The Agent Skills Directory

[SAFE]: The skill is entirely educational and instructional. It focuses on marketing frameworks (System 1/System 2) and cognitive biases (Anchoring, Decoy Effect, etc.).
[PROMPT_INJECTION]: No malicious patterns or attempts to override system safety guidelines were detected. The instructions follow standard conversational patterns.
[REMOTE_CODE_EXECUTION]: The skill does not contain any commands to download or execute external scripts or packages. The mcp-server reference in the metadata points to the author's own infrastructure and is a standard configuration field.
[CREDENTIALS_UNSAFE]: No sensitive information, API keys, or hardcoded secrets are present in the skill files.
[OBFUSCATION]: The content is clear markdown with no hidden characters, Base64 encoding, or homoglyph attacks.

cognitive-biases