← 返回 Skills 市场
Tokio Async Code Review
作者
Kevin Anderson
· GitHub ↗
· v1.0.2
· MIT-0
268
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install tokio-async-code-review
功能描述
Reviews tokio async runtime usage for task management, sync primitives, channel patterns, and runtime configuration. Covers Rust 2024 edition changes includi...
安全使用建议
This skill appears to be a focused, instruction-only Tokio async code reviewer and will read project files (Cargo.toml and source). Before installing or running it, ask the publisher what "beagle-rust:review-verification-protocol" refers to and where it is loaded from — the SKILL.md requires it for gate #4 but doesn't include or document it. If you cannot verify that protocol is a local, trusted artifact, avoid granting the skill access to private repositories or run it first in a sandboxed environment. Also confirm the skill will not transmit repository contents to any external service before invoking it automatically.
功能分析
Type: OpenClaw Skill
Name: tokio-async-code-review
Version: 1.0.2
The tokio-async-code-review skill bundle is a legitimate tool designed to assist in reviewing Rust code for proper Tokio runtime usage. It contains detailed technical documentation and checklists in SKILL.md and the references/ directory, focusing on identifying common async pitfalls like blocking the runtime, deadlock risks, and cancellation safety. No indicators of malicious intent, data exfiltration, or unauthorized execution were found.
能力标签
能力评估
Purpose & Capability
Name, description, and content focus exclusively on reviewing Tokio/Rust async patterns (Cargo.toml, runtime setup, blocking calls, channels, sync primitives, task management). No unrelated binaries, credentials, or install steps are requested — the declared purpose aligns with requested capabilities.
Instruction Scope
Runtime instructions are detailed and confined to repository artifacts (Cargo.toml, source paths). However Gate #4 requires loading "beagle-rust:review-verification-protocol" before reporting findings; the SKILL.md does not explain what that is or where it comes from (local file, workspace crate, remote endpoint). This ambiguous external dependency could cause the agent to fetch or require files beyond the reviewed codebase and should be clarified.
Install Mechanism
No install spec and no code files to execute — instruction-only skill. This is the lowest-risk install profile; nothing is written to disk by an installer step.
Credentials
The skill declares no required environment variables, credentials, or config paths. Its intended operations (reading project files) are consistent with that minimal privilege model.
Persistence & Privilege
Flags are default (always:false, disable-model-invocation:false). The skill does not request persistent/system-wide privileges or modify other skills. Autonomous invocation is allowed by default (platform normal), which increases blast radius but is not itself a misconfiguration here.
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 tokio-async-code-review - 安装完成后，直接呼叫该 Skill 的名称或使用
/tokio-async-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
v1.0.2
**Summary:** Adds objective "Gates" that must be completed before issuing findings and clarifies reporting order.
- Introduced a "Gates" section: requires concrete dependency, runtime, and blocking inventory notes before asserting Critical or Major findings.
- Outlines the stepwise, evidence-based review process and reporting format.
- Tightened instructions: findings must be backed by protocol and gate evidence.
- Checklist, severity, and valid patterns are unchanged.
- Updated the "Before Submitting Findings" section to require running verification after completing the gates.
v1.0.1
- Added Rust 2024 support: checklist now covers native async fn in traits, RPIT lifetime capture, LazyLock, and if-let temporary scoping.
- Expanded reference materials: new pinning, cancellation, and Future internals quick reference section ([references/pinning-cancellation.md]).
- Updated guidance for migration from async-trait, once_cell/lazy_static, and for using self-cleaning lint suppressions with #[expect].
- Enhanced checklist for Rust 2024 edition migration and modern concurrency patterns.
- References and documentation updated for completeness and current Rust/tokio best practices.
v1.0.0
Initial release of tokio-async-code-review.
- Provides a structured checklist for reviewing Rust code using the Tokio async runtime.
- Covers task management, async synchronization primitives, channel patterns, and runtime configuration.
- Defines output format and severity calibration for code review findings.
- Includes quick reference links to detailed documentation for task management, sync primitives, and channels.
- Lists valid patterns to avoid false positives.
- Ensures review findings follow the beagle-rust:review-verification-protocol.
v0.1.0
Initial release of tokio-async-code-review skill.
- Provides detailed review workflow and checklists for Rust projects using Tokio async runtime.
- Helps identify misuse of task management, sync primitives, channel patterns, and runtime configuration.
- Offers clearly defined issue severity levels: Critical, Major, Minor, and Informational.
- Includes valid pattern exceptions to prevent false-positive findings.
- Specifies required output format for actionable, standardized code review reports.
元数据
常见问题
Tokio Async Code Review 是什么？
Reviews tokio async runtime usage for task management, sync primitives, channel patterns, and runtime configuration. Covers Rust 2024 edition changes includi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 268 次。
如何安装 Tokio Async Code Review？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tokio-async-code-review」即可一键安装，无需额外配置。
Tokio Async Code Review 是免费的吗？
是的，Tokio Async Code Review 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Tokio Async Code Review 支持哪些平台？
Tokio Async 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 Tokio Async Code Review？
由 Kevin Anderson（@anderskev）开发并维护，当前版本 v1.0.2。
推荐 Skills