The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown text guiding the agent on how to approach complex development tasks by building validation harnesses.
[NO_CODE]: No executable code blocks, shell commands, or script files are included with this skill.
[PROMPT_INJECTION]: No evidence of prompt injection, safety bypasses, or instruction overrides. The content focuses on development best practices.
[DATA_EXFILTRATION]: No network operations, sensitive file access, or hardcoded credentials were detected.
[OBFUSCATION]: No base64 encoding, zero-width characters, or homoglyph substitutions were found in the file content.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute any remote scripts or unverifiable packages.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not utilize the dynamic context injection syntax (!command) in its markdown file.

feedback-loops