The Agent Skills Directory

[SAFE]: The skill is a meta-instruction set that guides the agent on how to write other skills efficiently. It emphasizes token economy, procedural clarity, and progressive disclosure.
[PROMPT_INJECTION]: No malicious prompt injection patterns were detected. The instructions provided are intended to improve the quality of skill authoring and do not attempt to bypass safety filters or override system-level constraints.
[DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files or perform network requests to external domains.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns, package installations, or dynamic script generation are present.
[NO_CODE]: The skill consists entirely of natural language instructions and does not include any scripts or executable assets.

write-skills