The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscated content were detected in the skill instructions or reference files. The skill is entirely instructional and does not perform any dangerous actions.
[NO_CODE]: The skill consists entirely of markdown files and does not include any executable scripts, binaries, or automated configuration changes.
[DATA_EXFILTRATION]: While the skill references external resources like Wikipedia and a GitHub repository, these are provided as static documentation links for the user and are not used for automated data transfer or exfiltration.
[INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided text drafts. While this presents an inherent attack surface, the risk is negligible due to the skill's restricted scope of text manipulation and absence of network or shell access.

concise-writing