CtrlK
BlogDocsLog inGet started
Tessl Logo

rust

Mental-model reset for Rust. Use when writing or reviewing Rust code to shift from "it compiles" to "thinks in Rust." Triggers on Rust code review, "is this idiomatic", borrow-checker errors, API design, domain modeling, ownership, lifetimes, errors, traits, async/Tokio, unsafe, serde, FFI, tests, performance, Cargo structure, .rs files, Cargo.toml, rustc diagnostics, clippy findings, Result/Option, thiserror vs anyhow, newtype, typestate, enum vs trait, dyn Trait, Send/Sync, Pin, Miri, PyO3, napi-rs, cxx, UniFFI, wasm-bindgen, serde attributes, or feature unification.

87

1.05x
Quality

82%

Does it follow best practices?

Impact

99%

1.05x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-structured pattern catalog that excels at workflow clarity via the review checklist and leans on a rich references bundle, but it repeats itself across four sections and, critically, many of its cross-reference links point to non-existent files, which undermines navigation.

Suggestions

Consolidate the redundant 'Common Mistakes', 'Review Checklist', and 'Quick Reference' sections into one to cut tokens — they restate the same defaults three times.

Fix the broken cross-reference links: ownership.md, error-handling.md, traits.md, async.md, atomics.md, unsafe.md, serde.md, interop.md, project-structure.md (and similar) do not exist in references/; point them at the actual files (e.g. ownership-before-refcell.md, thiserror-patterns.md/anyhow-patterns.md, trait-patterns.md, blocking-and-bridging.md).

Add a few short executable code snippets for the highest-value defaults (newtype constructor, bool→enum, borrow-by-default signature) so the body is actionable without requiring every reference to be opened.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude knows Rust syntax, but it is sizable and partly redundant — the 'How Rust Thinks', 'Common Mistakes', 'Review Checklist', and 'Quick Reference' tables repeat the same defaults in four forms, which adds tokens beyond what a single well-organized pass would need.

2 / 3

Actionability

Guidance is concrete at the pattern level (e.g. 'Borrow by default — accept &str, &[T], &Path', 'Never block the runtime... use spawn_blocking'), but it offers almost no executable code snippets; it instructs by naming moves and code smells rather than copy-paste-ready examples, leaving implementation detail to the references.

2 / 3

Workflow Clarity

The Review Checklist gives a clearly sequenced, numbered review process with explicit decision branches ('Borrow checker appeased with clone(), 'static, Rc<RefCell<_>>, or unsafe? → Rework ownership first'), functioning as a validation/checkpoint workflow for code review.

3 / 3

Progressive Disclosure

The references/ directory exists with 59 well-organized one-level-deep files, and the references/-prefixed links resolve to real files; however roughly half the in-body links (ownership.md, error-handling.md, traits.md, async.md, atomics.md, unsafe.md, serde.md, interop.md, project-structure.md, etc.) point to files that do not exist, so navigation is partly broken.

2 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both what the skill does and when to use it, with a rich set of natural Rust-flavored triggers. It is third-person and concrete throughout.

DimensionReasoningScore

Specificity

The description enumerates many concrete capabilities — code review, borrow-checker errors, API design, domain modeling, ownership, lifetimes, errors, traits, async/Tokio, unsafe, serde, FFI, tests — naming specific actions rather than vague language.

3 / 3

Completeness

It answers both what ("Mental-model reset for Rust... shift from 'it compiles' to 'thinks in Rust'") and when via the explicit "Use when..." / "Triggers on..." clause listing specific triggering situations.

3 / 3

Trigger Term Quality

It covers a dense spread of natural terms users would actually say ("is this idiomatic", borrow-checker errors, thiserror vs anyhow, newtype, typestate, Send/Sync, Pin, Miri, PyO3, napi-rs, cxx, UniFFI, wasm-bindgen, clippy findings), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The trigger set is tightly scoped to Rust-specific artifacts and tooling (.rs files, Cargo.toml, rustc diagnostics, clippy, thiserror vs anyhow, PyO3, UniFFI), making it clearly distinguishable and unlikely to fire for non-Rust skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 31 missing

Warning

Total

15

/

16

Passed

Repository
joshuadavidthomas/agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.