agent-reviewer

Agent skill for reviewer - invoke with $agent-reviewer

1.15x

Quality

13%

Does it follow best practices?

Impact

81%

1.15x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Discovery

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 is critically deficient across all dimensions. It provides only an invocation command without explaining what the skill does, when to use it, or what domain it covers. The term 'reviewer' is too ambiguous to distinguish this skill from others or help Claude select it appropriately.

Suggestions

Add specific concrete actions describing what the reviewer does (e.g., 'Reviews pull requests for code quality, security issues, and style compliance').

Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks for code review, PR feedback, or wants changes reviewed').

Clarify the domain to make it distinctive (e.g., specify if this is for code review, document review, design review, etc.).

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for reviewer' is completely abstract with no indication of what the skill actually does.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command with no explanation of capabilities or use cases.	1 / 3
Trigger Term Quality	The only potential trigger term is '$agent-reviewer' which is technical jargon for invocation, not a natural keyword users would say. No domain-relevant terms like 'review', 'code review', 'feedback', etc.	1 / 3
Distinctiveness Conflict Risk	'Reviewer' is extremely vague - could mean code reviewer, document reviewer, PR reviewer, content reviewer, etc. Without specificity, this could conflict with many other skills.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill is comprehensive but severely over-engineered for its purpose. It explains well-known concepts (SQL injection, SOLID principles, N+1 queries) that Claude already understands, wasting significant token budget. The content would benefit from aggressive trimming to focus on the specific review workflow, output format, and MCP coordination patterns unique to this system.

Suggestions

Remove explanations of common security vulnerabilities, design principles, and performance anti-patterns - Claude knows these. Keep only the checklist items.

Split into SKILL.md (overview + workflow) and separate files: REVIEW_TEMPLATE.md (output format), CHECKLISTS.md (security/performance/quality checklists).

Add explicit validation steps: 'After identifying issues, verify each has: severity, location, suggested fix, and impact assessment before finalizing review.'

Condense the MCP tool integration to just the essential coordination patterns, removing the explanatory comments.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude already knows (SOLID principles, DRY, SQL injection, N+1 queries). The document is ~250 lines when the core actionable content could be condensed to ~50 lines.	1 / 3
Actionability	Provides concrete code examples showing good vs bad patterns, but many examples are illustrative rather than executable in context. The MCP tool integration section has specific commands, but the review process itself is more descriptive than prescriptive.	2 / 3
Workflow Clarity	Lists 5 review phases with checklists, but lacks explicit validation checkpoints or feedback loops. No clear 'if issues found, then X' recovery steps. The process is more of a checklist than a sequenced workflow with verification gates.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content is inline including detailed examples, checklists, and guidelines that could be split into separate reference documents (e.g., SECURITY_CHECKLIST.md, REVIEW_TEMPLATE.md).	1 / 3
	Total	6 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: b2618f9

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.