Maintainer of this skill?
Automated security scan — not a certification.
by sunyuzheng
Source-grounded public context for 立正: Superlinear posts, selected comments, YouTube, Public Axioms V1, and 《真本事》.
# Add to your Claude Code skills
git clone https://github.com/sunyuzheng/lizheng-open-contextGuides for using ai agents skills like lizheng-open-context.
Last scanned: 9/1/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-01T09:11:58.378Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how lizheng-open-context compares with popular alternatives.
lizheng-open-context is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by sunyuzheng. Source-grounded public context for 立正: Superlinear posts, selected comments, YouTube, Public Axioms V1, and 《真本事》. It has 145 GitHub stars.
Yes. lizheng-open-context passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/sunyuzheng/lizheng-open-context" and add it to your Claude Code skills directory (see the Installation section above).
lizheng-open-context is primarily written in Python. It is open-source under sunyuzheng on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh lizheng-open-context against similar tools.
No comments yet. Be the first to share your thoughts!
30 days in the Featured rail · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
立正的公开资料库：以已发表的原文和媒体为依据，保存原文、精校文本，以及人物、节目和来源关系。给人和AI提供可检索、可引用、可继续开发的数据。个人网站与问问立正消费同一份版本。
| 目录 | 内容 | 用途 |
|---|---|---|
corpus/ |
文章、课程与书籍文字、视频字幕、对谈原稿、原话摘录及译稿 | 阅读、检索与引用，保留作者、日期、时间码和质量 |
catalog/ |
人物、别名、节目、参与关系、伴读链接及来源目录 | 共享结构化事实，按人物和来源发现资料 |
context/ |
AI整理的阅读地图、框架与判断卡 | 独立的提炼层，帮助阅读并回指原文 |
index/ |
按来源、时间与主题组织的目录 | 导航，由数据自动生成 |
scripts/ |
校验、导入、目录生成与本地搜索 | 维护和使用资料 |
docs/ |
数据合同、引用协议与开发说明 | 接入不同产品 |
catalog/guests.json分别保存实体、来源与参与关系，catalog/guest-articles.json保存已发表伴读文章的链接，catalog/guest-names.json是由它们生成的名字表。人物ID稳定，姓名、别名、介绍和链接可持续校准。结构化对谈原稿保留字幕单元及各自的时间码、发言者和质量。
当前资料数量、时间与许可由数据生成，见目录；文件版本由release-manifest.json固定。
无需向量数据库，可先运行本地搜索：
python3 scripts/search.py "如何建立信念" --layer raw --json
python3 scripts/search.py "职业发展" --layer derived --json
python3 scripts/search.py "growth accounting" --type book
python3 scripts/search.py "项目复盘" --type video
python3 scripts/search.py "科学能解释的东西很少" --type excerpt
结果带原文片段、来源、日期和归属，视频可定位到对应时间点。原稿与AI提炼分别检索；节目参与者用于发现资料，字幕单元用于确认具体发言。
接入Agent或其他产品：
资料修改在本仓库完成，校验后生成release。网站从固定commit和manifest生成嘉宾页快照；Context Infra重建语料副本、索引与证据包。更新数据与调整检索策略各在其所属项目进行。
python3 scripts/validate_release.py --write-manifest
python3 scripts/validate_release.py
原稿、精校版本和质量依据保留可追溯关系。公开release按已审阅的源文件及许可收录，具体规则在config/。新素材在本地整理后，审阅准确公开变更，再发布到main。发现错字、归属问题或断链可开issue。
每份资料保留自己的许可：
具体使用条件见LICENSE.md。--license open可限定搜索自由再利用的资料。
参考实现：真本事Advisor · Superlinear Advisor · 社区项目
欢迎带着使用结果、问题或新的实现加入仓库讨论。