Local SkillsSAFE
Portable local skills for MCP clients, with on-demand loading, validation, and trigger evaluation.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Enable any LLM or AI agent to utilize expert skills from your local filesystem via MCP
[![npm version][npm-version-badge]][npm-package] [![npm downloads][npm-downloads-badge]][npm-package] [![npm types][npm-types-badge]][npm-package] [![License: MIT][license-badge]][license] [![Node][node-badge]][nodejs] [![MCP][mcp-badge]][mcp-protocol]
[![CI][ci-badge]][ci-workflow] [![codecov][codecov-badge]][codecov] [![CodeQL][codeql-badge]][codeql-workflow]
[![GitHub Stars][stars-badge]][stargazers] [![GitHub Forks][forks-badge]][network] [![GitHub Issues][issues-badge]][repo-issues] [![GitHub Last Commit][commit-badge]][commits] [![PRs Welcome][prs-badge]][contributing]
Quick Start • Features • Usage • FAQ • Contributing
📑 Table of Contents
- What is Local Skills MCP?
- ✨ Features
- 🚀 Quick Start
- 📝 SKILL.md Format
- 🎯 Usage
- ❓ FAQ
- 🤝 Contributing
What is Local Skills MCP?
A universal Model Context Protocol (MCP) server that enables any LLM or AI agent to access expert skills from your local filesystem. Write skills once, use them across Claude Code, Claude Desktop, Cline, Continue.dev, custom agents, or any MCP-compatible client.
Transform AI capabilities with structured, expert-level instructions for specialized tasks. Context-efficient lazy loading—only skill names/descriptions load initially (~50 tokens/skill), full content on-demand.
🆚 Why Use Local Skills MCP?
3bf05ae66431OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add local-skills-mcp --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"local-skills-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
}
}
}
}Exposed tools (13)
13 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
code-reviewer | read | Reviews code for best practices |
complex-skill | read | A skill with complex content |
evaluate_skill | read | Runs Anthropic skill-creator eval loop for a skill (requires Python, Claude CLI auth, and an eval set JSON; legacy layouts may also require ANTHROPIC_API_KEY + anthropic package). |
mapped-skill | read | Skill in map |
minimal-skill | read | minimal description |
name | read | required-description |
required-name | read | description |
skill1 | read | First skill |
skill2 | read | Second skill |
special-path-skill | read | Skill with special path characters |
test | read | test description |
test-skill | read | A test skill |
validate_skill | read | Validates a SKILL.md file against name/description/frontmatter rules and returns errors + warnings. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (7)
.gitmodules
.prettierignore
.releaserc.json
skill_name: "../../../etc/passwd", // Path traversal attempt
expect(() => requireSkillName("../../etc")).toThrow("Invalid skill_name");arguments: { skill_name: "../../../../tmp" },@modelcontextprotocol/sdk, yaml, @commitlint/cli, @commitlint/config-conventional, @eslint/js, @semantic-release/changelog, @semantic-release/commit-analyzer, @semantic-release/exec
Gates applied: no_behavioural_pass.
3bf05ae66431full audit observations/trust-audit/mcp-server/kdpa-llc__local-skills.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 3bf05ae66431 | SAFE | B | 89 | first audit |
Questions
What is the Local Skills MCP server?
Portable local skills for MCP clients, with on-demand loading, validation, and trigger evaluation.
What tools does Local Skills expose?
13 in total: 13 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Local Skills safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Local Skills need?
It reads ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Local Skills run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as local-skills-mcp at 1.0.7.
How current is this page?
The grade is for one exact copy of the source (3bf05ae66431), read on 2026-10-08. The repository is watched and re-audited when it changes.