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

75%

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 ./codex/gemini/SKILL.md

Quality

Content

71%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 executable commands, clear sequencing, and useful safety/error-handling guidance, but it is verbose due to heavy repetition and monolithic — several sections could be extracted into reference files.

Suggestions

De-duplicate the background/yolo warning: state it once prominently and reference it elsewhere instead of restating it five times.

Consolidate the model list into one canonical table and remove the repeated enumerations in 'Running a Task', 'Tips', and the Model Selection Guide.

Extract the full Troubleshooting and Model Selection Guide into references/ files and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body provides useful specifics but repeats material heavily — the background/yolo warning appears ~5 times, the model list is restated three times, and the hung-process guidance is duplicated in both the critical-warning and full troubleshooting sections.	3 / 5
Actionability	Supplies copy-paste-ready commands (`gemini -m gemini-3-pro-preview --approval-mode yolo "..."`), timeout wrappers, ps/pkill diagnostics, a full flag reference, and use-case tables covering the common cases.	5 / 5
Workflow Clarity	The 'Running a Task' section is a clear numbered 1–7 sequence with AskUserQuestion confirmation gates, and the Error Handling section provides stop/retry feedback loops; minor gap is no explicit validation of Gemini output before reporting back.	4 / 5
Progressive Disclosure	No bundle files exist and all content is inlined in a ~230-line SKILL.md; sections are well-organized, but splittable material (model benchmark tables, full troubleshooting, common-use-case command blocks) lives inline with no one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

78%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 well-structured with an explicit 'Use when...' trigger, a clear statement of what the skill does, and a distinct named-tool niche. It is slightly held back by use-case-style actions rather than exhaustive concrete operations and a few missing natural synonyms.

Suggestions

Add concrete action verbs for what Gemini does with results (e.g., 'returns findings you can quote', 'generates a review report') to lift specificity.

Include synonyms users naturally say, such as 'second opinion' or 'large context window', alongside 'big context (>200k)'.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete use cases ('code review, plan review, or big context (>200k) processing'), but these are use-case categories rather than a comprehensive list of discrete actions the skill performs, and 'comprehensive analysis' is somewhat abstract.	3 / 5
Completeness	Explicitly answers both 'what' (run Gemini CLI for code/plan review and big-context analysis) and 'when' via a concrete 'Use when the user asks...' trigger phrase, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('code review', 'plan review', 'big context', 'Gemini CLI') with the '>200k' qualifier, but misses common synonyms like 'second opinion' and 'large context windows' beyond the one mention.	4 / 5
Distinctiveness Conflict Risk	Gemini CLI is a distinct named tool with a clear large-context/second-opinion niche, but 'code review' as a trigger carries minor overlap risk with general code-review skills.	4 / 5
	Total	16 / 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: jdrhyne/agent-skills
Path: codex/gemini/SKILL.md
Commit: 439cd3a

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.