The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx, specifically npx skills find and npx skills add to interact with the skills ecosystem.
[REMOTE_CODE_EXECUTION]: The skill facilitates the download and execution of external code from GitHub or other repositories via the npx skills add command.
[REMOTE_CODE_EXECUTION]: Instructions encourage the use of the -y flag, which bypasses user confirmation prompts during the installation process, and the -g flag for global installation.
[EXTERNAL_DOWNLOADS]: The skill references https://skills.sh/ as a source for browsing and downloading external skills.
[EXTERNAL_DOWNLOADS]: References resources from Vercel Labs' and Anthropic's official repositories.
[PROMPT_INJECTION]: The skill processes untrusted search results and descriptions from external sources (Ingestion points). It lacks explicit boundary markers or instructions to ignore embedded commands in that data (Boundary markers). The agent has the capability to execute shell commands via npx (Capability inventory). Sanitization is limited to manual reputation checks based on metadata (Sanitization).

find-skills