The Agent Skills Directory

[SAFE]: The skill functions as a documentation and style guide (AXI
Agent eXperience Interface). It provides recommendations for output formatting (TOON), schema design, and agent platform integrations. It does not contain any executable code, scripts, or commands that trigger automatically.
[EXTERNAL_DOWNLOADS]: The skill references external URLs such as toonformat.dev (for a token-efficient data format specification) and agentskills.io (an informational site for agent skills). These are included as technical references for developers following the AXI standard and do not involve silent downloads or automated execution.
[PERSISTENCE]: The documentation describes how developers can integrate their own tools into agent session lifecycles by using hooks in files like ~/.claude/settings.json or ~/.codex/hooks.json. These are documented as architectural patterns for external tools and are not persistence mechanisms executed by this skill itself.
[COMMAND_EXECUTION]: The skill includes example commands using npx (e.g., npx skills add) and placeholder CLI commands (e.g., tasks list). These are provided strictly as instructional examples within the documentation and are not executed by the agent upon loading the skill.

axi