The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard command-line tools to perform code analysis and context gathering. Specifically, it executes git commands for diffing and history, golangci-lint for Go code, cargo clippy and cargo audit for Rust, and gitleaks for detecting sensitive information. In the verification stage, it uses grep, rg, and ast-grep to confirm findings.
[EXTERNAL_DOWNLOADS]: The skill references several well-known and trusted external development tools. It utilizes npx eslint, which may download the eslint package from the official npm registry if not present. It also provides installation instructions for other reputable tools such as golangci-lint and ast-grep from their official GitHub repositories.
[PROMPT_INJECTION]: As an automated code review tool, the skill is subject to indirect prompt injection from malicious content within the source code it analyzes. This risk is mitigated by the structured multi-pass review architecture and a verification stage that uses structural analysis (ast-grep) to confirm findings before they are presented to the user.

deepreview