CtrlK
BlogDocsLog inGet started
Tessl Logo

vmcp-review

Reviews vMCP code changes for known anti-patterns that make the codebase harder to understand or more brittle. Use when reviewing PRs, planning features, or refactoring vMCP code.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The body is concise, actionable, and clearly sequenced with explicit validation signals (severity classification, clean-review reporting). Progressive disclosure is the weakest point because the core anti-pattern catalog is deferred entirely to an external rule file rather than being structured as a navigable reference.

Suggestions

Add a clearly signaled one-level-deep reference (e.g., a '## Anti-patterns' section pointing to a references/ file) so the deferred catalog is discoverable rather than relying solely on auto-loaded rules.

Consider listing the anti-pattern categories inline or in a references/vmcp-anti-patterns.md file with a pointer, so reviewers can see what will be checked before reading the rule file.

Clarify how to locate the anti-pattern file when it is not auto-loaded (e.g., the exact path) to make the workflow robust when the rule file is absent.

DimensionReasoningScore

Conciseness

Lean body with no padding or explanation of concepts Claude already knows; each section (Purpose, Instructions, scope rules, severity classification, report template, exclusions) earns its place and assumes competence.

3 / 3

Actionability

Provides concrete, copy-paste-ready guidance: explicit scope rules ('changed files under pkg/vmcp/ and cmd/vmcp/'), three severity classifications with clear definitions, and a complete markdown report template with path:line placeholders.

3 / 3

Workflow Clarity

Multi-step process is clearly sequenced (1. Determine Scope -> 2. Anti-Pattern Detection -> 3. Present Findings) with severity-based decision checkpoints and an explicit instruction to report a clean review when no issues are found.

3 / 3

Progressive Disclosure

Content is well-organized into sections, but the single external reference ('.claude/rules/vmcp-anti-patterns.md') is referenced inline rather than via a clearly signaled one-level-deep pointer; no bundle files exist and the anti-pattern detail is entirely deferred to an auto-loaded rule file rather than structured in references.

2 / 3

Total

11

/

12

Passed

Description

100%

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 concise, specific, and follows the recommended 'what it does + Use when...' pattern with a clearly scoped vMCP niche. It assumes third person voice and avoids fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Reviews vMCP code changes for known anti-patterns', 'reviewing PRs, planning features, or refactoring') describing specific review activities rather than vague behavior.

3 / 3

Completeness

Clearly answers both what ('Reviews vMCP code changes for known anti-patterns that make the codebase harder to understand or more brittle') and when via an explicit 'Use when reviewing PRs, planning features, or refactoring vMCP code.' clause.

3 / 3

Trigger Term Quality

Includes natural user-facing terms ('reviewing PRs', 'planning features', 'refactoring vMCP code') that users would plausibly say when needing the skill.

3 / 3

Distinctiveness Conflict Risk

Scoped specifically to vMCP code, with a clear niche ('known anti-patterns') and distinct triggers; unlikely to conflict with general code-review skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
stacklok/toolhive
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.