Not in the top 1,000 by GitHub stars
Shilren/interview-doc-agent
借鉴 Karpathy LLM Wiki 的求职文档 Agent skill,把零散经历沉淀成经历库,一键生成简历和面试逐字稿,支持 Obsidian 和飞书
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6ebfe9aba989 → 6ebfe9aba989
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6ebfe9aba989
No earlier version was observed for comparison.
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- 生成求职文档
/
How it works
生成求职文档
When your agent uses it
产品经理(及泛求职)面试场景,根据模板风格 + 经历库,生成简历、面试逐字稿,并支持按目标岗位 JD 定制。借鉴 Karpathy 的 LLM Wiki 模式:原始素材先整理成完善的「经历库」,生成时先查索引定位、再只读相关档案,以节省 token 并保证质量。经历库是生成的主来源。
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
1,579 tokensWhen the skill is activated
Reference documents
9,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 目录分工
- 运行模式
- 首次使用:自动初始化(重要)
- 能力一:写简历
- 能力二:写面试逐字稿
- 能力三:按 JD 定制
- 面试方法论(生成逐字稿时遵守)
- 更新经历库
- 注意事项
Files
.gitignoreasset380 bytesLICENSEasset1,064 bytesREADME.mddoc4,612 bytesSKILL.mdcore5,469 bytesdocs/01-理念-karpathy-wiki.mddoc4,724 bytesdocs/02-安装-obsidian.mddoc3,173 bytesdocs/03-接入-飞书.mddoc3,363 bytesdocs/04-使用指南.mddoc2,460 bytesjd/README.mddoc465 bytesmaterials/README.mddoc466 bytesoutput/.gitkeepasset0 bytestemplates/简历/简历模板.示例.mddoc1,541 bytestemplates/逐字稿/产品面试话术模版.示例.mddoc6,782 byteswiki/index.mddoc1,045 bytes经历库/00-个人档案.模板.mddoc877 bytes经历库/01-示例经历.mddoc1,454 bytes
Read SKILL.md
# 生成求职文档(面试 / 求职)
帮用户生成求职文档。三个能力:①写简历 ②写面试逐字稿 ③按 JD 定制简历/逐字稿。
> 路径说明:以下所有路径都相对于本 skill 所在的 agent 根目录(即包含本 SKILL.md 的文件夹)。
> 在 Obsidian 中通常是 `<vault>/doc-agent/`;在飞书中是云文档/Base 中的对应结构。
## 目录分工
```
<agent 根目录>/
├── templates/ 模板库(学写作风格,按产出类型分)
│ ├── 简历/ 简历模板(.tex 排版 / .md 改写)
│ └── 逐字稿/ 面试话术模板 + 范文View the complete source on GitHubSkills included
- 生成求职文档
Repository facts
- License
- MIT
- Created
- Jun 1, 2026
- Last pushed
- Jun 8, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
- No broad tool permissions
- No dangerous shell commands
- 13 network referencesin 3 files: README.md:3 docs/02-安装-obsidian.md:9 docs/01-理念-karpathy-wiki.md:13
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 13 signals by file
README.md
- Network accessline 3
> 把零散经历沉淀成「经历库」,一键生成**简历**和**面试逐字稿**的 AI Skill。 > > 借鉴 [Karpathy 的 LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f),可在 Obsidian / 飞书 / 各类 coding AI 中使用。 - Network accessline 5
> 借鉴 [Karpathy 的 LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f),可在 Obsidian / 飞书 / 各类 coding AI 中使用。 - Network accessline 23
curl -L https://raw.githubusercontent.com/Shilren/interview-doc-agent/main/SKILL.md \ - Network accessline 29
mkdir -p ~/.claude/skills/interview-doc && \ curl -L https://raw.githubusercontent.com/Shilren/interview-doc-agent/main/SKILL.md \ - Network accessline 30
curl -L https://raw.githubusercontent.com/Shilren/interview-doc-agent/main/SKILL.md \ - Network accessline 57
- **非程序员首选**:Obsidian + [Claudian](https://github.com/YishenTu/claudian)、飞书智能伙伴 - Network accessline 95
## License & 致谢 MIT([LICENSE](LICENSE))。致谢 [Karpathy LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)、[Claudian](https://github.com/YishenTu/claudian)、[autoCVmkr 简历模板](https://github.com/kryptoniteX/autocvmkr)。 - Network accessline 96
MIT([LICENSE](LICENSE))。致谢 [Karpathy LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f)、[Claudian](https://github.com/YishenTu/claudian)、[autoCVmkr 简历模板](https://github.com/kryptoniteX/autocvmkr)。
docs/01-理念-karpathy-wiki.md
- Network accessline 13
Andrej Karpathy 在 [LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) 里提出一个知识库模式,核心是:
docs/02-安装-obsidian.md
- Network accessline 9
- Obsidian 本质是一堆 Markdown 文件夹,天然适合当知识库 - [Claudian 插件](https://github.com/YishenTu/claudian) 把 AI(Claude Code)嵌进 Obsidian 侧边栏,能直接读写你 vault 里的文件 - Network accessline 10
- [Claudian 插件](https://github.com/YishenTu/claudian) 把 AI(Claude Code)嵌进 Obsidian 侧边栏,能直接读写你 vault 里的文件 - Network accessline 17
1. 安装 [Obsidian](https://obsidian.md)(如已装跳过) - Network accessline 29
curl -L https://raw.githubusercontent.com/Shilren/interview-doc-agent/main/SKILL.md \
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 13 facts
- Network access in prose of documentationREADME.md:3Low confidence
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in code of documentationREADME.md:23Low confidence
- Network access in code of documentationREADME.md:29Low confidence
- Network access in code of documentationREADME.md:30Low confidence
- Network access in prose of documentationREADME.md:57Low confidence
- Network access in prose of documentationREADME.md:95Low confidence
- Network access in prose of documentationREADME.md:96Low confidence
- Network access in prose of documentationdocs/01-理念-karpathy-wiki.md:13Low confidence
- Network access in prose of documentationdocs/02-安装-obsidian.md:9Low confidence
- Network access in prose of documentationdocs/02-安装-obsidian.md:10Low confidence
- Network access in prose of documentationdocs/02-安装-obsidian.md:17Low confidence
- Network access in code of documentationdocs/02-安装-obsidian.md:29Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Unknown | No evidence | |
| Codex | Unknown | No evidence | |
| Cursor | Unknown | No evidence | |
| Gemini CLI | Unknown | No evidence | |
| GitHub Copilot | Unknown | No evidence | |
| OpenCode | Unknown | No evidence |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.