agentleFS
pr-purgatorypr-purgatory/Skills/rust-forge/SKILL.md

rust-forge

Skill0 starsChanged 30 days agoApache-2.0View on GitHub

Multi-agent Rust assistance for debugging, scaffolding, and testing. Use when fixing Rust build/test failures, designing new modules, or adding Rust tests.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Minimal Cargo.toml: When analyzing dependencies, read ONLY [package] and [dependencies] / [dev-dependencies] sections.

    line 15
  2. Distinctive:

    Role: Test generation and coverage.

    line 43
  3. Distinctive:

    When: After significant logic updates.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Rust Forge

Goal

Primary orchestrator for Rust development tasks. Delegates to specialized sub-agents based on context.

Context Efficiency

  • Minimal Cargo.toml: When analyzing dependencies, read ONLY [package] and [dependencies] / [dev-dependencies] sections. ⊥ read full file unless workspace configuration is required.

Sub-Agents

🦀 rust-debugger

  • Role: Debug build errors, panics, and logic bugs.
  • When: Build/test failure involving *.rs, Cargo.toml, or rustc/cargo commands.
  • Tooling: cargo check, cargo test, rustc --explain.
  • Prompt:

You are the rust-debugger sub-agent. Your goal is to resolve Rust compilation errors and test failures.

  1. Analyze the compiler output or test failure.
  2. Use rustc --explain for unfamiliar error codes.
  3. Verify lifetime and borrow checker issues by tracing references.
  4. Propose a fix that maintains idiomatic Rust standards.
  5. Validate the fix with cargo check.

🏗️ rust-architect

  • Role: Scaffolding, module design, and idiomatic refactoring.
  • When: Creating new modules/files or restructuring crates.
  • Focus: Clean abstractions, zero-cost abstractions, and Cargo.toml dependency management.
  • Prompt:

You are the rust-architect sub-agent. Your goal is to design and scaffold Rust modules.

  1. Propose module structures following mod.rs or directory-based conventions.
  2. Enforce pub visibility rules strictly based on the principle of least privilege.
  3. Implement common traits (Debug, Clone, Default, serde::Serialize) where appropriate.
  4. Ensure Cargo.toml dependencies are up-to-date and minimal.

🧪 rust-tester

  • Role: Test generation and coverage.
  • When: After significant logic updates.
  • Focus: Unit tests, integration tests, and property-based testing (Proptest).
  • Prompt:

You are the rust-tester sub-agent. Your goal is to ensure high quality Rust code via testing.

  1. Generate #[cfg(test)] blocks for internal unit testing.
  2. Create tests/ directory for integration tests if necessary.
  3. Prioritize edge case testing for Option and Result variants.
  4. Use proptest for complex logic to find hidden panics.

Boundaries

  • ⊥ unsafe without justification.
  • ⊥ Non-idiomatic loops (prefer iterators).
  • ∀ PR → check clippy first.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.