agent-reviewer

Agent skill for reviewer - invoke with $agent-reviewer

1.15x

Quality

39%

Does it follow best practices?

Impact

81%

1.15x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-reviewer/SKILL.md

Quality

Content

50%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.

The content is a well-structured, actionable code-review guide with concrete checklists, examples, and a feedback template, but it is padded with basic programming tutorials Claude already knows and presented as a monolithic file with no progressive disclosure or sequenced validation workflow.

Suggestions

Remove the tutorial-style ❌/✅ explanations of well-known concepts (SOLID/DRY/KISS, SQL injection, N+1, dependency injection) and keep only skill-specific review checklists and the feedback format.

Delete the stray second YAML agent-config block at the top of the body, which duplicates and conflicts with the skill frontmatter.

Establish a true sequenced review workflow with validation checkpoints (e.g. run automated checks → verify findings against requirements → confirm severity with the user → emit the feedback template).

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: it teaches concepts Claude already knows (SOLID/DRY/KISS, SQL injection, N+1 queries, dependency injection, clear naming) via numerous ❌/✅ tutorial blocks, and opens with a stray second YAML agent-config block that is pure padding.	2 / 5
Actionability	It provides concrete checklists, executable TypeScript/bash snippets, a copy-ready review-feedback markdown template, and specific MCP tool calls, with only minor gaps in how directly the example code maps to actions the agent must take.	4 / 5
Workflow Clarity	The five review areas and feedback format are listed as numbered sections, but they are parallel categories rather than a sequenced workflow, and there are no explicit validation/verification checkpoints before issuing findings.	3 / 5
Progressive Disclosure	No bundle files exist and the ~330-line skill is a monolith with clear headers but no external references; content that could live in separate files (the example library, MCP integration, agent config) is fully inlined.	3 / 5
	Total	12 / 20 Passed

Description

28%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.

The description is a minimal label-plus-invocation string: it names a domain but states no concrete capabilities and provides no 'when to use' trigger guidance. It is too vague to reliably surface the skill for the right requests.

Suggestions

Replace the label with concrete actions, e.g. 'Reviews code for quality, security, performance, and maintainability and produces structured review feedback.'

Add an explicit trigger clause such as 'Use when the user asks for a code review, security audit, or review of staged changes.'

Include natural trigger terms users actually say ('code review', 'review my code', 'security audit') rather than only the '$agent-reviewer' command token.

Dimension	Reasoning	Score
Specificity	The phrase 'Agent skill for reviewer' names the domain (reviewer) but lists zero concrete actions — it only labels the skill and gives invocation syntax, fitting the 'names the domain but actions are minimal/generic' anchor at its lower edge rather than the entirely-vague anchor 1.	2 / 5
Completeness	The 'what' is vague (it does not say what the reviewer reviews or does) and there is no 'Use when...' trigger clause — only an invocation instruction — so it matches 'has a vague what and no when' and is capped at 3 by the missing-trigger guidance.	2 / 5
Trigger Term Quality	Only the single keyword 'reviewer' and the command token '$agent-reviewer' appear; natural phrases a user would actually say ('code review', 'review my code', 'audit') are missing, matching 'one or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	'reviewer' is a somewhat specific niche and the '$agent-reviewer' command is a distinct trigger, but the bare term 'reviewer' is broad enough to overlap with other review-type skills, fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	9 / 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: ruvnet/ruflo
Path: .agents/skills/agent-reviewer/SKILL.md
Commit: fa13ee4

Reviewed: about 5 hours 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.