/ ディレクトリ / プレイグラウンド / career-ops
● コミュニティ santifer ⚡ 即起動

career-ops

作者 santifer · santifer/career-ops

14-mode job search system — resume tuning, JD matching, cover letters, batch application PDFs, Go dashboard.

career-ops packages the whole job-hunt flow as Claude Code skills: resume tuning against each JD, cover letter drafting in your voice, batch PDF generation, application tracking via a small Go dashboard. Built for volume — people who are applying to 50+ roles.

なぜ使うのか

主な機能

ライブデモ

実際の動作

準備完了

インストール

クライアントを選択

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

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

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

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

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

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

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

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "career-ops-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/santifer/career-ops",
        "~/.claude/skills/career-ops"
      ]
    }
  ]
}

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json
{
  "context_servers": {
    "career-ops-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/santifer/career-ops",
          "~/.claude/skills/career-ops"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add career-ops-skill -- git clone https://github.com/santifer/career-ops ~/.claude/skills/career-ops

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方: career-ops

Apply to 30 roles with tuned resumes and cover letters in an afternoon

👤 Job seekers, especially mid-career switching roles ⏱ ~180 min intermediate

使うタイミング: You've saved 30 JDs and each wants a slightly different resume angle.

前提条件
  • Skill installed — git clone https://github.com/santifer/career-ops ~/.claude/skills/career-ops
  • Base resume in Markdown — Convert current resume to /career/resume-base.md
フロー
  1. Ingest JDs
    Use career-ops. Load JDs from /career/jds/. For each, score my resume match + identify the 3 highest-leverage tweaks.✓ コピーしました
    → Scorecard per JD with concrete tweak suggestions
  2. Tune + cover letter
    For each JD: produce a tuned resume + cover letter. Save to /career/applications/<company>/✓ コピーしました
    → Per-company folder with both docs
  3. Render PDFs
    Render every .md to PDF. Verify page count <= 2 for resumes.✓ コピーしました
    → PDFs generated; page counts reported

結果: A stack of tuned application packets, ready to submit in batch.

注意点
  • Over-tuning — resumes look inconsistent across applications — The skill preserves your narrative spine; review a few manually
組み合わせ: filesystem

Run the Go dashboard to track applications

👤 Job seekers needing kanban-style visibility ⏱ ~15 min beginner

使うタイミング: You've applied to 30+ places and lost track of who's at what stage.

前提条件
  • Go installedbrew install go or grab from go.dev
フロー
  1. Start dashboard
    Use career-ops to start the dashboard on localhost:7070.✓ コピーしました
    → Dashboard visible with current apps
  2. Update status
    Move "Acme Co" to "interview-scheduled" for April 30 10am.✓ コピーしました
    → Card updated on board
  3. Weekly review
    What's stale (no action in 14 days)? What's my response rate?✓ コピーしました
    → Stats + stale-item list

結果: A working pipeline view, not a mental juggle.

注意点
  • Dashboard DB isn't backed up — Add the DB path to your dotfiles sync or back it up manually

組み合わせ

他のMCPと組み合わせて10倍の力を

career-ops-skill + filesystem

Organize per-company folders

Save all applications under /career/applications/<slug>/ with a standard structure.✓ コピーしました
career-ops-skill + humanizer-skill

Make cover letters not sound AI

Run humanizer on the cover letter before rendering PDF.✓ コピーしました

ツール

このMCPが提供する機能

ツール入力呼び出すタイミングコスト
score_jd_match resume, jd Per-JD triage 0
tune_resume base, jd, tweaks Once you commit to applying 0
draft_cover_letter resume, jd, voice_samples Always after resume 0
render_pdf md_path Final output stage 0
dashboard_start port? Tracking mode 0

コストと制限

運用コスト

APIクォータ
N/A
呼び出しあたりのトークン
High in batch mode — expect significant token use per batch
金額
Free (MIT)
ヒント
Batch 5 at a time, not 30 — you'll catch voice drift and recalibrate

セキュリティ

権限、シークレット、影響範囲

最小スコープ: filesystem-read filesystem-write
認証情報の保管: Dashboard DB local
データ送信先: None

トラブルシューティング

よくあるエラーと対処法

PDF rendering fails

LaTeX or Typst must be installed. Skill tells you which path it uses — install accordingly.

Dashboard port in use

Pass --port 7171

確認: `lsof -i :7070`
Cover letters all sound identical

Per-company personalization is on by default; increase the per-JD research step depth

代替案

career-ops 他との比較

代替案代わりに使う場面トレードオフ
Huntr / TealYou want a polished SaaS job trackerNot LLM-integrated; manual data entry
A plain spreadsheet + Word templateYou're only applying to a few rolesNo automation on the tuning side

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る