The Agent Skills Directory

Command Execution: The skill utilizes local CLI tools and scripts, including apm, grep, node, and the GitHub CLI (gh), to verify documentation claims and manage pull request comments. These actions are scoped to the project environment and the repository's lifecycle.\n- Dynamic Execution: The python-architect agent is designed to execute python -c commands to verify claims made in the documentation. This represents a dynamic execution pattern where command logic is derived from documentation impact analysis.\n- Indirect Prompt Injection Surface: The skill ingests untrusted data from pull request titles, descriptions, and code diffs (Ingestion Points). While explicit boundary markers and sanitization are not detailed (Boundary Markers/Sanitization), the skill employs a multi-agent synthesis loop and requires manual human confirmation before implementing structural changes or opening companion pull requests (Capability Inventory: gh, apm, grep, python -c, node) to manage the associated risks.

docs-sync