skrills
Verified Safeby athola
Overview
Provides a Machine-checked Proof (MCP) server and CLI for efficient discovery, filtering, and injection of local SKILL.md files into AI agent prompts.
Installation
skrills serveEnvironment Variables
- HOME
- SKRILLS_PROMPT
- SKRILLS_EXTRA_DIRS
- SKRILLS_INCLUDE_CLAUDE
- SKRILLS_DIAG
- SKRILLS_AUTO_PIN
- SKRILLS_AUTOLOAD_MAX_BYTES
- SKRILLS_RENDER_MODE_LOG
- SKRILLS_MANIFEST
- SKRILLS_CACHE_TTL_MS
- SKRILLS_TRACE_WIRE
- SKRILLS_EMBED_THRESHOLD
- SKRILLS_EXPOSE_AGENTS
- SKRILLS_MANIFEST_FIRST
- SKRILLS_MANIFEST_MINIMAL
- SKRILLS_ACCEPT_GZIP
- SKRILLS_MANIFEST_ALLOWLIST
Security Notes
The server primarily communicates over standard I/O (stdio), minimizing network attack surface. It employs a `SIGCHLD` handler on Unix to prevent zombie processes, reflecting careful child process management. File system access is confined to expected directories (~/.codex, ~/.claude, user-specified skill paths) and explicit actions like `skrills sync`. No `eval` or obvious hardcoded secrets were found. Warnings are provided in documentation about reviewing third-party skills before integration.
Similar Servers
skillz
Acts as an MCP server to expose Claude-style skills and their resources as callable tools for AI agents.
rust-docs-mcp
Provides AI agents with deep, cached access to Rust crate documentation, source code, and project structure for enhanced development.
org-mcp-server
A Model Context Protocol (MCP) server for org-mode knowledge management, providing search, content access, and note linking capabilities for AI agents.
mcp-framework
A Rust framework implementing the Model Context Protocol for building production-ready MCP servers, clients, and intelligent AI agents that integrate with LLMs for tool use and browser automation.