Name: google-gemini
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

google-gemini

Google Gemini integration. Manage Users, Conversations. Use when the user wants to interact with Google Gemini data.

Quality

65%

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/google-gemini/SKILL.md

Quality

Content

67%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 body is action-dense with executable Membrane CLI commands and a clear connection workflow including state-based polling, but it opens with unnecessary conceptual padding and references an undefined "Step 2". Splitting reference tables into bundle files and trimming the intro would push it higher.

Suggestions

Delete or compress the opening "Google Gemini is a multimodal AI model..." paragraph, which restates knowledge Claude already has.

Label the post-connection section as "Step 2" (or remove the dangling "skip to Step 2" references) so the workflow's steps are unambiguous.

Move the proxy-flag options table and popular-actions catalog into a references/ file and link to it from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The opening "Google Gemini is a multimodal AI model developed by Google..." explains a concept Claude already knows, and a few sections could be tightened, but the bulk is concrete commands, matching the mostly-efficient score-3 anchor rather than the lean score-4 anchor.	3 / 5
Actionability	Copy-paste-ready commands cover the common cases (install, login, connection ensure, action list/run, request) with the popular-actions table giving concrete keys, but a few examples rely on placeholders and lack a full end-to-end worked example, keeping it at score 4.	4 / 5
Workflow Clarity	The install→authenticate→connect→poll sequence is clear and the connection-state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) provides an explicit feedback loop, but the body references a "Step 2" that is not actually labeled, a minor validation gap that caps it at 4 rather than 5.	4 / 5
Progressive Disclosure	With no bundle files present, the single SKILL.md is well-organized into clear sections with no nested references, though the proxy-flag and popular-actions tables could arguably live in a separate reference file, matching the good-structure score-4 anchor.	4 / 5
	Total	15 / 20 Passed

Description

62%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 cleanly states both what the skill does and when to use it, anchored to a specific named product, but its action list is thin and its trigger terms lack synonyms and concrete variations. Tightening the actions and trigger phrases would lift the weaker dimensions.

Suggestions

Replace the generic "Manage Users, Conversations" with several specific concrete actions (e.g., list models, generate content, embed text, count tokens) to raise specificity.

Expand the "Use when..." clause with natural trigger phrases and synonyms users actually say, such as "Gemini chats, conversations, generating content, embeddings, or model listings".

Add file-extension or entity keywords (e.g., Gemini models, prompts) to improve trigger term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	"Manage Users, Conversations" names the Google Gemini domain plus one or two concrete actions, but the actions are minimal and not comprehensive, matching the score-3 anchor rather than the multi-action score-4 anchor.	3 / 5
Completeness	It states both what ("Google Gemini integration. Manage Users, Conversations") and an explicit when ("Use when the user wants to interact with Google Gemini data"), but the when clause is generic rather than concrete trigger phrases, so it sits at score 4 and not 5.	4 / 5
Trigger Term Quality	Terms like "Google Gemini", "Users", "Conversations", and "interact with Google Gemini data" are relevant but the description misses common variations and synonyms a user would naturally say, fitting the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	"Google Gemini integration" targets a named product niche with distinct triggers and only minor overlap risk against other AI-model skills, which matches the score-4 anchor better than the fully-distinct score-5 anchor.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/google-gemini/SKILL.md
Commit: f484c82

Reviewed: 5 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.