CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-reviewer

Agent skill for reviewer - invoke with $agent-reviewer

37

1.15x
Quality

7%

Does it follow best practices?

Impact

81%

1.15x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Content

14%

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 document that explains well-known software engineering concepts Claude already understands, rather than providing lean, actionable instructions for performing code reviews. It lacks a clear sequential workflow, has no validation checkpoints, and dumps all content into a single monolithic file. The MCP tool integration section adds some value but uses non-executable pseudo-code.

Suggestions

Remove all explanations of concepts Claude already knows (SOLID, DRY, SQL injection patterns, N+1 queries, dependency injection) and replace with a concise checklist of what to check during review.

Add a clear sequential workflow: 1) Receive review target, 2) Run automated checks, 3) Perform manual review by category, 4) Validate findings, 5) Format and report results — with explicit validation steps.

Extract the review feedback template and MCP integration examples into separate reference files, keeping SKILL.md as a lean overview with pointers.

Make the MCP tool calls executable with correct syntax rather than pseudo-JavaScript, and clarify the exact entry point — what does the agent do first when invoked?

DimensionReasoningScore

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 checks, and code quality examples are all textbook knowledge that wastes token budget. The review guidelines section ('Be Constructive', 'Focus on the code, not the person') is generic advice Claude doesn't need.

1 / 3

Actionability

Provides concrete code examples for common issues (SQL injection, N+1 queries, naming), and a review feedback template is useful. 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 doesn't give clear instructions on what to actually do when invoked (e.g., which files to review, how to start).

2 / 3

Workflow Clarity

There is no clear sequential workflow for performing a review. The numbered sections (1-5) are categories of review, not steps in a process. There are no validation checkpoints, no feedback loops for when issues are found, and no clear entry/exit criteria. The 'Automated Checks' section lists commands but doesn't integrate them into a workflow with verification steps.

1 / 3

Progressive Disclosure

Monolithic wall of text with no references to external files and no content splitting. Everything — from basic examples to MCP integration to review templates — is crammed into a single file. The extensive code examples for well-known patterns (SQL injection, DRY, SOLID) should either be omitted or placed in a reference file.

1 / 3

Total

5

/

12

Passed

Description

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 is an extremely weak description that fails on all dimensions. It provides no information about what the skill does, when it should be used, or what domain it operates in. It reads more like a label or invocation hint than a functional description.

Suggestions

Describe the specific 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 review, or wants feedback on code changes').

Specify the domain clearly to distinguish from other review-related skills (e.g., code review vs. document review vs. design review).

DimensionReasoningScore

Specificity

The description provides no concrete actions whatsoever. 'Agent skill for reviewer' is extremely vague—it doesn't describe what the skill actually does (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 generic. There are no natural terms a user would say when needing this skill. The invocation command '$agent-reviewer' is not a natural trigger term.

1 / 3

Distinctiveness Conflict Risk

'Reviewer' is extremely generic and could conflict with any skill related to reviewing code, documents, PRs, designs, or anything else. There is nothing to distinguish this skill's niche.

1 / 3

Total

4

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.