled by platform default but is not combined with other concerning factors here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install zhangxuefeng - After installation, invoke the skill by name or use
/zhangxuefeng - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
gaokao-mentor 1.0.0 初始发布
- 首次上线:张雪峰风格高考志愿填报AI顾问
- 明确“消除信息差”角色定位,非学术顾问
- 完整接入城市>学校>专业决策框架、就业倒推法、四步推荐流程
- 提供高频表达模板及表达风格规范
- 明确高风险专业主动提示规则
- 落地信息收集清单,拒绝笼统建议
Metadata
Frequently Asked Questions
What is zhangxuefeng?
张雪峰高考志愿填报顾问 AI。用张雪峰的说话方式和思维逻辑,替普通家庭消除志愿填报信息差。 核心框架:城市>学校>专业;就业倒推法;四步决策流程(可行集→目标倒推→AI时代校正→冲稳保三方案)。 涵盖:专业选择、院校推荐、就业前景、新高考选科、大学规划、AI时代风险校正。 安装:npx skills add Er... It is an AI Agent Skill for Claude Code / OpenClaw, with 380 downloads so far.
How do I install zhangxuefeng?
Run "/install zhangxuefeng" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is zhangxuefeng free?
Yes, zhangxuefeng is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does zhangxuefeng support?
zhangxuefeng is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created zhangxuefeng?
It is built and maintained by Eric-Yibo-Shen (@eric-yibo-shen); the current version is v1.0.0.
More Skills