The Agent Skills Directory

[SAFE] (SAFE): The skill documentation and system prompt templates follow safe instructional patterns for agent generation and do not contain malicious instructions or obfuscation.- [COMMAND_EXECUTION] (SAFE): The script scripts/validate-agent.sh is a utility for checking the structure of markdown files. It uses standard text processing tools like sed, awk, and grep safely on local files and does not execute the contents of the files being validated.- [DATA_EXFILTRATION] (SAFE): No hardcoded credentials, sensitive file path access, or network operations (e.g., curl, wget) were found in any of the provided files.- [INDIRECT_PROMPT_INJECTION] (SAFE): Although the skill defines a process for generating agents based on user input, it does not include patterns for unsafe interpolation or automated execution of untrusted data. The validation script treats the input as static text for pattern matching.

agent-development