gemini

Gemini CLI for one-shot Q&A, summaries, and generation.

1.32x

Quality

66%

Does it follow best practices?

Impact

99%

1.32x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./openclaw/skills/gemini/SKILL.md

Evaluation results

98%

38%

Automated Code Review Feedback Tool

One-shot JSON output invocation

Criteria

Without context

With context

Positional prompt syntax

100%

One-shot invocation

100%

JSON output flag used

100%

No --yolo flag

100%

gemini CLI as interface

100%

Output captured

66%

86%

File content passed to gemini

100%

Without context: $0.1948 · 55s · 16 turns · 22 in / 2,905 out tokens

With context: $0.3367 · 1m 2s · 22 turns · 432 in / 3,474 out tokens

100%

Model Benchmarking Script for Gemini Variants

Model selection flag usage

Criteria

Without context

With context

--model flag used

100%

Model value as flag argument

100%

Positional prompt syntax

100%

One-shot invocation

100%

No --yolo flag

100%

Multiple models queried

100%

Without context: $0.1492 · 36s · 13 turns · 20 in / 2,005 out tokens

With context: $0.3163 · 1m 3s · 21 turns · 139 in / 3,175 out tokens

100%

35%

Gemini CLI Extension Audit and Setup Script

Extension management commands

Criteria

Without context

With context

List extensions command

100%

Extensions management command

100%

One-shot verification query

100%

Positional prompt in query

100%

No --yolo flag

100%

Auth prerequisite documented

100%

Without context: $0.2265 · 1m 7s · 15 turns · 18 in / 3,660 out tokens

With context: $0.1980 · 41s · 15 turns · 424 in / 2,129 out tokens

Repository: trpc-group/trpc-agent-go
Commit: 8763418

Evaluated: 16 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Automated Code Review Feedback Tool Model Benchmarking Script for Gemini Variants Gemini CLI Extension Audit and Setup Script

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.