woodshed MCP — Use Cases, Install & Live Demo

Why use it

Key features

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

Live Demo

What it looks like in practice

woodshed-skill.replay ▶ ready

0/0

Install

Pick your client

~/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
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

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

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

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

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use 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

When to use: You have an idea for a skill but every time you write one, it degrades after 3 uses.

Prerequisites

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

Flow

Scaffold

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

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

Generate 5 diverse test inputs.✓ Copied

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

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

→ Outputs presented with rating slots
Iterate based on ratings

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

→ Proposed diff with rationale per change

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

Pitfalls

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

Combine with: filesystem

Improve a skill that's been disappointing you

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

When to use: You have a skill that half-works and you can't tell why.

Flow

Characterize the failures

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

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

Propose minimal SKILL.md edits to address those patterns.✓ Copied

→ Specific diffs

Outcome: A skill you can trust.

Combinations

Pair with other MCPs for X10 leverage

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.✓ Copied

woodshed-skill + filesystem

Persist iteration history across sessions

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

Tools

What this MCP exposes

Tool	Inputs	When to call
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

Cost & Limits

What this costs to run

API quota: None
Tokens per call: High during iteration (many test runs)
Monetary: Free (Claude API usage applies)
Tip: Keep test sets small — 5 tests beats 50 that never get reviewed.

Security

Permissions, secrets, blast radius

Credential storage: None

Data egress: None from skill

Troubleshooting

Common errors and fixes

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

Alternatives

woodshed vs others

Alternative	When to use it instead	Tradeoff
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

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills