Back to Home
dmgrok icon

agent_skills_directory

Verified Safe

by dmgrok

Overview

Provides a centralized, automatically-updated catalog of AI agent skills from multiple providers, consumable by MCP servers, AI agents, and developer tools.

Installation

Run Command
python scripts/aggregate.py

Environment Variables

  • GITHUB_TOKEN

Security Notes

The primary `aggregate.py` script uses `yaml.safe_load` for parsing YAML frontmatter, which is a secure practice. It retrieves the GitHub token from environment variables, preventing hardcoding. Network requests are made to GitHub APIs, which is expected. The use of `subprocess.run` to call `npx @toon-format/cli` carries a moderate theoretical risk if the `toon-format/cli` itself has vulnerabilities or if the input to it were untrusted. However, in this context, it processes locally generated content (`catalog.json`), mitigating direct input-based injection risks. No `eval` or obvious malicious patterns were detected.

Similar Servers

Stats

Interest Score0
Security Score8
Cost ClassLow
Stars0
Forks0
Last Update2026-01-17

Tags

Agent SkillsCatalogMCPAI AgentsAggregation