gemini

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

Quality

82%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

A highly actionable skill body with concrete, runnable Gemini CLI commands and a real hung-process feedback loop. Its weaknesses are conciseness (repeated warnings and marketing benchmarks) and structure (monolithic inline content with no progressive disclosure to separate files).

Suggestions

Consolidate the background/yolo-mode warning into one authoritative section and reference it elsewhere instead of restating it five times; this alone would meaningfully tighten the document.

Remove or relocate vendor benchmark figures ('76.2% SWE-bench', 'GPQA Diamond 91.9%', 'WebDev Arena 1487 Elo', '35% better', 'vibe coding') — they are marketing fluff Claude does not need for invocation.

Move the model-selection guide, quick-reference table, and troubleshooting runbook into separate reference files (e.g. references/models.md, references/troubleshooting.md) and link to them from the main workflow to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but padded: the background/yolo-mode warning is repeated across at least five sections, and marketing benchmarks ('35% better at software engineering', '76.2% SWE-bench', 'GPQA Diamond 91.9%', 'WebDev Arena 1487 Elo', 'vibe coding') add tokens Claude does not need. Not a level-3 lean document, but tighter than the verbose level-1 anchor.	2 / 3
Actionability	Provides fully executable, copy-paste commands such as 'gemini -m gemini-3-pro-preview --approval-mode yolo "Review this codebase..."' plus concrete troubleshooting commands ('ps aux \| grep gemini', 'pkill -9 -f ...', 'lsof -p <PID>'). Specific examples throughout.	3 / 3
Workflow Clarity	A numbered 'Running a Task' sequence exists and there is a detect→diagnose→kill feedback loop for hung processes, but the validation checkpoints are scattered across separate sections rather than inline in the run sequence, and heavy repetition of the same warnings dilutes the canonical flow. Present-but-implicit checkpoints match the level-2 anchor.	2 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the ~225-line body is monolithic — troubleshooting, the model-selection guide, and the quick-reference table are all inline when they could be split into referenced files. Sections are well-organized, but content that should be separate is inline, matching level 2.	2 / 3
	Total	9 / 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.

A well-crafted description with an explicit 'Use when' trigger, concrete named actions, and a clear tool-specific niche. It hits all top anchors; the only nit is a minor over-claim ('state-of-the-art') that does not undermine specificity.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'run Gemini CLI for code review, plan review, or big context (>200k) processing' and 'Uses Gemini 3 Pro by default' — rather than vague language. The only soft spot is the mild buzzword 'state-of-the-art reasoning and coding', but the enumerated actions are specific enough for the top anchor.	3 / 3
Completeness	Explicitly answers both what (runs Gemini CLI for review/analysis using Gemini 3 Pro) and when ('Use when the user asks to run Gemini CLI for code review, plan review, or big context processing'), matching the top anchor's 'what AND when' requirement.	3 / 3
Trigger Term Quality	Includes natural terms users would say — 'code review', 'plan review', 'Gemini CLI' — plus an explicit 'Use when the user asks to run Gemini CLI' trigger. 'big context (>200k) processing' is slightly jargon-y but overall coverage is good.	3 / 3
Distinctiveness Conflict Risk	Gated on the user asking to run a specific external tool ('Gemini CLI'), giving it a clear niche unlikely to trigger competing skills, even though 'code review' alone could overlap with others.	3 / 3
	Total	12 / 12 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: jdrhyne/agent-skills
Commit: a4d31ad

Reviewed: 11 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.