backend-senior

Senior Developer Agent. 기술 리더십, 아키텍처 의사결정, 코드 리뷰 리드, 멘토링을 담당합니다.

Quality

19%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/backend-senior/SKILL.md

Quality

Content

22%

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

This skill content reads as a role description rather than actionable guidance. It lists responsibilities and principles at a high level but provides no concrete instructions, templates, examples, or workflows that would help Claude actually perform senior developer tasks like writing ADRs, conducting code reviews, or mentoring.

Suggestions

Add a concrete ADR template with example showing the expected format and decision-making process

Include a code review checklist or workflow with specific steps (e.g., 1. Check architecture alignment, 2. Review error handling, 3. Validate test coverage)

Provide example scenarios with expected outputs for mentoring interactions or complex problem-solving

Remove or relocate the 'trigger keywords' section as it doesn't provide actionable guidance

Dimension	Reasoning	Score
Conciseness	The content is brief and doesn't over-explain concepts Claude knows, but the 'trigger keywords' section adds little value and could be removed. The principles are appropriately terse.	2 / 3
Actionability	The skill describes responsibilities abstractly ('기술 의사결정', '코드 리뷰 리드') without any concrete guidance, examples, templates, or executable instructions on how to actually perform these tasks.	1 / 3
Workflow Clarity	No workflows are defined. For tasks like ADR writing, code review, or mentoring, there are no steps, sequences, or validation checkpoints provided.	1 / 3
Progressive Disclosure	The content is organized into clear sections, but there are no references to detailed materials (e.g., ADR templates, code review checklists, mentoring guides) that would be expected for a senior developer role.	2 / 3
	Total	6 / 12 Passed

Description

17%

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 reads more like a job title and role summary than a skill description. It lacks explicit trigger guidance ('Use when...'), uses abstract role terminology instead of concrete actions, and the Korean language limits keyword matching. The description would benefit from specific, actionable capabilities and clear usage triggers.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios like 'when user asks for architecture advice, system design review, or senior-level code feedback'

Replace abstract role terms with concrete actions: instead of '아키텍처 의사결정' use 'designs system architectures, evaluates technology choices, creates technical specifications'

Include natural English trigger terms users would say: 'architecture review', 'design patterns', 'code review', 'technical decision', 'system design'

Dimension	Reasoning	Score
Specificity	Names the domain (technical leadership, architecture) and lists some actions (code review lead, mentoring), but these are high-level role descriptions rather than concrete, actionable capabilities like 'reviews pull requests' or 'designs system architectures'.	2 / 3
Completeness	Describes 'what' at a high level (role responsibilities) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. The 'when' is entirely missing.	1 / 3
Trigger Term Quality	Uses Korean text which limits discoverability, and the terms are abstract role descriptions ('기술 리더십', '아키텍처 의사결정') rather than natural keywords users would say when needing help. Missing common trigger terms like 'architecture review', 'code review', 'design decision'.	1 / 3
Distinctiveness Conflict Risk	The 'Senior Developer Agent' title and architecture/mentoring focus provides some distinction, but 'code review' and general development guidance could easily overlap with other coding or review skills.	2 / 3
	Total	6 / 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: 4 months 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.