secondsky/claude-skills / plugins/gemini-cli/skills/gemini-cli
gemini-cli
VerifiedGoogle Gemini CLI for second opinions, architectural advice, code reviews, security audits. Leverage 1M+ context for comprehensive codebase analysis via command-line tool.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.0 KB |
| references/gemini-experiments.md | markdown | 12.7 KB |
| references/helper-functions.md | markdown | 1000 B |
| references/models-guide.md | markdown | 3.9 KB |
| references/prompting-strategies.md | markdown | 1.7 KB |
| scripts/install-gemini-coach.shexecutable | script | 4.1 KB |
| scripts/setup-slash-command.shexecutable | script | 3.8 KB |
| scripts/test-connection.shexecutable | script | 3.1 KB |
references/models-guide.md
View on GitHub# Gemini Models Comparison Guide
Based on systematic testing (2025-11-08)
---
## Available Models
### gemini-2.5-flash (Default)
**Characteristics**:
- Fast response time: ~5-25 seconds (average ~20s)
- Good quality for most tasks: ⭐⭐⭐⭐
- Prioritizes: Performance, simplicity, speed
- Safe with directory scanning
- Lower cost
**Best For**:
- Code reviews
- Debugging (root cause analysis is strong)
- Directory/file scanning
- General questions
- When speed matters
**Example**:
```bash
gemini-coach review src/auth.ts
gemini-coach debug "Error message here"
```
---
### gemini-2.5-pro
**Characteristics**:
- Response time: ~15-30 seconds (average ~23s, often similar to Flash!)
- Excellent quality: ⭐⭐⭐⭐⭐
- Prioritizes: Correctness, consistency, thoroughness
- May get confused with directory scanning (tries to use tools)
- Higher cost
**Best For**:
- Architecture decisions (critical)
- Security audits (thorough)
- Complex reasoning tasks
- When accuracy > speed
- Major refactoring plans
**Example**:
```bash
gemini-coach architect "Should I use D1 or KV?" .
gemini-coach security-scan ./src/api
```
---
### gemini-2.5-flash-lite
**Status**: ❌ **Not accessible via Gemini CLI**
Model exists in Gemini API but returns 404 error when accessed via CLI. Do not use.
---
## When Models Disagree
**Critical Finding**: Flash and Pro can give **opposite recommendations** for the same question, and **both can be valid**.
**Example** (D1 vs KV for sessions):
- **Flash**: Recommends KV
- Prioritizes: Performance, edge caching, TTL
- "Usually acceptable" eventual consistency
- **Pro**: Recommends D1
- Prioritizes: Strong consistency, SQL queries
- "Critical" consistency for sessions
**Why This Happens**:
- Flash: Performance-focused
- Pro: Consistency-focused
**How to Handle**:
1. For critical/security decisions → Prefer Pro's perspective
2. For performance-sensitive apps → Consider Flash's perspective
3. For major architectural choices → Get both viewpoints:
```bash
gemini-coach quick "Question?" # Flash
GEMINI_MODEL=gemini-2.5-pro gemini-coach architect "Same question" . # Pro
```
---
## Model Selection Matrix
| Task Type | Recommended Model | Why |
|-----------|-------------------|-----|
| Quick questions | Flash | Acceptable quality, fast |
| Architecture decisions | **Pro** | More thorough trade-off analysis |
| Security reviews | **Pro** | Catches subtle issues |
| Debug assistance | Flash | Root cause analysis is good enough |
| Code review | Flash | Comprehensive enough for most cases |
| Directory scanning | Flash | Pro may get confused, use tools |
| Whole project analysis | Pro | Better with 1M context |
---
## Performance Comparison
Based on testing with same question ("D1 vs KV for sessions"):
| Model | Time | Quality | Recommendation |
|-------|------|---------|----------------|
| Flash | ~25s | ⭐⭐⭐⭐ | KV (performance) |
| Pro | ~23s | ⭐⭐⭐⭐⭐ | D1 (consistency) |
| Flash-lite | 404 error | N/A | Not accessible |
**Key Finding**: Pro isn't significantly slower than Flash on many queries!
---
## Override Default Model
```bash
# Use Pro for single command
GEMINI_MODEL=gemini-2.5-pro gemini-coach review src/auth.ts
# Use Pro for all commands in session
export GEMINI_MODEL=gemini-2.5-pro
gemini-coach review src/auth.ts
gemini-coach architect "Question" .
```
---
## Recommendations
**Default Strategy**: Use Flash for most tasks, Pro for critical decisions
**When to Always Use Pro**:
- Architectural decisions
- Security audits
- Major refactors
- Production deployment reviews
**When Flash is Better**:
- Quick code reviews
- Debugging
- Directory/file scanning
- Non-critical questions
**When to Get Both Perspectives**:
- Critical architectural decisions
- Technology choices that affect entire project
- Performance vs consistency trade-offs
---
**Last Updated**: 2025-11-08
**Source**: Systematic testing documented in `gemini-experiments.md`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |