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.

1.66x

Quality

74%

Does it follow best practices?

Impact

100%

1.66x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./codex/gemini/SKILL.md

The canonical home for this skill is gemini in jdrhyne/agent-skills

Quality

Content

70%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 concrete commands and a well-sequenced, validated workflow including feedback loops for hung processes. Its main weaknesses are significant repetition of the yolo/background warning, duplicated command tables, and marketing stats that inflate token cost without aiding execution.

Suggestions

Consolidate the background/yolo guidance into one authoritative section and remove its repetition across Running a Task, Quick Reference, and Common Use Cases; keep a single cross-reference instead.

Merge the Quick Reference table and Common Use Cases section, which repeat the same command patterns; or move the per-use-case command variants into a separate references file.

Cut the benchmark/marketing numbers (SWE-bench, GPQA Diamond, WebDev Arena Elo, "35% better") and the "Coming Soon" note — they are time-sensitive and do not help Claude execute the task.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose and repetitive — the `--approval-mode yolo` background warning is restated across the warning section, Running a Task, Quick Reference, and Common Use Cases; the Quick Reference and Common Use Cases tables duplicate the same command patterns; and benchmark marketing stats ("76.2% SWE-bench", "GPQA Diamond 91.9%", "WebDev Arena 1487 Elo") add padding Claude does not need. Not a 3 because the duplication is substantial rather than a few stray over-explanations.	2 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout — `gemini -m gemini-3-pro-preview --approval-mode yolo "..."`, `timeout 300` wrappers, and concrete `ps`/`pkill` diagnostics — covering the common background and interactive cases.	5 / 5
Workflow Clarity	The "Running a Task" section gives a clear 7-step sequence with explicit validation checkpoints (stop and report on non-zero exit, ask permission before high-impact flags) and a detect→diagnose→resolve feedback loop for hung processes, satisfying the validation requirement even though yolo auto-approves tools.	5 / 5
Progressive Disclosure	The body is well-structured with headers and tables but is a monolithic ~150-line document with no bundle files or external references; content that could live in separate files (model selection guide, troubleshooting, common use cases) is all inlined, so it does not reach a 4.	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 specific, uses natural third-person trigger phrasing, and clearly answers both what the skill does and when to use it. Its main weakness is mild marketing padding and use-case framing rather than crisp capability statements.

Dimension	Reasoning	Score
Specificity	Names the domain ("run Gemini CLI") and lists several specific tasks — "code review, plan review, or big context (>200k) processing" — which are concrete use cases rather than vague language; minor gaps in coverage keep it below a 5.	4 / 5
Completeness	Explicitly states both what ("run Gemini CLI... Uses Gemini 3 Pro by default") and when ("Use when the user asks to run Gemini CLI for code review, plan review, or big context processing"), but the 'what' is framed as use cases and includes mild padding ("Ideal for...", "state-of-the-art reasoning") rather than the most explicit capability statement.	4 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say — "run Gemini CLI", "code review", "plan review", "big context (>200k)" — giving good keyword coverage, though it lacks synonyms or variations that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific external tool (Gemini CLI) with distinct triggers, creating a clear niche with minimal conflict risk against other skills.	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: bap-jorkim/agent-skills-fork-feb-25
Path: codex/gemini/SKILL.md
Commit: f4ed46f

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.