The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a bundled bash script, scripts/next-intent-index.sh, to manage the naming of design notes files. This script performs routine local operations, such as directory creation and scanning for existing numeric prefixes in the docs/intent/ directory, to ensure sequential file indexing.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided design plans. This represents a standard input surface for AI agents. The skill mitigates risks by applying a strict 'Questioning lens' and structured 'Rules of engagement' (e.g., limiting the agent to one question at a time and requiring codebase checks before asking questions), which focus the agent on technical plan analysis.
[SAFE]: No obfuscation, hardcoded credentials, or network exfiltration patterns were identified. The skill's operations are confined to the local project workspace and its stated purpose as a documentation and design review assistant.

grill-me