The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to use the npx skills command-line tool for searching, checking, and updating skills. It specifically suggests using the -y flag with npx skills add to automate installations by skipping manual confirmation prompts.
[EXTERNAL_DOWNLOADS]: The skill is designed to facilitate the downloading of external packages from GitHub. It mitigates associated risks by instructing the agent to prioritize well-known organizations like Anthropic, Microsoft, and Vercel, and to treat sources with low popularity with skepticism.
[REMOTE_CODE_EXECUTION]: By using the add command, the skill installs third-party code modules intended to extend the agent's runtime capabilities. This represents a controlled remote code execution vector common to package management tools.
[PROMPT_INJECTION]: The skill's search and discovery workflow creates an indirect prompt injection surface where the agent processes external search results from the open ecosystem.
Ingestion points: Output from the npx skills find command processed in SKILL.md.
Boundary markers: None present; search results are interpolated directly into the agent's context.
Capability inventory: The skill can execute shell commands (npx skills) and perform global installations (-g) as seen in SKILL.md.
Sanitization: The skill implements a verification step requiring the agent to check stars, install counts, and author reputation before presenting or installing options.

find-skills