by sharzoy
AI 求职助手 Skill：简历解析 → JD 硬性条件核对 → A/B/C 匹配评分 → 生成投递包（开场白、HR模拟、简历优化建议）。保留人工确认环节，不进行无人值守批量投递。
# Add to your Claude Code skills
git clone https://github.com/sharzoy/auto-job-applyGuides for using ai agents skills like auto-job-apply.
Last scanned: 9/13/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-13T09:00:47.315Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how auto-job-apply compares with popular alternatives.
auto-job-apply is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by sharzoy. AI 求职助手 Skill：简历解析 → JD 硬性条件核对 → A/B/C 匹配评分 → 生成投递包（开场白、HR模拟、简历优化建议）。保留人工确认环节，不进行无人值守批量投递。. It has 118 GitHub stars.
Yes. auto-job-apply 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/sharzoy/auto-job-apply" and add it to your Claude Code skills directory (see the Installation section above). auto-job-apply ships a SKILL.md manifest, so compatible agents can discover and load it automatically.
auto-job-apply is primarily written in Python. It is open-source under sharzoy 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 auto-job-apply 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.
Never submit until the user explicitly confirms.
Docs: README.md · docs/scoring.md · reference.md
One .txt per job under grade folder:
applications/packets/A|B|C/<date>-<company>-<role-slug>.txt
Template: templates/packet.txt
Must include top 摘要卡（等级/星级/推荐原因或🚫原因/硬性核对）+ 一～六 + 七 HR视角 + 八 简历修改建议 + 九 投递备注.
- [ ] 1. Ingest JD
- [ ] 2. Hard-requirement check → scorecard → A/B/C (docs/scoring.md)
- [ ] 3. Write packet into packets/{A|B|C}/
- [ ] 4. Dry-run
- [ ] 5. Confirm (A→B priority; C default skip)
- [ ] 6. Submit
- [ ] 7. Log (include grade)
| Grade | Score | Action |
|---|---|---|
| A | 90–100 | 优先投；简历建议「无需改」 |
| B | 60–89 | 可投；先包装表述（八） |
| C | <60 | 不推荐；写🚫原因；默认不进一键投递 |
防误判： 任 1 项 JD 硬性未过 → 分封顶 79（不能 A）；≥2 项 → 封顶 59（C）。技能再像也不能强行 A。
Show/submit order: A high→low, then B high→low. C listed separately.
Approve phrases: 确认投递 / 一键投递 / 强制投递 …
Not approve: 先别投 / 跳过
GitHub About： AI 求职助手 Skill：简历解析 → JD 硬性条件核对 → A/B/C 匹配评分 → 生成投递包（开场白、HR模拟、简历优化建议）。保留人工确认环节，不进行无人值守批量投递。
一个基于 AI Agent 的求职辅助 Skill，帮助用户从职位分析到投递准备完成完整流程：
不是无人值守群发器。 人工确认→ 预览打招呼原文 → 等你说「确认投递 / 一键投递」→ 才点 招聘软件的「立即沟通」等按钮。
Repository name
auto-job-apply
Description（About 栏）
AI 求职助手 Skill：简历解析 → JD 硬性条件核对 → A/B/C 匹配评分 → 生成投递包（开场白、HR模拟、简历优化建议）。保留人工确认环节，不进行无人值守批量投递。
Topics（标签）
cursor-skill, job-search, resume, boss-zhipin, 51job, ai-agent, chinese
| 给谁读 | 文件 |
|---|---|
| 人类（安装、理念、演示） | 本 README |
| Agent / Cursor | SKILL.md |
| 打分公式 | docs/scoring.md |
| 平台与确认指令 | reference.md |
applications/packets/{A|B|C}/<日期>-公司-岗位.txt（摘要卡、打招呼、HR 视角、简历建议…）支持平台约定：Boss 直聘、前程无忧、智联、公司站、邮件（见 reference.md）。
~/.cursor/skills/auto-job-apply/
cp profile.template.md profile.md
cp config.example.yaml config.yaml
cp applications/log.example.md applications/log.md
profile.md：姓名、联系方式、resume_path、目标岗位、min_match_score。用 auto-job-apply 处理这个岗位，先生成材料，别投：
<JD 或链接>
确认后再说：确认投递 或 一键投递。
详见 docs/scoring.md。
| 等级 | 分数 | 含义 |
|---|---|---|
| A | 90–100 | 强匹配，建议优先投递 |
| B | 60–89 | 有机会；需包装简历表述（尤其 60–80） |
| C | <60 | 不推荐；写清🚫原因 |
examples/sample-scorecard.jsonexamples/sample-scorecard-hardfail-C.jsonPacket 按优先级进目录：applications/packets/A|B|C/。
默认 项目/场景 Final：在{项目/场景}中我担任{角色}，负责{具体工作}，帮前司{价值/结果}。看到贵司{岗位}岗，我能把这段经验用在{帮你做的1-2件事}上。 有作品集时追加邀请语+链接。规则与 legacy 备选见 templates/greeting.md。
| 块 | 内容 |
|---|---|
| 摘要卡 | 等级/分/星/结论/推荐原因或🚫不建议原因/硬性核对 |
| 一～六 | 岗位信息、打招呼、定位、Cover、Form、邮件 |
| 七 HR视角模拟 | 优势✓ / 疑虑× / 可能淘汰原因 |
| 八 简历修改建议 | A免改；B/C 给「现状→改法」（不整份重写） |
| 九 投递备注 | 状态与确认门闩 |
完整版式见 templates/packet.txt、examples/sample-packet.txt。
写稿 → 展示 Final → 你下指令 → 才提交
一键投递默认只投 A→B（已排序）；C 需强制
| 你说 | 效果 |
|---|---|
确认投递 / 发送 |
投当前 |
一键投递 / 一键投递 1,3 |
批投 A+B |
强制投递 |
明确投 C |
跳过 / 编辑后再投 / 先别投 |
不投或改稿 |
完整说明：reference.md。
applications/log.example.mdpython scripts/stats_log.py
python scripts/stats_log.py --log applications/log.md
在 notes 里写上「已回复」「面试」等，脚本会粗算回复率。
.gitignore 已排除：
profile.md、config.yamlapplications/packets/、applications/log.md、cookies / .env只提交 *.template / *.example / examples/ 脱敏样例。
auto-job-apply/
├── SKILL.md
├── README.md
├── LICENSE
├── config.example.yaml
├── profile.template.md
├── reference.md
├── docs/scoring.md
├── prompts/ # score / packet / confirm
├── templates/ # packet.txt, greeting.md
├── examples/ # 脱敏 JD + 打分卡 + packet
├── scripts/stats_log.py
└── applications/ # 本地 log / packets/A|B|C（gitignore）
MIT — see LICENSE.
求职材料与账号安全自负；本工具不保证面试或录用结果。