rust-review

Rust code review guidelines for Coglet

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/rust-review/SKILL.md

Quality

Content

80%Weight 40%Scale 1-5

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

The body is a tight, well-organized review checklist that assumes Rust expertise and avoids padding. Its main weakness is the absence of a sequenced review workflow with validation checkpoints and of concrete before/after code examples.

Suggestions

Add a short ordered review workflow (e.g. run clippy/cargo-deny first, then sweep each category) with a checkpoint to confirm linters passed before manual review.

Include one or two before/after Rust snippets illustrating the most common findings (e.g. bare ? vs. .context(), blocking call in async vs. spawn_blocking) to make guidance copy-paste concrete.

Add a brief "when reviewing" trigger note at the top tying the checklist to crates/coglet and crates/coglet-python reviews.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's Rust competence, referencing thiserror/anyhow, tokio, PyO3, and insta without explaining them, with every line carrying a concrete review check — matching the score-5 anchor.	5 / 5
Actionability	Guidance is concrete and specific (e.g. "use spawn_blocking", "use .context() not bare ?", "Any unsafe block needs a safety comment") and actionable as a checklist, but there are no code examples showing the bad vs. good pattern, leaving minor gaps versus the score-5 anchor.	4 / 5
Workflow Clarity	The content is organized by review category with a useful "skip these" pre-filter, but it is a topic checklist rather than a sequenced review process, with no checkpoints or feedback loops, matching the score-3 anchor.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and is organized into clear, well-labeled sections (linters, error handling, ownership, async, safety, architecture, dependencies), qualifying for the score-5 simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

48%Weight 40%Scale 1-5

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

The description identifies a specific niche (Rust review for the Coglet project) but is thin on concrete capabilities and lacks any explicit "Use when" trigger guidance. It is distinct but under-specified.

Suggestions

List concrete review actions in the description, e.g. "Reviews Rust error handling, ownership/lifetimes, async tokio usage, unsafe blocks, and FFI boundaries in Coglet."

Add an explicit "Use when" clause, e.g. "Use when reviewing Rust code in crates/coglet or crates/coglet-python."

Include natural trigger variations like "Rust code review", "Coglet PR review", or "crates/ review" to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description "Rust code review guidelines for Coglet" names the domain (Rust code review for Coglet) but the only action stated is generic "guidelines", with no concrete capabilities listed, matching the score-2 anchor.	2 / 5
Completeness	It states a clear "what" (Rust code review guidelines for Coglet) but has no "Use when..." trigger clause, so per the missing-trigger cap it cannot exceed 3.	3 / 5
Trigger Term Quality	"Rust code review" is a natural phrase a user might say, but the description lacks common variations, synonyms, or file/extension cues, fitting the score-3 anchor of some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to "Coglet" and Rust gives it a clear niche with low conflict risk, though "code review" still overlaps slightly with general review skills, matching the mostly-distinct score-4 anchor.	4 / 5
	Total	12 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: replicate/cog
Path: .opencode/skills/rust-review/SKILL.md
Commit: ec8082f

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.