Agent skill · Business & Finance

querying-gemini

Queries Gemini 3 Flash for high-speed code analysis, generation, and complex coding questions. Provides P0-P3 prioritized analysis reports, architecture audits, and code generation with configurable thinking levels (minimal/low/medium/high). 1M context, 64K output. Pro-level intelligence at Flash pricing.

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill costiash-cognivagent-claude-skills-querying-gemini --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Allowed tools: -Read-Grep-Glob-Bash
Path: skills/ai-llm/costiash-cognivagent-claude-skills-querying-gemini/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

# Querying Gemini 3 Flash Queries Gemini 3 Flash for fast, intelligent code analysis, generation, and complex technical questions. Leverages Gemini 3 Flash's 1M token context window and configurable thinking levels to provide comprehensive analysis with P0-P3 prioritized findings. ## Quick Reference Gemini 3 Flash provides four specialized capabilities via standalone scripts: | Script | Purpose | Use Case | |--------|---------|----------| | `gemini_query.py` | General queries | Complex coding questions, algorithm design, concept explanations | | `gemini_analyze.py` | Code analysis | Pre-merge reviews, architecture audits, security scans | | `gemini_code.py` | Code generation | Generate production-ready code with best practices | | `gemini_fix.py` | Root-cause fixes | Bug debugging that addresses underlying issues (not symptoms) | **Key Features:** - 1,000,000 token context window (analyze very large codebases) - 64,000 token output limit (comprehensive responses) - Configurable thinking levels (minimal/low/medium/high) - Structured P0-P3 prioritization for findings - Jan 2025 knowledge cutoff - Pro-level intelligence at Flash pricing ($0.50/1M input, $3/1M output) ## Scripts ### ge

What's inside
Steps it walks through
  1. Quick Reference
  2. Scripts
  3. geminiquery.py
  4. geminianalyze.py
  5. geminicode.py
  6. geminifix.py
  7. When to Use
  8. Code Analysis
  9. Code Generation
  10. Root-Cause Debugging
  11. Complex Questions
  12. When NOT to Use
  13. Limitations
  14. File Size Constraints
Ships with 1 file
  • metadata.json
Commands it runs
python .claude/skills/querying-gemini/scripts/gemini_query.py \
Ask about Python async patterns
Complex algorithm design
python .claude/skills/querying-gemini/scripts/gemini_analyze.py \
Security audit of API endpoints
Quick quality check before merge
python .claude/skills/querying-gemini/scripts/gemini_code.py \
Generate a FastAPI endpoint
Generate a React component
python .claude/skills/querying-gemini/scripts/gemini_fix.py \
More from claude-skill-registry
All skills →
About this skill
What does the querying-gemini skill do?

Queries Gemini 3 Flash for high-speed code analysis, generation, and complex coding questions. Provides P0-P3 prioritized analysis reports, architecture audits, and code generation with configurable thinking levels (minimal/low/medium/high). 1M context, 64K output. Pro-level intelligence at Flash pricing.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill costiash-cognivagent-claude-skills-querying-gemini --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