Skill79 repo starsupdated yesterday

handoff-gemini

The handoff-gemini skill enables delegating specific tasks to Google's Gemini CLI to preserve Claude's context window. Use it for long document analysis, multimodal processing, research summarization, and large file comprehension, while keeping Claude focused on complex coding, architecture decisions, and multi-step workflows that require sustained reasoning.

View source Repository: director-mode-lite

Install in Claude Code

Copy

git clone --depth 1 https://github.com/claude-world/director-mode-lite /tmp/handoff-gemini && cp -r /tmp/handoff-gemini/skills/handoff-gemini ~/.claude/skills/handoff-gemini

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# Handoff to Gemini CLI

Delegate tasks to Google Gemini CLI to save Claude context.

---

## When to Use Gemini

| Use Gemini For | Keep in Claude |
|----------------|----------------|
| Long document analysis | Complex coding |
| Multimodal tasks | Architecture decisions |
| Research and summarization | Multi-step workflows |
| Large file comprehension | Problem analysis |

---

## Prerequisites

```bash
# Install Gemini CLI (Google)
npm install -g @google/gemini-cli
# Or via: https://github.com/google-gemini/gemini-cli
```

---

## Handoff Process

### 1. Prepare Context
```markdown
## Task for Gemini
**Goal**: [What needs to be done]
**Files**: [Which files to analyze]
**Output**: [What format to return]
```

### 2. Generate Command
```bash
# Analyze large file
gemini "Summarize components in codebase" -f src/**/*.ts

# Research task
gemini "Research best practices for [topic]"

# Document analysis
gemini "Extract key points" -f docs/spec.md
```

### 3. Provide Instructions
- Why Gemini is suitable
- Expected output
- How to continue workflow

---

## Example

```markdown
## Task: Research API Best Practices

**Command:**
gemini "Research REST API versioning strategies. Summarize pros/cons."

**After:**
- Review research
- Share relevant findings
- Implement chosen strategy
```

---

## Benefits

- **Token Savings**: Research tasks don't consume Claude context
- **Long Context**: Handles very large documents
- **Specialization**: Use each AI's strengths