The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions and quote references. There are no executable scripts (.py, .js, .sh), binaries, or configuration files that could trigger unauthorized actions.
[SAFE]: All external URLs in SKILL.md and README.md point to the author's (simbajigege) official GitHub repository. These links are used solely for citation and grounded knowledge referencing, which is a standard and safe practice for knowledge-distillation skills.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided queries about creative blocks and procrastination. While this creates a surface for indirect prompt injection, the skill lacks any dangerous capabilities (such as file system writes, network exfiltration, or command execution) that could be exploited by such an injection. The risk is negligible.
Ingestion points: User input queries describing creative avoidance or discipline issues (processed in SKILL.md).
Boundary markers: None explicitly defined in the instructions.
Capability inventory: None. The skill contains no code, shell commands, or network operations.
Sanitization: Not applicable as no dangerous actions are performed.
[SAFE]: The installation instruction npx skills add simbajigege/book2skills/... is a standard method for adding skills to agent platforms and points directly to the vendor's own resource, representing legitimate installation behavior.

war-of-art-pressfield