Claude-Code-Workflow/.claude/commands/gemini/chat.md at 3d521f0af1cfcfa4d86a5d8126924541c280aaa1

mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-13 02:41:50 +08:00

Files

catlog22 3d521f0af1 Refactor gemini chat commands: split into simplified modular structure

- Simplify /gemini:chat by removing complex template selection logic
- Create /gemini:chat:bug-fix for specialized bug analysis with diagnostic template
- Create /gemini:chat:plan for project planning with architecture template
- Remove dependencies on chat-template-load.sh script
- Organize template commands in gemini/chat/ folder structure
- Update README documentation for new command structure

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-09-08 23:44:11 +08:00

2.8 KiB

Raw Blame History

name, parent, description, usage, argument-hint, examples, allowed-tools, model

name

parent

description

usage

argument-hint

examples

allowed-tools

model

gemini-chat

/gemini

Simple Gemini CLI interaction command for direct codebase analysis

/gemini:chat "inquiry"

your question or analysis request

/gemini:chat "analyze the authentication flow"

/gemini:chat "how can I optimize this React component performance?"

/gemini:chat "review security vulnerabilities in src/auth/"

Bash(gemini:*)

sonnet

🚀 Command Overview: `/gemini:chat`

Type: Basic Gemini CLI Wrapper
Purpose: Direct interaction with the gemini CLI for simple codebase analysis
Core Tool: Bash(gemini:*) - Executes the external Gemini CLI tool

📥 Parameters & Usage

<inquiry> (Required): Your question or analysis request
--all-files (Optional): Includes the entire codebase in the analysis context
--save-session (Optional): Saves the interaction to current workflow session directory
File References: Specify files or patterns using @{path/to/file} syntax

🔄 Execution Workflow

Parse Input -> Assemble Context -> Construct Prompt -> Execute Gemini CLI -> (Optional) Save Session

📚 Context Assembly

Context is gathered from:

Project Guidelines: Always includes @{CLAUDE.md,**/*CLAUDE.md}
User-Explicit Files: Files specified by the user (e.g., @{src/auth/*.js})
All Files Flag: The --all-files flag includes the entire codebase

📝 Prompt Format

=== CONTEXT ===
@{CLAUDE.md,**/*CLAUDE.md} [Project guidelines]
@{target_files} [User-specified files or all files if --all-files is used]

=== USER INPUT ===
[The user inquiry text]

⚙️ Execution Implementation

FUNCTION execute_gemini_chat(user_inquiry, flags):
  // Construct basic prompt
  prompt = "=== CONTEXT ===\n"
  prompt += "@{CLAUDE.md,**/*CLAUDE.md}\n"
  
  // Add user-specified files or all files
  IF flags contain "--all-files":
    result = execute_tool("Bash(gemini:*)", "--all-files", "-p", prompt + user_inquiry)
  ELSE:
    prompt += "\n=== USER INPUT ===\n" + user_inquiry
    result = execute_tool("Bash(gemini:*)", "-p", prompt)
  
  // Save session if requested
  IF flags contain "--save-session":
    save_chat_session(user_inquiry, result)
  
  RETURN result
END FUNCTION

💾 Session Persistence

When --save-session flag is used:

Check for existing active session (.workflow/.active-* markers)
Save to existing session's .chat/ directory or create new session
File format: chat-YYYYMMDD-HHMMSS.md
Include query, context, and response in saved file

Session Template:

# Chat Session: [Timestamp]

## Query
[Original user inquiry]

## Context
[Files and patterns included in analysis]

## Gemini Response
[Complete response from Gemini CLI]

2.8 KiB Raw Blame History

🚀 Command Overview: /gemini:chat