BeautifulRust
morganlinton/BeautifulRustReviewed by AI
What it does
Beautiful Rust is three Agent Skills plus a clippy configuration. Installed into a coding agent such as Claude Code, Codex, Copilot, Cursor or Gemini CLI, they steer it toward idiomatic Rust when it writes code, make it produce a prioritized review of existing Rust where each finding cites the rule it breaks, and guide it when porting C, C++, Python, Go or JavaScript to Rust. The rules are distilled from five published Rust guides, and the lint file enforces the machine-checkable ones in CI. It is for Rust developers who already use a coding agent and have cargo and clippy installed.
How easy it is to install
C · install 1 or 2 tools · Windows
Installing is one command such as npx skills add morganlinton/BeautifulRust or claude plugin install, but you need a coding agent set up first and a Rust toolchain with cargo and clippy for the review and the lint file to do anything.
Numbers on GitHub
- Stars
- 1,619on Oct 31, 2026
- Downloads
- —all releases
- Growth
- +309stars in 4 days
Stars over time
Facts
- Runs on
- Windows, macOS, Linux, Web
- You need to install
- Rust, Other tools
- Disk space
- not determined
- Accounts or keys
- Coding agent account (Claude Code, Codex, GitHub Copilot, Cursor or Gemini CLI)
- Cost
- Free, API costs extra · The skills and the lint config are MIT; the work is done by a coding agent you pay for, and the README notes that running the eval cases means "real model runs" that "are billed".
- License
- MIT (Permissive)
- Last update
- Oct 30, 2026
Risk signals (3)
- Infobenchmark single run self graded
README, cross-agent benchmark: "it was one run per configuration, graded by a Claude model", and "They hurt in one case: Claude did worse on the Bevy feature task with them."
AI review
- Infosources summarized under mixed licenses
README attribution table: the five digests bundled in the skill paraphrase sources with different terms, including Effective Rust under "CC BY-NC-ND 4.0 (online edition)" and Rust Design Patterns under MPL-2.0, while the repository itself is MIT.
AI review
- Infoskill runs commands on your code
README: the rust-review skill "runs `cargo fmt`, `clippy`, and the tests when a toolchain is available", and the port skill "verifies with `cargo test` and `clippy`", so the agent runs build commands in your project.
AI review
Evidence is shown in its original language.
What Radar could not check
- Whether the Rust it produces for your own project is better, since the published comparison is one run per configuration.
- How well it works in agents other than Claude Code and Codex, the two the benchmark covers.
- How many tokens the roughly 500-line writing skill and its reference digests add to each session.
- Whether the clippy table fits an existing codebase without a long list of allows.