rust-review

Rust code review guidelines for Coglet

Quality

75%

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

100%

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

The content is a dense, well-organized review checklist that assumes Claude's knowledge and delivers highly actionable, specific guidance across error handling, ownership, async, safety, and architecture. It exemplifies token-efficient, instruction-only skill design with no padding or unnecessary indirection.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining concepts like Rust, async, or PyO3; every line is actionable review guidance with no padding.	3 / 3
Actionability	Concrete, specific rules throughout (e.g. "use .context() or .with_context() from anyhow, not bare ?", "use spawn_blocking", "Any unsafe block needs a safety comment") give copy-ready review criteria; absence of code is fine for an instruction-only review skill.	3 / 3
Workflow Clarity	As a single-purpose review checklist with no multi-step or destructive process, its single action is unambiguous and the category-organized sections keep the sequence clear, satisfying the simple-skill allowance.	3 / 3
Progressive Disclosure	The under-50-line body is self-contained with well-organized sections and no need for external references, meeting the simple-skill threshold for top progressive-disclosure scoring.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 concisely identifies a clear, scoped niche (Rust review for Coglet) but lacks any explicit "Use when" trigger and enumerates no concrete actions, leaving all dimensions at the mid-level. Adding a trigger clause and one or two specific review actions would lift it to the top anchor.

Suggestions

Add a 'Use when...' clause naming explicit triggers, e.g. 'Use when reviewing Rust code in Coglet, the prediction server crate, or when the user asks to review crates/ changes.'

List one or two concrete actions in the description, e.g. 'Flags error-handling, ownership, async, and unsafe-block issues that clippy and cargo-deny miss.'

Include common trigger variations like 'reviewing Rust PRs', 'checking Coglet crates', or 'cargo review' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Rust code review guidelines for Coglet" names a concrete domain and project scope but lists no specific review actions, placing it above pure vagueness yet short of the multi-action anchor.	2 / 3
Completeness	It states what the skill does ("Rust code review guidelines") but provides no explicit "Use when" trigger, so per the rubric missing-trigger guidance completeness is capped at 2.	2 / 3
Trigger Term Quality	"Rust" and "code review" are natural terms a user might say, but coverage is thin with no common variations or "Use when" phrasing, matching the some-relevant-keywords anchor.	2 / 3
Distinctiveness Conflict Risk	Scoping to the Coglet project reduces conflict, but "Rust code review" could still overlap with generic Rust-review skills and there are no explicit distinct triggers.	2 / 3
	Total	8 / 12 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: 4e62b8b

Reviewed: 6 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.