The Agent Skills Directory

[SAFE]: The skill instructions and documentation follow professional engineering best practices. No malicious code, obfuscation, or deceptive metadata patterns were found in the analyzed files.- [EXTERNAL_DOWNLOADS]: The skill references implementation examples and architectural patterns from a public GitHub repository (github.com/huykn/distributed-cache). This is a neutral reference to a well-known service for educational purposes and does not involve automated execution or installation of untrusted scripts.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data during pull request reviews and performance profiling. 1. Ingestion points: Reads local files, repository history (via git), and external web content (via WebFetch). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided. 3. Capability inventory: The agent has access to Edit, Write, and Bash tools. 4. Sanitization: No sanitization of external content is specified. However, the skill's inherent 'Gate' process, which requires verifiable targets and profiling proof, acts as a mitigation against the uncritical acceptance of malicious or unvetted suggestions.

engineering-perf-optimization-process