/ 目錄 / 演練場 / job-hunt-copilot
● 社群 spontaneousai ⚡ 即開即用

job-hunt-copilot

作者 spontaneousai · spontaneousai/job-hunt-copilot

Build a personal project library once; auto-generate tailored resumes, interview pitches, and mock interviews for every role you apply to.

A job-hunt skill that separates 'what you've done' from 'what you'll tell this company about it.' You feed in a durable project library. For each role, it generates a tailored resume, a pitch script, and mock interview prompts grounded in the JD and your actual experience.

為什麼要用

核心特性

即時演示

實際使用效果

job-hunt-copilot-skill.replay ▶ 就緒
0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "job-hunt-copilot-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spontaneousai/job-hunt-copilot",
        "~/.claude/skills/job-hunt-copilot"
      ],
      "_inferred": true
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "job-hunt-copilot-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spontaneousai/job-hunt-copilot",
        "~/.claude/skills/job-hunt-copilot"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "job-hunt-copilot-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spontaneousai/job-hunt-copilot",
        "~/.claude/skills/job-hunt-copilot"
      ],
      "_inferred": true
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示,然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "job-hunt-copilot-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spontaneousai/job-hunt-copilot",
        "~/.claude/skills/job-hunt-copilot"
      ],
      "_inferred": true
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "job-hunt-copilot-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spontaneousai/job-hunt-copilot",
        "~/.claude/skills/job-hunt-copilot"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列,而非映射。

~/.config/zed/settings.json
{
  "context_servers": {
    "job-hunt-copilot-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/spontaneousai/job-hunt-copilot",
          "~/.claude/skills/job-hunt-copilot"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add job-hunt-copilot-skill -- git clone https://github.com/spontaneousai/job-hunt-copilot ~/.claude/skills/job-hunt-copilot

一行命令搞定。用 claude mcp list 驗證,claude mcp remove 移除。

使用場景

實戰用法: job-hunt-copilot

Tailor your resume to a specific JD without starting over

👤 Job seekers who send 5+ applications a week ⏱ ~15 min beginner

何時使用: You found a role, you have a base resume, you don't want to rewrite from scratch.

前置條件
  • Project library set up — Follow SKILL.md to populate projects.md with detailed project notes once
  • Skill installed — git clone https://github.com/spontaneousai/job-hunt-copilot ~/.claude/skills/job-hunt-copilot
步驟
  1. Paste the JD
    Use job-hunt-copilot. Here's the JD: [...]. Tailor my resume to it using my project library.✓ 已複製
    → Resume with bullets reshuffled and reworded to match JD keywords — without inventing experience
  2. Verify honesty
    Show me any bullet where the framing is a stretch from my actual project notes.✓ 已複製
    → Flags for review, not a clean 'all good'
  3. Export
    Save as resume-acme-senior-pm.md and also convert to PDF.✓ 已複製
    → File saved with clean filename

結果: A tailored resume per role in ~10 minutes, same facts, different emphasis.

注意事項
  • Hallucinated accomplishments — Always use the honesty-check step; your project library is the source of truth
搭配使用: filesystem

Generate a 2-minute 'tell me about yourself' pitch for a role

👤 Interviewees preparing for first-round screens ⏱ ~20 min beginner

何時使用: You have a screen in 24 hours.

步驟
  1. Align pitch to JD
    Use job-hunt-copilot. Write my 2-min pitch for this role [JD]. Emphasize the projects that map to their top 3 requirements.✓ 已複製
    → Script with natural flow, not a resume readout
  2. Practice variants
    Now give me a 45-second version and a 5-minute version.✓ 已複製
    → Three lengths, same core

結果: A pitch that sounds like you, tuned to the role.

注意事項
  • Sounding robotic — Read aloud; trim anything that feels LinkedIn-flavored

Run a mock interview for a specific role

👤 Candidates with a real interview soon ⏱ ~45 min intermediate

何時使用: You want to rehearse the likely questions.

步驟
  1. Set up the role context
    Use job-hunt-copilot. Act as a hiring manager for this role [JD] doing a behavioral interview. Ask me questions one at a time.✓ 已複製
    → One question, waits for answer, then probes
  2. Get feedback
    After we finish, critique my answers — structure, specificity, signal.✓ 已複製
    → Per-answer feedback with improvement hooks

結果: A rehearsed set of stories for the interview.

注意事項
  • Mock becomes chummy and doesn't probe — Tell Claude to be skeptical and ask follow-up 'why' questions

組合

與其他 MCP 搭配,撬動十倍槓桿

job-hunt-copilot-skill + filesystem

Keep a structured folder per role: JD, resume version, pitch, notes

For every new role, create jobs/<company>/<role>/ with JD, resume, pitch, and interview notes.✓ 已複製

工具

此 MCP 暴露的能力

工具輸入參數何時呼叫成本
tailor_resume JD, base resume, project library Per role application 0
pitch_script JD, focus projects Before a screen 0
mock_interview role type, rounds Rehearsal 0
honesty_check resume draft After tailoring, before sending 0

成本與限制

運行它的成本

API 配額
None
每次呼叫 Token 數
Modest per role; the library doc is the biggest token cost
費用
Free
提示
Keep projects.md well-organized — smaller, dense entries beat long narratives.

安全

權限、密鑰、影響範圍

憑證儲存: None
資料出站: Project library and JDs sent to Claude API

故障排查

常見錯誤與修復

Tailored resume invents claims

Your project library may be too sparse; expand it so tailoring has real material to pull from

驗證: Open projects.md and check each entry has metrics and details
Pitch sounds LinkedIn-y

Prompt for 'natural spoken words, not buzzwords'; read aloud

替代方案

job-hunt-copilot 對比其他方案

替代方案何時用它替代權衡
ChatGPT + manual tailoringOne-off applicationsNo persistent library; you repeat yourself
Teal / JobScanKeyword matching onlyNo narrative tailoring

更多

資源

📖 閱讀 GitHub 上的官方 README

🐙 查看未解決的 issue

🔍 瀏覽全部 400+ MCP 伺服器和 Skills