gemini-delegation
npx machina-cli add skill athola/claude-night-market/gemini-delegation --openclawTable of Contents
- Overview
- When to Use
- Prerequisites
- Delegation Flow
- Quick Start
- Basic Command
- Save Output
- Shared Patterns
- Gemini-Specific Details
- Exit Criteria
Gemini CLI Delegation
Overview
This skill implements conjure:delegation-core for the Gemini CLI. It provides Gemini-specific authentication, quota management, and command construction using shared patterns.
When To Use
- After
Skill(conjure:delegation-core)determines Gemini is suitable - When you need Gemini's large context window (1M+ tokens)
- For batch processing, summarization, or pattern extraction tasks
- If the
geminiCLI is installed and authenticated
When NOT To Use
- Deciding which model to use (use delegation-core first)
- Gemini CLI not installed
- Deciding which model to use (use delegation-core first)
- Gemini CLI not installed
Prerequisites
Installation:
# Verify installation
gemini --version
# Check authentication
gemini auth status
# Login if needed
gemini auth login
# Or set API key
export GEMINI_API_KEY="your-key"
Verification: Run the command with --help flag to verify availability.
Delegation Flow
Implements standard delegation-core flow with Gemini specifics:
gemini-delegation:auth-verified- Verify Gemini authenticationgemini-delegation:quota-checked- Check Gemini API quotagemini-delegation:command-executed- Execute via Gemini CLIgemini-delegation:usage-logged- Log Gemini API usage
Quick Start
Basic Command
# File analysis
gemini -p "@path/to/file Analyze this code"
# Multiple files
gemini -p "@src/**/*.py Summarize these files"
# With specific model
gemini --model gemini-2.5-pro-exp -p "..."
# JSON output
gemini --output-format json -p "..."
Verification: Run the command with --help flag to verify availability.
Save Output
gemini -p "..." > delegations/gemini/$(date +%Y%m%d_%H%M%S).md
Verification: Run the command with --help flag to verify availability.
Shared Patterns
This skill uses shared modules from delegation-core:
- Authentication: See
delegation-core/../../leyline/skills/authentication-patterns/SKILL.md - Quota Management: See
delegation-core/../../leyline/skills/quota-management/SKILL.md - Usage Logging: See
delegation-core/../../leyline/skills/usage-logging/SKILL.md - Error Handling: See
delegation-core/../../leyline/skills/error-patterns/SKILL.md
Gemini-Specific Details
For Gemini-specific models, CLI options, cost reference, and troubleshooting, see modules/gemini-specifics.md.
Exit Criteria
- Authentication confirmed working
- Quota checked and sufficient
- Command executed successfully
- Usage logged for tracking
Source
git clone https://github.com/athola/claude-night-market/blob/master/plugins/conjure/skills/gemini-delegation/SKILL.mdView on GitHub Overview
This skill implements conjure:delegation-core for the Gemini CLI, providing Gemini-specific authentication, quota management, and command construction to enable batch processing and leverage Gemini's 1M+ token context window. It integrates shared delegation-core patterns with Gemini-specific details to streamline delegation flows.
How This Skill Works
Follows the standard delegation-core flow, augmented with Gemini specifics: authenticate the Gemini CLI, verify API quota, execute commands via the Gemini CLI, and log usage. It references shared modules for authentication, quota management, and usage logging, plus Gemini-specific details to handle CLI options and cost considerations.
When to Use It
- After conjure:delegation-core determines Gemini is suitable
- When you need Gemini's 1M+ token context window for long analyses
- For batch processing, summarization, or pattern extraction tasks
- If the Gemini CLI is installed and authenticated
- When you want integrated Gemini authentication and quota checks as part of delegation
Quick Start
- Step 1: Verify Gemini CLI is installed and authenticated (gemini --version; gemini auth status; gemini auth login or set GEMINI_API_KEY)
- Step 2: Run a sample delegation command (e.g., gemini -p "@path/to/file Analyze this code" )
- Step 3: Optional: output as JSON or save results (gemini --output-format json -p '...' or gemini -p '...' > delegations/...md)
Best Practices
- Verify Gemini CLI installation and authentication before delegating
- Rely on delegation-core first to decide Gemini suitability
- Monitor and log usage with the shared usage-logging patterns
- Before execution, ensure authentication and quota checks pass
- Consult Gemini-specific modules for CLI options and troubleshooting
Example Use Cases
- Analyze a large codebase with gemini -p '@path/to/file Analyze this code'
- Summarize multiple Python files: gemini -p '@src/**/*.py Summarize these files'
- Obtain JSON output: gemini --output-format json -p '...'
- Save delegated results: gemini -p '...' > delegations/gemini/$(date +%Y%m%d_%H%M%S).md
- Check auth and quota before running a delegation: gemini auth status; gemini quota status