skill-mcp-master

Skill MCP - Master Usage Guide

What Is the Skill MCP?

The Skill MCP server is a self-hosted agent skills registry accessible to any MCP-compatible AI agent or tool. It stores curated, expert-authored instruction sets ("skills") and delivers them on demand through a structured 3-tier disclosure model.

Each skill contains:

Tier	Content	Tools
1	Frontmatter - name, description, tags, score	skills_find_relevant
2	Instructions, system prompt addition	skills_get_body, skills_get_options
3	Reference docs, executable scripts, asset templates	skills_get_reference, skills_run_script, skills_get_asset

---

The Canonical 3-Step Workflow

Follow this sequence for every task where a skill might apply.

Step 1 - Discover (skills_find_relevant)

skills_find_relevant(query="<specific description of your task>", top_k=5)

Interpret scores:

• score > 0.6 → strong match - proceed to Step 2
• score 0.4–0.6 → possible match - read description to decide
• score < 0.4 → no relevant skill - proceed without one

Query tips:

• ✅ "write pytest unit tests for a Flask REST API endpoint"
• ✅ "extract tables from a multi-page PDF and output as CSV"
• ✅ "review Python code for security vulnerabilities"
• ❌ "testing" (too generic - poor embedding)
• ❌ "help me" (no task signal)

---

Step 2 - Load (skills_get_body)

skills_get_body(skill_id="<top result from Step 1>")

The response contains:

{
  "skill_id": "test-writer",
  "instructions": "## Testing Workflow\n1. Identify the function under test ...",
  "system_prompt_addition": "You are a senior test engineer ...",
  "tier3_manifest": {
    "references": ["TESTING-GUIDE.md", "COVERAGE-POLICY.md"],
    "scripts":    ["coverage_check.py"],
    "assets":     ["test-template.py"]
  }
}

After loading:

1. Read and apply instructions - this is the authoritative guidance
2. If system_prompt_addition is non-empty, incorporate it into your context
3. Check tier3_manifest - only proceed to Step 3 if instructions reference specific files