SkillCompass MCP — 使用場景, 安裝 & 即時演示

為什麼要用

核心特性

Multi-dimensional skill scoring (clarity, activation, correctness, cost)
'Weakest link' identification across a bundle
Suggests concrete SKILL.md edits
Before/after eval harness
JavaScript tooling — runs locally

即時演示

實際使用效果

skillcompass-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": {
    "skillcompass-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Evol-ai/SkillCompass",
        "~/.claude/skills/SkillCompass"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

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

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

~/.codeium/windsurf/mcp_config.json

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

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "skillcompass-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Evol-ai/SkillCompass",
        "~/.claude/skills/SkillCompass"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "skillcompass-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/Evol-ai/SkillCompass",
          "~/.claude/skills/SkillCompass"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add skillcompass-skill -- git clone https://github.com/Evol-ai/SkillCompass ~/.claude/skills/SkillCompass

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： SkillCompass

Find the skill pulling your agent's performance down

👤 Skill authors with 5+ skills installed ⏱ ~45 min advanced

何時使用： You feel the agent has gotten worse, not better, as you added skills.

前置條件

Node 20+ — nvm install 20
Skill cloned and installed — git clone https://github.com/Evol-ai/SkillCompass ~/.claude/skills/SkillCompass; npm i

步驟

Run the evaluator

Score all skills in ~/.claude/skills/ — show me the weakest link.✓ 已複製

→ Ranked skill list with per-dimension scores
Diagnose the loser

For the weakest skill, what specifically is wrong?✓ 已複製

→ Concrete critique (vague description, conflicting with other skill, etc.)
Propose a fix

Suggest a minimal edit to SKILL.md to fix it.✓ 已複製

→ Small, reviewable diff
Re-evaluate

Re-run the eval and show before/after.✓ 已複製

→ Metrics improved, with evidence

結果： A measurably better skill bundle, with a reproducible eval process.

注意事項

Gaming the eval metric instead of helping real tasks — Include task-level downstream metrics (actual agent outcomes), not just text-level

搭配使用： skill-optimizer-skill · filesystem

Review a new skill before you publish it

👤 Skill authors shipping their first bundle ⏱ ~20 min intermediate

何時使用： Before pushing to GitHub and telling the world about your skill.

步驟

Score the draft

Evaluate my draft skill at ./my-skill/.✓ 已複製

→ Dimension scores
Fix obvious issues

Apply the low-hanging suggestions✓ 已複製

→ Edits in SKILL.md

結果： A publication-ready skill rather than a rough draft.

注意事項

Chasing a perfect score — Ship when scores plateau — diminishing returns

組合

與其他 MCP 搭配，撬動十倍槓桿

skillcompass-skill + skill-optimizer-skill

Two complementary tools: SkillCompass ranks, skill-optimizer drills into SKILL.md patterns

Use SkillCompass to pick the worst skill; use skill-optimizer to deeply analyze its SKILL.md.✓ 已複製

skillcompass-skill + filesystem

Operate across the full ~/.claude/skills/ directory

Evaluate every skill in ~/.claude/skills/ and give me a CSV.✓ 已複製

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫	成本
skill-scoring	skill path(s)	Periodic audits	eval compute
weakest-link-id	bundle scores	After scoring	0
fix-suggestion	weak skill + critique	Before editing	0
before-after-eval	pre/post SKILL.md	After applying fixes	eval compute

成本與限制

運行它的成本

API 配額: none beyond your LLM provider (evals use LLM calls)
每次呼叫 Token 數: evals can be heavy — budget 20–100k tokens for a full bundle scan
費用: free, MIT
提示: Run on one skill at a time during iteration; bundle runs only for audits

安全

權限、密鑰、影響範圍

憑證儲存： none at skill level

資料出站： none beyond your LLM provider

故障排查

常見錯誤與修復

Node errors on install

Ensure Node 20+; npm i inside the skill directory.

驗證： node -v

Evals are inconsistent run-to-run

Fix the task seed and use a non-stochastic sample; record provider+model.

替代方案

SkillCompass 對比其他方案

替代方案	何時用它替代	權衡
skill-optimizer-skill	You want a single skill analyzed deeply rather than a bundle ranked	Depth over breadth
manual review	You have 1–2 skills total	Doesn't scale

SkillCompass

為什麼要用

核心特性

即時演示

實際使用效果

安裝

選擇你的客戶端

使用場景

實戰用法： SkillCompass

Find the skill pulling your agent's performance down

前置條件

步驟

注意事項

Review a new skill before you publish it

步驟

注意事項

組合

與其他 MCP 搭配，撬動十倍槓桿

工具

此 MCP 暴露的能力

成本與限制

運行它的成本

安全

權限、密鑰、影響範圍

故障排查

常見錯誤與修復

替代方案

SkillCompass 對比其他方案

更多

資源