code-mate-gemini

Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent.

Quality

91%

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

Quality

Content

100%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 exemplary for a simple skill: lean, fully executable, with a clear sequence and explicit failure handling plus permission guardrails. It assumes Claude's competence and adds only what is non-obvious.

Dimension	Reasoning	Score
Conciseness	The body is lean: it sets a timeout, checks availability with `command -v gemini`, runs one command, and defines failure handling, without explaining what Gemini or a CLI is, matching anchor 5's 'every token earns its place'.	5 / 5
Actionability	Provides a copy-paste-ready executable command (`gemini -p "<prompt>" --output-format json`), a concrete availability check, and a worked example, matching anchor 5's fully-executable guidance.	5 / 5
Workflow Clarity	A clear numbered sequence with explicit validation ('Parse the JSON result and treat a JSON error or nonzero exit as failure') and stop-and-ask checkpoints for auth/permission problems, matching anchor 5 for a simple skill.	5 / 5
Progressive Disclosure	A simple, under-50-line skill with no external references needed and two well-organized sections (Run, Authentication And Permissions), which per the simple-skill note earns anchor 5; no bundle files exist to verify.	5 / 5
	Total	20 / 20 Passed

Description

82%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 strong: it states what the skill does and gives explicit, natural use-when triggers tied to a distinct, named tool. The only soft spot is specificity, where 'coding tasks' is broad rather than enumerating concrete actions.

Suggestions

Replace the generic 'coding tasks' with one or two concrete capabilities (e.g., 'refactors modules', 'generates patches') to lift specificity toward anchor 4-5.

Add a synonym or natural phrasing variant (e.g., 'run Gemini in the background' or 'compare Gemini vs. Claude output') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Gemini CLI headlessly') and a couple of actions ('repository analysis and coding tasks'), but 'coding tasks' is broad and the action set is not comprehensive, matching anchor 3 rather than the several-specific-actions of anchor 4.	3 / 5
Completeness	Explicitly answers both what ('Runs Gemini CLI headlessly for repository analysis and coding tasks') and when ('Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('delegate work to Gemini CLI', 'compare its result with another coding agent'), giving good keyword coverage, though it lacks synonyms or extension variations that would reach anchor 5.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific named tool (Gemini CLI) with distinct triggers, giving it a clear niche and minimal conflict risk with other skills, matching anchor 5.	5 / 5
	Total	17 / 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: CherryHQ/cherry-studio
Path: resources/code-cli-skills/code-mate-gemini/SKILL.md
Commit: 113ef7e

Reviewed: 3 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.