The Agent Skills Directory

[SAFE]: The skill is composed entirely of markdown documentation files and a standard JSON manifest. There are no executable scripts (.py, .js, .sh), binaries, or shell commands included.
[SAFE]: No Dynamic Context Injection (using the !command syntax) was detected in the SKILL.md or any supporting files.
[SAFE]: All external URL references point to official project documentation (e.g., astro.build, aws.amazon.com, react.dev), well-known developer resources, or the author's own GitHub repository as identified in the author context.
[SAFE]: Example strings that resemble credentials (e.g., 'sk_live_...', 'eyJ...') are used strictly within markdown code blocks as 'Wrong vs Right' examples and are clearly placeholders.
[SAFE]: No obfuscation, data exfiltration patterns, or attempts to override AI safety guidelines were found in the instructional text.

code-craft