woodshed MCP — 使用場景, 安裝 & 即時演示

為什麼要用

核心特性

Scaffolds new skills with clean SKILL.md + structure
Runs test cases against the skill
Captures ratings and qualitative notes
Iterates on the skill's prompts based on feedback
Track record of which changes helped

即時演示

實際使用效果

woodshed-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": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_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": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "woodshed-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ],
      "_inferred": true
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "woodshed-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/gaearon/woodshed",
        "~/.claude/skills/woodshed"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "woodshed-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/gaearon/woodshed",
          "~/.claude/skills/woodshed"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add woodshed-skill -- git clone https://github.com/gaearon/woodshed ~/.claude/skills/woodshed

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： woodshed

Author a new skill and iterate it to 'actually works'

👤 Skill authors who've noticed their first drafts don't survive real use ⏱ ~120 min advanced

何時使用： You have an idea for a skill but every time you write one, it degrades after 3 uses.

前置條件

Skill installed — git clone https://github.com/gaearon/woodshed ~/.claude/skills/woodshed

步驟

Scaffold

Use woodshed. Create a new skill called 'changelog-writer' that turns git logs into user-facing changelogs.✓ 已複製

→ skills/changelog-writer/ created with SKILL.md
Create test cases

Generate 5 diverse test inputs.✓ 已複製

→ tests/ folder with 5 sample git log fixtures
Run and rate

Run the skill on each. Show me the output; I'll rate.✓ 已複製

→ Outputs presented with rating slots
Iterate based on ratings

Based on my ratings, suggest prompt changes to SKILL.md. Don't apply yet.✓ 已複製

→ Proposed diff with rationale per change

結果： A skill that works on your real use cases, not just the demo.

注意事項

Overfitting to test cases — Hold out some tests; re-run after every iteration to catch regressions

搭配使用： filesystem

Improve a skill that's been disappointing you

👤 Anyone with a skill installed they're unhappy with ⏱ ~60 min intermediate

何時使用： You have a skill that half-works and you can't tell why.

步驟

Characterize the failures

Use woodshed. Here's a skill I installed. Here are 3 sessions where it underperformed. Diagnose.✓ 已複製

→ Pattern in failures — instruction gap, example gap, framing issue
Propose fixes

Propose minimal SKILL.md edits to address those patterns.✓ 已複製

→ Specific diffs

結果： A skill you can trust.

組合

與其他 MCP 搭配，撬動十倍槓桿

woodshed-skill + skill-fetch-skill

Find skills with skill-fetch, improve them with woodshed

Find a changelog-writer skill; install; run woodshed on it to tune for my repo.✓ 已複製

woodshed-skill + filesystem

Persist iteration history across sessions

Keep woodshed logs in skills/<name>/.woodshed/ for traceability.✓ 已複製

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫
scaffold_skill	skill name, goal	New skill
run_tests	skill + test set	Evaluating
capture_rating	rating + notes	After each test
iterate_prompt	skill + ratings	After a rating round

成本與限制

運行它的成本

API 配額: None
每次呼叫 Token 數: High during iteration (many test runs)
費用: Free (Claude API usage applies)
提示: Keep test sets small — 5 tests beats 50 that never get reviewed.

安全

權限、密鑰、影響範圍

憑證儲存： None

資料出站： None from skill

故障排查

常見錯誤與修復

Iteration keeps changing but doesn't improve

Your test set is too narrow; add diverse cases

Skill works in woodshed but not in real use

Production prompts differ from test fixtures; add real-session logs to the test set

替代方案

woodshed 對比其他方案

替代方案	何時用它替代	權衡
Hand-tuning SKILL.md without loop	Simple skills with obvious prompts	Slower convergence; easier to miss regressions
claude-skills-vault-skill	You want ready-made skills, not authoring tools	Different goal

woodshed