by Sunanzhe2004
A toolkit for turning internship materials into resume-ready bullets and interview-ready project narratives, with achievement auditing, JD-based ranking, AI-heavy phrasing checks, and structured interview prep outputs.
# Add to your Claude Code skills
git clone https://github.com/Sunanzhe2004/shushu-internship-resume-optimizerGuides for using ai agents skills like shushu-internship-resume-optimizer.
Last scanned: 8/25/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-25T04:37:54.423Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}shushu-internship-resume-optimizer is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Sunanzhe2004. A toolkit for turning internship materials into resume-ready bullets and interview-ready project narratives, with achievement auditing, JD-based ranking, AI-heavy phrasing checks, and structured interview prep outputs. It has 101 GitHub stars.
Yes. shushu-internship-resume-optimizer 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/Sunanzhe2004/shushu-internship-resume-optimizer" and add it to your Claude Code skills directory (see the Installation section above).
shushu-internship-resume-optimizer is primarily written in Python. It is open-source under Sunanzhe2004 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 shushu-internship-resume-optimizer against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ 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.
把你的实习材料,从“散乱记录”变成“可投简历 + 可讲项目故事”。
Shushu 会先审计成果与证据,再按目标 JD 排序,最后生成简历 bullet、项目总结、STAR 草稿、面试 Q&A 和风险检查清单。
最近更新:2026-07-14

⚠️ 使用前请先脱敏:不要提交公司内部文档、真实用户数据、密钥、访问凭证,或任何不能公开传播的实习材料。
这一轮更新把主流程进一步收敛到 model-first, script-second:
achievement_audit 优先读取 sources.json 里的 structured_extract_path 或 structured_extractbusiness_docs 默认主要补业务上下文,不再单独产生成果候选污染主线resume_rank / interview_pack 进一步收回了脚本里的写法模板和项目类型硬编码,更偏向做结构化压缩、排序、提示与可读性复核更推荐的使用顺序是:
project_summary.md 或等价原始项目材料。structured_extract.json。sources.json 里通过 structured_extract_path 接入这份结构化结果。business_docs 主要承担业务背景和流程上下文补充,而不是主导成果抽取。很多实习材料的问题不是“没有内容”,而是内容太散:
这个项目的目标不是替你“直接编一份简历”,而是先把原始材料拆开审计,再把可验证的成果、证据、风险和缺口整理出来,最后生成更适合你自己二次确认和改写的求职材料。
code_repo、project_summary、business_docs环境要求:Python >= 3.10
仓库内自带一套可公开提交的最小示例输入,适合先验证命令、输出结构和工作流,再替换成你自己的本地材料。
示例文件:
examples/minimal_input/sources.jsonexamples/minimal_input/project_summary.mdexamples/minimal_input/business_overview.mdexamples/minimal_input/target_jd.txtgit clone https://github.com/Sunanzhe2004/shushu-internship-resume-optimizer.git
cd shushu-internship-resume-optimizer
python -m venv .venv
macOS / Linux:
source .venv/bin/activate
python -m pip install -e ".[dev]"
python -m shushu_internship_tool.achievement_audit \
--sources examples/minimal_input/sources.json \
--out demo_reports/audit \
--name demo-materials
python -m shushu_internship_tool.resume_rank \
--jd examples/minimal_input/target_jd.txt \
--achievements demo_reports/audit/achievement_audit.json \
--target-role llm-application-intern \
--out demo_reports/rank
python -m shushu_internship_tool.interview_pack \
--project-notes demo_reports/rank/resume_rank.json \
--target-role llm-application-intern \
--out demo_reports/interview
Windows PowerShell:
.\.venv\Scripts\Activate.ps1
python -m pip install -e ".[dev]"
python -m shushu_internship_tool.achievement_audit `
--sources examples/minimal_input/sources.json `
--out demo_reports/audit `
--name demo-materials
python -m shushu_internship_tool.resume_rank `
--jd examples/minimal_input/target_jd.txt `
--achievements demo_reports/audit/achievement_audit.json `
--target-role llm-application-intern `
--out demo_reports/rank
python -m shushu_internship_tool.interview_pack `
--project-notes demo_reports/rank/resume_rank.json `
--target-role llm-application-intern `
--out demo_reports/interview
跑完后优先看:
demo_reports/audit/overview.mddemo_reports/rank/resume_project_summary.mddemo_reports/interview/interview_qa.md主流程:
JD + 多源实习材料 -> achievement_audit -> resume_rank -> interview_pack
可选增强:
business_docs -> doc_knowledge
推荐顺序:
sources.json,把代码仓库、项目总结和业务背景文档整理进去。achievement_audit,确认成果抽取、证据和风险提醒是否合理。resume_rank,判断哪些成果最适合当前目标岗位,并检查项目数、bullet 数和可读性提醒是否合理。interview_pack,把结果转成 STAR、项目介绍和面试问答,再由 skill / prompt 做最终口语化或风格整理。把上面 Demo 里的 examples/minimal_input/... 替换成你自己的 your_materials/... 即可。最小输入结构可以参考 examples/minimal_input:
sources.json:输入索引,串起 repo、总结和业务文档project_summary.md:长一点也没关系,适合先交给工具做拆解business_overview.md:帮助补足业务背景、上下游关系和问题场景target_jd.txt:目标岗位 JD,用来做成果排序和表达校准如果你想让材料先走结构化抽取,sources.json 可以这样写:
{
"code_repo": [
{ "path": "./repo", "label": "main-repo" }
],
"project_summary": [
{
"path": "./project_summary.md",
"label": "internship-summary",
"structured_extract_path": "./structured_extract.json"
}
],
"business_docs": [
{ "path": "./business_overview.md", "label": "business-context" }
]
}
如果你还想让工具辅助理解业务文档,可以额外运行:
python -m shushu_internship_tool.doc_knowledge --docs your_materials/business_overview.md --mode basic_rag --query "What are the main failure modes?" --out reports/knowledge
运行主流程后,通常会得到三组核心结果:
reports/audit/:成果审计、证据、风险提醒、业务背景改写reports/rank/:按目标 JD 排序后的简历版项目总结,包含 bullet 数控制、可读性复核和可人工审阅的合并候选reports/interview/:项目介绍、STAR 草稿、面试 Q&A、风险回答;默认提供结构化骨架,最终语气和细化表达建议由 skill / prompt 再处理如果需要业务文档问答或知识检索,可以额外运行 doc_knowledge。
这个仓库基于原项目做了面向“实习简历整理 / 面试复盘”场景的二次开发与定向重构。 感谢原项目开发者提供基础工作流与思路,原始项目:
如果你想改进成果抽取、简历改写、面试表达、测试覆盖或文档内容,建议先阅读 CONTRIBUTING.md,也欢迎直接提交 Issue 或 PR。
使用这个项目整理实习经历、项目材料或业务文档时,请优先遵守所在公司或团队的安全规范,不要触碰公司安全红线。
尤其不要上传、提交或公开以下内容: