The Agent Skills Directory

[SAFE]: The skill functions as a static knowledge base providing guidance on performance-focused code reviews. It contains no instructions that attempt to bypass safety filters or override agent behavior.
[NO_CODE]: The skill is composed entirely of markdown documentation and reference code snippets. It does not include scripts, binaries, or automated configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill describes how to review external data such as pull request diffs, creating a theoretical attack surface for indirect prompt injection. However, since the skill provides no executable tools or capabilities, the severity is minimal.
Ingestion points: Pull request diffs, database queries, and source code files as described in the usage section.
Boundary markers: None provided in the reference material.
Capability inventory: No subprocess calls, network operations, or file-write capabilities are defined or requested.
Sanitization: Not applicable as the skill does not process input through automated tools.

performance-anti-patterns