agent-reviewer
Agent skill for reviewer - invoke with $agent-reviewer
41
13%
Does it follow best practices?
Impact
81%
1.15xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-reviewer/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no information about what the skill does, when it should be used, or what domain it operates in. The word 'reviewer' is the only hint at functionality but is far too vague to enable proper skill selection.
Suggestions
Describe concrete actions the skill performs (e.g., 'Reviews pull requests for code quality, checks for bugs, suggests improvements, and validates adherence to coding standards').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks for a code review, PR feedback, or wants to check code quality').
Specify the domain clearly to distinguish from other review-related skills (e.g., code review vs. document review vs. design review).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for reviewer' is extremely vague—it doesn't describe what the skill actually does (e.g., code review, document review, PR review). | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities. | 1 / 3 |
Trigger Term Quality | The only potentially relevant keyword is 'reviewer,' which is overly generic. There are no natural terms a user would say when needing this skill. The invocation syntax '$agent-reviewer' is technical jargon, not a user trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | 'Reviewer' is extremely generic and could conflict with any skill related to code review, document review, PR review, peer review, etc. There is nothing to distinguish this skill from others. | 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 a verbose, textbook-style code review guide that explains many concepts Claude already knows (SOLID, DRY, SQL injection, N+1 queries, dependency injection). At 250+ lines, it would benefit enormously from trimming to just the novel information: the specific review feedback format, the MCP tool integration patterns, and the prioritization scheme. The content reads more like a junior developer training document than a concise skill for an AI agent.
Suggestions
Remove all explanations of well-known patterns (SOLID, DRY, SQL injection, N+1 queries, dependency injection) — Claude already knows these. Focus only on the specific review process, output format, and MCP coordination.
Extract the review feedback format template and MCP tool integration into separate referenced files, keeping SKILL.md as a concise overview of the review workflow.
Add explicit validation checkpoints and decision criteria: when to approve, when to request changes, and how to handle disagreements or edge cases in the review process.
Make MCP tool examples use actual valid syntax rather than pseudo-JavaScript object notation — clarify whether these are function calls, JSON payloads, or something else.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ lines. Explains basic concepts Claude already knows (SOLID principles, DRY, SQL injection, N+1 queries, dependency injection). The security checklist, performance patterns, and code quality examples are all standard knowledge that don't need to be taught. Most of the content is a generic code review tutorial rather than skill-specific instructions. | 1 / 3 |
Actionability | Provides concrete code examples for common issues and fixes, and includes a review feedback format template. However, much of it is illustrative rather than executable — the MCP tool integration examples use pseudo-JavaScript that isn't directly executable, and the skill reads more like a textbook than actionable instructions for performing a specific review task. | 2 / 3 |
Workflow Clarity | The review process is broken into numbered sections (Functionality, Security, Performance, Code Quality, Maintainability) which provides some sequence, but there are no explicit validation checkpoints, no feedback loops for when issues are found during review, and no clear decision points about when to approve vs. request changes. The process is more of a checklist of areas to examine than a sequenced workflow. | 2 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files. Everything is inlined — the security checklist, performance patterns, code quality examples, review format template, and MCP integration could all be separate reference files. No bundle files are provided, and no attempt is made to organize content across files despite the length warranting it. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%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/ruflo
- Commit
619b263
- Reviewed
Table of Contents
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.