gemini-mcp

Manage MCP (Model Context Protocol) servers with Gemini CLI for extended tool capabilities, custom integrations, and enterprise workflows. Use when integrating external tools, databases, or APIs with Gemini.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/gemini-mcp/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 highly actionable with broad concrete examples for managing and building MCP servers, but it is a long, padded monolith that explains known concepts and lacks the progressive file-splitting and validation checkpoints the rubric expects for destructive/batch workflows.

Suggestions

Trim the redundant `gemini --yolo -p` numbered-prompt blocks (Database/API/Enterprise automation repeat the same pattern) to one representative example each, and remove the "What is MCP?" concept primer.

Add explicit validation checkpoints to destructive/batch YOLO workflows (e.g., a dry-run/preview step, then a verify-after step with retry-on-error) so each multi-step automation has a validate→fix→retry loop.

Split full server implementations (Python/Node/Docker, audit-logging code, load-balancing and performance configs) into separate reference files linked from a concise overview, and convert the JSON config blocks to valid JSON by moving comments out.

Dimension	Reasoning	Score
Conciseness	The 776-line body is noticeably verbose: a "What is MCP?" section explains a concept Claude already knows, and the many near-identical `gemini --yolo -p` numbered-prompt blocks across the YOLO/automation sections are padded and repetitive.	2 / 5
Actionability	It provides abundant concrete, copy-paste-ready CLI commands, JSON config, and Python/Node/Docker server code covering common cases, but JSON blocks contain `//` comments (invalid JSON) and some code has minor gaps (missing `import os`, undefined `start()`), holding it below 5.	4 / 5
Workflow Clarity	Sequences are present, but destructive/batch YOLO workflows (database deletes, financial transactions, migrations) lack explicit validate→fix→retry checkpoints; per the rubric cap, a destructive/batch skill without validation cannot score above 3.	3 / 5
Progressive Disclosure	Section headers give reasonable in-file structure, but there are no bundle files or reference links and full server implementations, the Dockerfile, and audit-logging code are inlined rather than split into separate reference files.	3 / 5
	Total	12 / 20 Passed

Description

83%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.

A clear, well-structured description that explicitly covers both what the skill does and when to use it, with natural trigger terms. It is held back from the top tier only by some benefit-framed buzzwords in the capabilities list and minor overlap with related Gemini skills.

Dimension	Reasoning	Score
Specificity	"Manage MCP (Model Context Protocol) servers" names the domain and primary action, and "extended tool capabilities, custom integrations, and enterprise workflows" lists several specific actions, but the latter read as benefit-framed buzzwords rather than concrete operations, keeping it below 5.	4 / 5
Completeness	It explicitly states both the what ("Manage MCP servers ... for extended tool capabilities, custom integrations, and enterprise workflows") and the when ("Use when integrating external tools, databases, or APIs with Gemini") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"Use when integrating external tools, databases, or APIs with Gemini" supplies natural keywords a user would say; coverage is good but missing common synonyms/variants like "connect", "plugins", or "extensions".	4 / 5
Distinctiveness Conflict Risk	The MCP-server-management niche with Gemini CLI is distinct, but the "Related Skills" list (gemini-cli, gemini-tools) signals minor overlap risk with closely related sibling skills, so it sits just below 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (781 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/gemini-mcp/SKILL.md
Commit: 93ed392

Reviewed: 2 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.