frb-pr-review

Review a flutter_rust_bridge PR before treating it as ready, including subagent checks for correctness and test weakening.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 compact, well-structured review workflow with concrete subagent instructions and an explicit readiness gate. It is efficient and actionable with strong sequencing and validation.

Suggestions

Remove the empty '# 1 Human SoT' header, which adds noise without content.

Inline the concrete execution commands for frb-test (and tom-style-tests principles) so the guidance is copy-paste ready rather than referencing other skills by name.

Add a short 'Use this before treating a non-trivial flutter_rust_bridge PR as ready, especially after CI-driven fixes or generated drift' trigger line at the top of the body to mirror the description and aid discovery.

Dimension	Reasoning	Score
Conciseness	Mostly lean bulleted instructions that assume competence; the stray empty '# 1 Human SoT' header and a few phrasings could be trimmed, keeping it just below the lean 5-anchor.	4 / 5
Actionability	Gives concrete subagent prompts with required finding fields (paths, line numbers, impact, fix); minor gaps remain since referenced skills (frb-test, tom-style-tests) are named without their exact commands.	4 / 5
Workflow Clarity	Clear numbered sequence in the Review Gate, an explicit Stop Condition validation gate, and a feedback loop ('fix the underlying failure'), matching the explicit-validation 5-anchor; no destructive/batch cap applies.	5 / 5
Progressive Disclosure	Under-50-line single file with well-organized sections (2.1 Review Gate, 2.2 Stop Condition) and no need for bundle files, satisfying the simple-skill exception for a 5.	5 / 5
	Total	18 / 20 Passed

Description

78%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 specific, well-targeted description that clearly states both capability and trigger conditions for a narrow niche. It is concise and uses third-person imperative voice with no over-claims.

Dimension	Reasoning	Score
Specificity	Names the domain (flutter_rust_bridge PR review) and several concrete actions — subagent checks for correctness and for test weakening — with only minor gaps in coverage, fitting the 4-anchor better than the 1-2-action 3-anchor.	4 / 5
Completeness	Answers both what (review PR via subagent checks) and when ('before treating it as ready', an explicit trigger clause so not capped at 3); the when could be more specific, matching the 4-anchor.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('PR', 'review', 'flutter_rust_bridge', 'correctness', 'test weakening') but lacks synonyms or file extensions needed for the comprehensive 5-anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow, named niche (flutter_rust_bridge PR readiness) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: fzyzcjy/flutter_rust_bridge
Path: .claude/skills/frb-pr-review/SKILL.md
Commit: 0876e2e

Reviewed: 4 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.