一键导入
这个仓库中的 skills
Write, review, or refactor Rust so it is idiomatic, safe, and maintainable. Use this skill whenever the task involves Rust code — implementing a feature in a `.rs` file, reviewing a Rust PR or module, refactoring a crate, designing a public API, fixing clippy or borrow-checker complaints, deciding how to structure error handling, or splitting an oversized function or file. Trigger even when the user does not say "best practices" explicitly: any request to "write this in Rust", "clean up this Rust code", "is this idiomatic", "add a Cargo crate", "handle these errors properly", or "make this compile without unwrap" should pull in this skill. Covers ownership and borrowing, error handling (Result / `?` / thiserror / anyhow), API design, module and crate layout, size limits, unsafe, dependencies, testing, and the verification steps (fmt, clippy, test) that must pass before the work is called done.
Get objective, unbiased analysis of your codebase, project, or documentation. Use when you need fresh eyes on a problem, want to challenge existing assumptions, need multiple perspectives on architecture or approach, or feel stuck in the current implementation. This skill deliberately avoids "existing code bias" by using debiasing techniques, multiple viewpoints, and structured synthesis. Perfect for: evaluating if your current approach is still optimal, exploring alternatives, identifying hidden assumptions, getting objective feedback before major refactors, or when AI tools keep echoing back your existing patterns. Trigger when user mentions: "is this still the best approach", "evaluate my architecture", "challenge my assumptions", "look at this objectively", "what am I missing", "are there better alternatives", "help me think outside the box", or similar requests for unbiased analysis. Also use when user wants multiple perspectives on a decision, needs to validate ideas against different mental models, or
Forge's universal task router. Evaluates any task against ALL available Forge resources — skills, subagents, external MCP tools, web access, the Lattice code graph — decomposes it, and routes each part through the best resource(s) in the right order. The default entry point for complex, ambiguous, or multi-step work.