rust-engineer

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: cli, code-quality, debugging, developer-tools, system-design.

What it does

Writes, reviews, and debugs idiomatic Rust code with memory safety and zero-cost abstractions. Implements ownership patterns, manages lifetimes, designs trait hierarchies, builds async applications with tokio, and structures error handling with Result/Option. Use when building Rust applications, solving ownership or borrowing issues, designing trait-based APIs, implementing async/await concurrency, creating FFI bindings, or optimizing for performance and memory safety. Invoke for Rust, Cargo, ownership, borrowing, lifetimes, async Rust, tokio, zero-cost abstractions, memory safety, systems programming.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill rust-engineer

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/rust-engineer ~/.claude/skills/rust-engineer

Safety box score

Grade B, low risk: 21 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only Rust engineering skill: it ships guidance and examples, not executable scripts. Its main blast radius comes from telling the agent to run Cargo-based validation commands and install optional Rust tooling, plus generating code that can make network requests.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It recommends running standard project commands like `cargo clippy --all-targets --all-features`, `cargo fmt --check`, `cargo test`, `cargo bench`, and `cargo fuzz run`, which execute repository code but are scoped to Rust workflows.
Network access	1 (low)	The async reference includes external HTTP calls such as `reqwest::get(url).await?` and `fetch_data("https://example.com")`, so code produced from it may talk to remote hosts, but there is no automatic remote fetch/exfil path in the skill itself.
Filesystem reach	1 (low)	The testing guide shows temp-file and temp-directory operations like `std::fs::File::create`, `std::env::temp_dir().join("test")`, and `std::fs::remove_dir_all(&self.temp_dir).ok()`, but nothing targets home dotfiles or system paths.
Secrets & credentials	0 (none)	There is no mention of tokens, keys, passwords, `.env` files, browser sessions, or other secret material.
Privilege & persistence	2 (moderate)	The testing docs explicitly say `cargo install cargo-tarpaulin`, `cargo install cargo-llvm-cov`, and `cargo install cargo-fuzz`, which install tools into the user's Cargo bin and broaden the machine beyond the project.
Instruction hijack surface	0 (none)	No prompt-injection patterns, hidden instructions, or requests to ignore higher-priority rules appear in the skill files.
Irreversible actions	0 (none)	The skill does not push, deploy, publish, message, pay, book, or delete anything on its own.
Transparency	0 (none)	All shipped files are plain Markdown; there are no binaries, obfuscated blobs, or decoded-at-runtime code.

Before installing

Read `references/testing.md` first: it asks for `cargo install` of extra tools.
Run the validation commands in a scratch Rust repo before using them on important code.
If you do not want outbound traffic, avoid generating `reqwest`-based examples or run them against localhost only.

Rated 2026-10-20 by an automated review of 6 files from the skill's repository.

Source

Repository: Jeffallan/claude-skills (all skills from this repository)
Path: skills/rust-engineer/SKILL.md
Branch: main
Updated: 2026-09-19

dwarf-expert — Analyzes DWARF debug information in compiled binaries.
modern-cpp — Guides C++ code toward modern idioms (C++20/23/26). Use when writing new C++ code, modernizing legacy patterns, or working on security-critical C++.
c-review — Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities.
check-compiler-errors — Run compile and type-check commands and report failures
code-improver — Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names.
modern-python — Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.