# Add to your Claude Code skills
git clone https://github.com/jinhanbuilds/bushiershiLast scanned: 9/6/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-06T08:23:49.572Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how bushiershi compares with popular alternatives.
bushiershi is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by jinhanbuilds. 对抗模型输出不良表达习惯的 Agent Skill. It has 62 GitHub stars.
Yes. bushiershi 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/jinhanbuilds/bushiershi" and add it to your Claude Code skills directory (see the Installation section above).
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 bushiershi 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.
bushiershi 是一个对抗模型输出不良表达习惯的 Agent Skill。
它仅在明确调用 $bushiershi 时生效。
我用了三年多 GPT。过去几个月,我把真实任务里反复纠正的表达问题整理成了这个 Skill。
在希望使用该 Skill 的 Git 项目目录中执行:
npx skills add jinhanbuilds/bushiershi --skill bushiershi -y
该命令会把 Skill 安装到当前项目的 .agents/skills/bushiershi。
不使用 Skills CLI 时,下载本仓库并在仓库根目录执行:
mkdir -p ~/.agents/skills
cp -R skills/bushiershi ~/.agents/skills/
如果你的客户端使用其他 Skills 目录,请把目标路径替换为对应位置。
在请求中明确调用 $bushiershi:
使用 $bushiershi 改写下面这段中文,保留原有事实、立场和不确定性:
<原文>
也可以从零生成:
使用 $bushiershi,根据以下事实写一段面向用户的中文说明:
<事实与要求>
这些不是禁词。判断一句话正在做什么,再决定如何修改。
删空话、合并重复或调整句段时,也不能损伤这些内容。
.
├── LICENSE
├── README.md
├── ORIGIN.md
└── skills/
└── bushiershi/
├── SKILL.md
└── agents/
└── openai.yaml
bushiershi不是而是本项目使用 MIT License。