backend-reviewer

Backend Reviewer Agent. 코드 리뷰, PR 검토, 코드 품질 평가를 담당합니다. 리뷰, 검토, PR, 코드 품질 관련 요청 시 사용됩니다.

Quality

59%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/backend-reviewer/SKILL.md

Quality

Discovery

67%

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

This description adequately covers the basic what and when, earning full marks for completeness. However, it lacks specific concrete actions beyond general review activities and could benefit from more distinctive trigger terms that clearly separate it from other code review skills. The Korean-only approach limits discoverability for bilingual users.

Suggestions

Add specific concrete actions like 'API 설계 검토', 'DB 쿼리 최적화 확인', 'security vulnerability 분석' to improve specificity

Include English variations of trigger terms (pull request, code review, backend) to improve trigger term coverage for bilingual users

Add more distinctive backend-specific triggers like 'API', 'database', 'server-side', '백엔드' to reduce conflict risk with general code review skills

Dimension	Reasoning	Score
Specificity	Names the domain (backend code review) and lists some actions (코드 리뷰, PR 검토, 코드 품질 평가), but lacks specific concrete actions like 'check for security vulnerabilities', 'analyze code complexity', or 'suggest refactoring patterns'.	2 / 3
Completeness	Clearly answers both what ('코드 리뷰, PR 검토, 코드 품질 평가를 담당합니다') and when ('리뷰, 검토, PR, 코드 품질 관련 요청 시 사용됩니다') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes relevant Korean keywords (리뷰, 검토, PR, 코드 품질) that users might say, but missing common variations like 'pull request', 'merge request', 'code check', or English equivalents that bilingual users might use.	2 / 3
Distinctiveness Conflict Risk	The 'Backend' qualifier helps distinguish from general code review, but could still overlap with other review-related skills. Terms like '코드 리뷰' and '검토' are fairly generic and might conflict with frontend or general code review skills.	2 / 3
	Total	9 / 12 Passed

Implementation

52%

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

The skill provides a comprehensive checklist for backend code review with good token efficiency and clear formatting. However, it lacks a defined workflow for how to actually conduct a review (what order, when to stop, how to prioritize findings) and provides more of a reference document than actionable step-by-step guidance.

Suggestions

Add a workflow section that sequences the review process: e.g., '1. Run lint/type checks first, 2. Review security items, 3. Check performance patterns, 4. Evaluate code quality'

Include a concrete example of reviewing a sample code snippet, showing how to apply the checklist and generate review comments

Add validation checkpoints such as 'If any 🔴 [필수] items found, request changes before proceeding to 🟡 [권장] review'

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, using checklists and tables to convey information densely. No unnecessary explanations of concepts Claude already knows; every section serves a clear purpose.	3 / 3
Actionability	Provides concrete bash commands and comment style examples, but the checklists are more descriptive than instructive. Missing executable code examples for actual review scenarios or how to apply the checklist programmatically.	2 / 3
Workflow Clarity	No clear workflow sequence for conducting a code review. The checklist items are listed but there's no process for how to use them, no validation checkpoints, and no guidance on review order or prioritization.	1 / 3
Progressive Disclosure	Content is well-organized with clear sections and headers, but everything is in one file with no references to external documentation for deeper topics like security best practices or NestJS patterns.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: shaul1991/shaul-agents-plugin
Commit: 9242c58

Reviewed: 29 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.