rust-review

Review Rust code changes in fallow for correctness, performance, cache-friendly design, and project conventions. Use when changes touch Rust crates such as config, types, extract, graph, core, cli, lsp, or mcp.

Quality

86%

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

Quality

Content

86%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.

A tight, well-organized review skill that delegates methodology to rule files while specifying a concrete report format and verdict labels. Could strengthen actionability by inlining a few high-value review checks or a feedback loop for borderline cases.

Suggestions

Inline one or two concrete review checks (e.g., a cache-friendly-design quick check) so the skill is actionable even before the external rule files are read.

Add a brief feedback loop for borderline findings, such as 're-check against the crate rule file before assigning CONCERN vs BLOCK', to strengthen workflow clarity.

Clarify when each crate-specific rule file applies (e.g., map crate name to file) so navigation is unambiguous when multiple crates are touched.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: a short read-list, a one-line review directive, and a four-item report template — every token earns its place and it assumes Claude's competence without explaining what code review is. Matches the 5 anchor; not lower because there is no padding or over-explanation.	5 / 5
Actionability	Provides concrete, executable guidance: specific files to read and a precise report format (file and line, what is wrong, the concrete fix, APPROVE/CONCERN/BLOCK verdict). Not a 5 because the actual issue-detection methodology is delegated to external rule files rather than given inline, leaving a minor gap; not a 3 because the report template and verdict labels are fully concrete.	4 / 5
Workflow Clarity	Clear three-step sequence (read rules -> review high-confidence issues -> report with verdict) with the verdict label acting as an output checkpoint. Not a 5 because there is no explicit feedback/validation loop, and not a 3 because the sequence is explicit and the skill is read-only review so the destructive-operation cap does not apply.	4 / 5
Progressive Disclosure	The body is a clear overview that points to detailed rule files via well-signaled, one-level-deep references organized under 'Read' and 'Also read' sections, with easy navigation. Matches the 5 anchor for a simple, well-organized skill; no bundle files are present so structure alone suffices.	5 / 5
	Total	18 / 20 Passed

Description

87%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.

A strong, third-person description that clearly states both what the skill does and when to use it, with concrete crate-name triggers bounding a distinct niche. Minor room to add natural synonyms (Rust diff, cargo, PR review) for fuller keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete review dimensions ('correctness, performance, cache-friendly design, and project conventions'), which are specific actions for a review skill, though they are review focus areas rather than discrete transformative actions. Not a 5 because the actions are review categories rather than a comprehensive set of concrete operations, and not a 3 because multiple specific dimensions are named.	4 / 5
Completeness	Explicitly answers both what ('Review Rust code changes ... for correctness, performance, cache-friendly design, and project conventions') and when ('Use when changes touch Rust crates such as ...') with concrete trigger phrases. Matches the 5 anchor directly; not lower because both what and when are present and concrete.	5 / 5
Trigger Term Quality	Includes natural terms ('Rust code changes', 'Rust crates') plus a concrete list of crate names (config, types, extract, graph, core, cli, lsp, mcp) that users would name. Not a 5 because common synonyms like 'Rust diff', 'cargo', or 'PR review' are missing, and not a 3 because keyword coverage is clearly good with explicit crate triggers.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Rust review in the 'fallow' project) with distinct triggers tied to specific named crates, giving minimal conflict risk with unrelated skills. Matches the 5 anchor; not lower because the scope is narrowly and specifically bounded.	5 / 5
	Total	18 / 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: fallow-rs/fallow
Path: .agents/skills/rust-review/SKILL.md
Commit: 74177e5

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.