The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill automates the execution of remote code by configuring MCP servers to run via npx, bunx, uvx, and go run using configurations defined in REFERENCE.md.\n
It references third-party GitHub repositories for execution, such as https://github.com/BeehiveInnovations/pal-mcp-server.git.\n
It installs and executes unversioned or @latest packages from registries (e.g., argocd-mcp, cclsp, @upstash/context7-mcp).\n
The --fix argument allows the agent to perform these installations automatically without requiring user confirmation for each server.\n- [EXTERNAL_DOWNLOADS]: The skill triggers downloads of executable content and configurations from external sources.\n
Fetches packages from NPM, PyPI, and Go registries.\n
Clones or runs code directly from GitHub repositories (e.g., github.com/github/github-mcp-server).\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to perform project discovery and environment setup.\n
Uses find, jq, and grep to inspect local files and configuration.\n
Recommends the execution of global package installation commands (e.g., npm i -g typescript-language-server, pip install python-lsp-server) which may require elevated privileges.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of untrusted project data.\n
Ingestion points: Reads and parses .mcp.json, .project-standards.yaml, and various source files (*.ts, *.py, etc.) via find and jq to determine project context.\n
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when parsing these files.\n
Capability inventory: The skill possesses Bash, Write, and Edit capabilities, enabling it to execute commands and modify the filesystem based on project configuration.\n
Sanitization: No sanitization or validation logic is defined for the content extracted from the project files before it is used in the configuration workflow.

configure-mcp