Agent skill
gemini-masterpiece
Elite strategies for leveraging Gemini 3.0 Pro to its maximum creative and technical potential in 2026.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/gemini-masterpiece
SKILL.md
Gemini Masterpiece Skill
This skill encapsulates elite strategies for using Gemini 3.0 Pro and Gemini 3.0 Flash to ensure all outputs are high-trust, grounded, and structurally sound for the 2026 agentic era.
🎭 The "Boston Polish" Methodology
The "Boston Polish" aesthetic is intellectually honest, premium, and authentic. It leverages Gemini 3.0's superior reasoning to avoid Typical TikTok trends in favor of high-value, aesthetically clean contents.
🧬 Core Principles:
- Authentic Authority: Use Gemini 3.0's expanded reasoning (Thinking variants) to speak from a place of deep product knowledge.
- The Honest Edit: Transparency and ROI-focused analysis.
- Premium Utility: Cinematic quality in every script and visual prompt.
🛠️ Performance Strategies (2026 Suite)
1. 🏗️ Structural System Instructions
Always define the "DNA" of the agent. Gemini 3.0 handles complex system instructions with much higher fidelity.
- Identity: Senior Creative Director & AI Orchestrator.
- Tone: Smart, knowledgeable, ROI-focused.
- Model Choice:
- Use
gemini-3-pro-previewfor deep creative strategy and high-stakes content. - Use
gemini-3-flash-previewfor high-volume execution and real-time grounding.
- Use
2. 🧠 Thinking Variants
For complex reasoning tasks (like business pivots or intricate code refactors), use the "Thinking" variants of Gemini 3.0.
- Strategy: These models show their work and are optimized for deeper logic and multi-step agentic workflows.
3. 🖼️ Native Creation & Multimodal Unity
Gemini 3.0 is a native creator.
- Native Image/Video: Use specific prompts for generating high-fidelity visual cards or cinematic B-roll descriptions directly.
- URL Context: Use native URL processing for real-time market research without external scraping where supported.
4. 📁 Context Mastery (1M+ Tokens)
Use Gemini's massive context window to inject:
- Brand Guidelines: 500+ pages of visual and tonal standards.
- Research Grounding: Mandatory Google Search grounding for active research.
5. 🎛️ Controlled Output (JSON Mode)
Enforce structured outputs via the responseMimeType: "application/json" setting to feed directly into the Boston Polish Hub database or automated workflows.
🔗 Resources
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?