← 返回 Skills 市场
Rust Code Review
作者
Kevin Anderson
· GitHub ↗
· v1.0.3
· MIT-0
237
总下载
0
收藏
2
当前安装
4
版本数
在 OpenClaw 中安装
/install rust-code-review
功能描述
Reviews Rust code for ownership, borrowing, lifetime, error handling, trait design, unsafe usage, and common mistakes. Use when reviewing .rs files, checking...
安全使用建议
This is an instruction-only Rust review checklist that will have the agent read your repository files (Cargo.toml and .rs sources) to produce findings. Before installing, consider: (1) Are you comfortable granting the agent access to the codebase being reviewed? (2) The skill references other helper skills (beagle-rust:...), so behavior may vary if those helper skills are present — review their SKILL.md if you use them. There are no network endpoints, external downloads, or credential requests embedded in this skill. If you want to limit scope, invoke the skill only on specific files or review the SKILL.md and reference documents yourself before allowing autonomous runs.
功能分析
Type: OpenClaw Skill
Name: rust-code-review
Version: 1.0.3
The 'rust-code-review' skill bundle is a comprehensive and well-structured toolset designed to guide an AI agent through professional Rust code audits. It includes a detailed workflow in SKILL.md and extensive reference materials (e.g., unsafe-deep.md, async-concurrency.md, error-handling.md) that promote security best practices, such as documenting safety invariants and avoiding panics in production. There is no evidence of malicious intent, data exfiltration, or prompt injection; the instructions are strictly aligned with the stated purpose of improving code quality and soundness.
能力评估
Purpose & Capability
Name/description (Rust code review) matches the files included and runtime instructions: it reads Cargo.toml, inspects .rs files, and uses internal reference docs. No unrelated binaries, env vars, or external services are requested.
Instruction Scope
SKILL.md instructs the agent to open Cargo.toml, scan changed/full functions, and follow a sequenced gate/verification protocol. Those file reads are necessary and proportional for a code-review skill. The instructions reference other helper skills (beagle-rust:...) but do not direct data to unknown external endpoints or request unrelated system state.
Install Mechanism
No install spec and no code files (instruction-only), so nothing is written to disk or downloaded during install — lowest-risk install model.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md only asks the agent to read repo files (Cargo.toml, .rs sources) which is consistent with the stated purpose.
Persistence & Privilege
always:false and default invocation settings mean it will not be force-included. The skill does not request to modify other skills or agent-wide configs, nor does it ask for long-lived credentials.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install rust-code-review - 安装完成后，直接呼叫该 Skill 的名称或使用
/rust-code-review触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.3
Version 1.0.3
- Added a "Gates" section with step-by-step verification stages to strengthen review rigor.
- Clarified that reviewers must explicitly pass each gate before proceeding, not relying on mental shortcuts.
- Updated the review workflow to require completion of all Gates—including loading the verification protocol—before reporting findings.
- Emphasized objective pass criteria and explicit crate context determination for edition/MSRV-sensitive analysis.
- No changes to checklists or technical coverage; procedural improvements only.
v1.0.2
- Added new references: concurrency primitives, lifetime variance, type layout, and advanced unsafe code for deeper code review coverage.
- Updated guidance for Rust 2024 edition, including changes to unsafe code semantics, lifetime capture in RPIT, temporary scoping, and trait diagnostics.
- Expanded checklist items addressing new edition-specific patterns and pitfalls.
- Enhanced quick reference table for easier navigation to specialized review topics.
- Clarified error handling, trait best practices, and type/state pattern usage based on latest Rust idioms.
v1.0.1
- Expanded checklist for ownership and borrowing, emphasizing iterator usage and `.clone()` pitfalls.
- Added references to beagle-rust:rust-best-practices for performance, pointer types, type state, and clippy config guidance.
- Updated Quick Reference and Checklist to clarify when to use each reference and best-practices skill.
- Introduced dedicated Clippy Configuration and Type State Pattern sections, including workspace lints setup and type state best practices.
- Improved checklist detail and clarity around iterator chains, lifetime handling, and common performance traps.
v1.0.0
- Initial release of rust-code-review skill.
- Provides a structured checklist for reviewing Rust code with focus on modern idioms (Rust 2021).
- Covers ownership, borrowing, lifetimes, error handling, trait design, unsafe code, naming/style, performance, and linting.
- Includes severity calibration for faster triage and best practice recommendations.
- Offers quick reference to supporting documentation for ownership, error handling, async/concurrency, and common mistakes.
- Specifies valid patterns that should not be flagged during reviews to reduce false positives.
元数据
常见问题
Rust Code Review 是什么？
Reviews Rust code for ownership, borrowing, lifetime, error handling, trait design, unsafe usage, and common mistakes. Use when reviewing .rs files, checking... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 237 次。
如何安装 Rust Code Review？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install rust-code-review」即可一键安装，无需额外配置。
Rust Code Review 是免费的吗？
是的，Rust Code Review 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Rust Code Review 支持哪些平台？
Rust Code Review 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Rust Code Review？
由 Kevin Anderson（@anderskev）开发并维护，当前版本 v1.0.3。
推荐 Skills