The Agent Skills Directory

Development Command Execution: The skill facilitates standard software engineering workflows, such as managing git repositories, configuring virtual environments, and executing automated test suites. These commands are essential for its primary purpose of rolling library versions and are used in a manner consistent with typical development environments.
Indirect Prompt Injection Surface: The skill involves a process where external markdown documentation is parsed to automatically generate Python code. This functionality introduces an attack surface where instructions embedded in the documentation could influence the generated code. However, this is a core architectural feature of the library's maintenance, and the source of truth is the official upstream repository from a trusted vendor.
Ingestion points: The skill reads documentation from docs/src/api/*.md in the upstream repository (SKILL.md).
Boundary markers: No explicit boundary markers are defined in the instructions for the parsing process.
Capability inventory: The skill utilizes commands such as python -m build, pytest, mypy, and pre-commit to process the generated output (SKILL.md).
Sanitization: The skill relies on the internal logic of the generate_api.js script to interpret the documentation structure.
Privilege Escalation Awareness: The instructions demonstrate a proactive security posture by explicitly advising against the use of sudo and providing non-privileged alternatives for environment setup. This ensures that the skill operates within the safety constraints of the execution environment.
Trusted Source Integration: The skill interacts exclusively with well-known technology infrastructure, such as official GitHub repositories and established package registries (npm). These interactions are documented neutrally as part of the library's standard update cycle.

playwright-roll