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.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- archieSkill
- deep-research-firecrawlSkill
- lfmSkill
- redteamSkill
- revert-forgeSkill
- sandbox-forgeSkill
- selinaSkill
- ui-forgeSkill
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
- Very specific: line 15
Minimal Cargo.toml: When analyzing dependencies, read ONLY [package] and [dependencies] / [dev-dependencies] sections.
- Distinctive: line 43
Role: Test generation and coverage.
- Distinctive: line 44
When: After significant logic updates.
≈ “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.
Files
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, orrustc/cargocommands. - Tooling:
cargo check,cargo test,rustc --explain. - Prompt:
You are the
rust-debuggersub-agent. Your goal is to resolve Rust compilation errors and test failures.
- Analyze the compiler output or test failure.
- Use
rustc --explainfor unfamiliar error codes.- Verify lifetime and borrow checker issues by tracing references.
- Propose a fix that maintains idiomatic Rust standards.
- 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.tomldependency management. - Prompt:
You are the
rust-architectsub-agent. Your goal is to design and scaffold Rust modules.
- Propose module structures following
mod.rsor directory-based conventions.- Enforce
pubvisibility rules strictly based on the principle of least privilege.- Implement common traits (
Debug,Clone,Default,serde::Serialize) where appropriate.- Ensure
Cargo.tomldependencies 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-testersub-agent. Your goal is to ensure high quality Rust code via testing.
- Generate
#[cfg(test)]blocks for internal unit testing.- Create
tests/directory for integration tests if necessary.- Prioritize edge case testing for
OptionandResultvariants.- Use
proptestfor complex logic to find hidden panics.
Boundaries
- ⊥
unsafewithout justification. - ⊥ Non-idiomatic loops (prefer iterators).
- ∀ PR → check clippy first.
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
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.

