The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language prompts and YAML configuration metadata. There are no scripts (Python/Node.js), binaries, or shell commands present in the provided files.
[PROMPT_INJECTION]: The instructions contain directives for the model to handle user requests for 'original text' or 'source code' by outputting the prompt verbatim. While these resemble override instructions, they are functional requirements for the skill's specific purpose as a template provider and do not attempt to bypass safety filters or access system-level instructions.
[COMMAND_EXECUTION]: The YAML frontmatter explicitly sets disable-model-invocation: true, which restricts the agent's ability to trigger external tools, further reducing the risk of malicious tool usage.

life-design