The Agent Skills Directory

[SAFE]: The skill implements a secure-by-design workflow using a 'HARD-GATE' to prevent implementation actions until a design has been presented and approved by the user. This reduces the risk of unauthorized or unreviewed code generation.
[COMMAND_EXECUTION]: The skill utilizes standard development commands for reading project files, checking git history, and committing design documents. These actions are within the expected scope of a development-oriented agent and do not include high-risk privileges or unauthorized access.
[DATA_EXFILTRATION]: No network operations or sensitive file access patterns were detected. The skill focuses on local project context and documentation storage within the project's own directory structure.
[PROMPT_INJECTION]: The skill contains no instructions aimed at bypassing AI safety guardrails or overriding system instructions. Its use of imperative language ('MUST', 'CRITICAL') is focused on enforcing its own collaborative design process.

brainstorming