The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill instructs the agent to run npm test [path]. This is a standard command for executing local test suites in Node.js environments and is essential for the stated purpose of TDD.
[PROMPT_INJECTION] (SAFE): The skill uses strong, authoritative language (e.g., "The Iron Law", "MANDATORY", "Delete it") to enforce the TDD process. This is instructional for the coding task and does not attempt to override the AI's safety protocols, extract system prompts, or simulate restricted modes.
[DATA_EXFILTRATION] (SAFE): No hardcoded credentials, sensitive file paths (like SSH keys or cloud credentials), or unauthorized network operations were found. The skill only references local project files like .planning/progress.md.
[REMOTE_CODE_EXECUTION] (SAFE): There are no patterns involving the download and execution of external scripts. The skill does not use curl or wget to fetch remote content for execution.
[OBFUSCATION] (SAFE): All content is in plain-text Markdown and code blocks. No Base64, zero-width characters, or hidden Unicode tags were detected.

tdd