Agent skill · Code Review & Quality

call-gemini

Invoke the Gemini CLI for architecture and scalability review.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill call-gemini-etroxtaran-conductor --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 6 KB
Bundled scripts: none
Version: 1.1.0
Path: skills/ai-llm/call-gemini-etroxtaran-conductor/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Call Gemini Skill Wrapper for invoking Gemini agent via CLI for architecture and scalability review. ## Overview Gemini is specialized for: - Architecture pattern analysis - Scalability assessment - Design principle compliance - Technical debt evaluation ## Prerequisites - `gemini` CLI installed and accessible on PATH. ## Usage ``` /call-gemini ``` ## Expertise Weights | Area | Weight | Description | |------|--------|-------------| | Architecture | 0.7 | Design patterns, modularity | | Scalability | 0.8 | Performance at scale, bottlenecks | | Patterns | 0.6 | Design patterns, anti-patterns | ## CLI Invocation ```bash gemini --yolo "<prompt>" ``` ### Flags | Flag | Purpose | |------|---------| | `--yolo` | Auto-approve tool calls (required for non-interactive) | | `--model` | Select model (optional, default: gemini-2.0-flash) | **IMPORTANT**: - Gemini does NOT support `--output-format` - Output must be parsed from raw response - Prompt is a positional argument ## Standard Prompts ### Plan Validation (Phase 2) ```bash gemini --yolo " You are reviewing an implementation plan for architecture and scalability. Read the plan JSON provided by the orchestrator (phase_outputs export). Eva

What's inside
Steps it walks through
  1. Overview
  2. Prerequisites
  3. Usage
  4. Expertise Weights
  5. CLI Invocation
  6. Flags
  7. Standard Prompts
  8. Plan Validation (Phase 2)
  9. Code Review (Phase 4)
  10. Output Parsing
  11. Error Handling
  12. Timeout
  13. Parse Error
  14. Agent Unavailable
Ships with 1 file
  • metadata.json
Commands it runs
gemini --yolo "<prompt>"
gemini --yolo "
You are reviewing an implementation plan for architecture and scalability.
Read the plan JSON provided by the orchestrator (phase_outputs export).
Evaluate for:
Return your assessment as JSON (wrap in code block):
Focus on design quality. Only block for fundamental architecture flaws.
You are performing an architecture-focused code review of recently implemented changes.
Review the implementation for:
Also check:
More from claude-skill-registry
All skills →
descriptive-statisticsSummarizing and visualizing data through measures of center, spread, shape, and position. Covers…Data & Analyticsperplexity-researcher-reasoning-proHighest level of research and reasoning capabilities for complex decision-making with significant…OtherretroBrutally honest engineering retrospective. Analyzes git history for what actually happened — not…Data & AnalyticsanalyzeUniversal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points…Otherarize-prompt-optimizationINVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data…Data & Analyticscellxgene-contextGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when…Data & Analytics
About this skill
What does the call-gemini skill do?

Invoke the Gemini CLI for architecture and scalability review.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill call-gemini-etroxtaran-conductor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.