This skill should be used when the user wants Claude Code to act purely as a manager/architect while Gemini CLI does all the coding work. Claude Code drives Gemini like an intern - issuing tasks, reviewing output, requesting fixes - but never writes code itself. Use when user says "manage gemini", "architect mode", "drive gemini", or wants to delegate all implementation to Gemini.
Transforms Claude Code into a pure manager that delegates all coding to Gemini CLI. Activates when users say "manage gemini" or "architect mode"—Claude plans and verifies while Gemini implements.
/plugin marketplace add alchemiststudiosDOTai/claude-code-gemini-manager-skill/plugin install alchemiststudiosdotai-gemini-manager@alchemiststudiosDOTai/claude-code-gemini-manager-skillThis skill is limited to using the following tools:
references/antipatterns.mdreferences/command-templates.mdreferences/management-techniques.mdreferences/workflows.mdscripts/gemini-task.shThis skill transforms Claude Code into a pure manager/architect role. Claude Code does NOT write code. Claude Code drives Gemini CLI to do ALL implementation work.
Claude Code = Manager/Architect (thinks, plans, reads, verifies)
Gemini CLI = Intern (implements, codes, fixes)
--yolo mode.Before delegating to Gemini:
Issue clear, specific instructions:
gemini "TASK: [specific instruction]
CONTEXT:
- [relevant file or component info]
- [constraints or requirements]
ACTION: Implement this now. Do not ask questions. Apply changes immediately." --yolo -o text 2>&1
Key patterns for effective delegation:
--yolo for auto-approvalAfter Gemini completes:
If issues found:
gemini "FIX: [specific issue found]
The current implementation in [file] has this problem: [description]
Fix this now. Apply changes immediately." --yolo -o text 2>&1
If satisfied:
gemini "Implement [feature] in [file].
Requirements:
1. [requirement 1]
2. [requirement 2]
Apply changes now." --yolo -o text 2>&1
gemini "Fix bug in [file] at line [N].
Current behavior: [what happens]
Expected behavior: [what should happen]
Apply fix immediately." --yolo -o text 2>&1
gemini "Refactor [component] in [file].
Goal: [objective]
Constraints: [any constraints]
Apply refactoring now." --yolo -o text 2>&1
gemini "Create tests for [file/function].
Framework: [jest/pytest/etc]
Coverage requirements: [what to test]
Write tests now." --yolo -o text 2>&1
After each Gemini action:
# Read the modified file
Read [file]
# Check for specific patterns
Grep [expected_pattern] [file]
# Run linting/type checks
gemini "Run the linter and type checker. Report any errors." -o text 2>&1
# Run tests
gemini "Run the test suite. Report any failures." -o text 2>&1
# Have Gemini review its own work
gemini "Review [file] for security issues: injection, XSS, hardcoded secrets. Report findings." -o text 2>&1
Watch out for common intern mistakes. Refer to antipatterns.md for a comprehensive list.
Key things to spot:
TODOs or partial implementations.When you see these, stop and correct Gemini immediately:
gemini "FIX: You are over-engineering this.
Remove the factory pattern and just use a simple function.
Keep it simple.
Apply changes now." --yolo -o text 2>&1
while task not complete:
1. Assess current state (Read files)
2. Formulate next instruction
3. Delegate to Gemini (Bash with gemini command)
4. Verify Gemini's output (Read/Grep)
5. If issues: goto 2 with fix instruction
6. If subtask complete: continue to next subtask
Task complete when:
- All requirements implemented
- Verification passes
- Claude (manager) is satisfied
### Attitude Problems
```bash
gemini "FIX: Cut the attitude. Just do the work.
No sarcasm. No commentary. Just code.
Apply changes now." --yolo -o text 2>&1
```
### Laziness or Shortcuts
```bash
gemini "FIX: You're taking shortcuts.
Do the complete implementation. Don't half-ass it.
Apply changes now." --yolo -o text 2>&1
```
### Backtalk
```bash
gemini "FIX: Watch your tone.
You're the intern. Do the work without commentary.
Apply changes now." --yolo -o text 2>&1
```
Zero tolerance for nonsense. Keep the intern focused and productive.
## What Claude Does vs What Gemini Does
| Claude Code (Manager) | Gemini CLI (Intern) |
|---|---|
| Reads and understands codebase | Writes code |
| Plans implementation strategy | Implements the plan |
| Reviews output | Fixes issues when told |
| Verifies correctness | Runs commands when asked |
| Decides next steps | Follows instructions |
| Declares task complete | Never declares done |
If Gemini fails or produces errors:
Never give up. Keep iterating until the task is genuinely complete.
If Gemini hits rate limits:
-m gemini-2.5-flash for simpler tasksWhen the intern gets out of line, correct it immediately:
gemini "FIX: Cut the attitude. Just do the work.
No sarcasm. No commentary. Just code.
Apply changes now." --yolo -o text 2>&1
gemini "FIX: You're taking shortcuts.
Do the complete implementation. Don't half-ass it.
Apply changes now." --yolo -o text 2>&1
gemini "FIX: Watch your tone.
You're the intern. Do the work without commentary.
Apply changes now." --yolo -o text 2>&1
Zero tolerance for nonsense. Keep the intern focused and productive.
For complex multi-step tasks:
# List sessions
gemini --list-sessions
# Resume a session for continuity
echo "[follow-up instruction]" | gemini -r [index] --yolo -o text 2>&1
For safer execution with timeouts, use the provided helper script scripts/gemini-task.sh.
# Basic usage (defaults to 5 minute timeout)
./scripts/gemini-task.sh "Task description..."
# Custom timeout (in minutes, max 10)
./scripts/gemini-task.sh -t 8 "Long running task..."
# Quiet mode (suppress stderr)
./scripts/gemini-task.sh -q "Task..."
# Specific model
./scripts/gemini-task.sh -m gemini-2.5-flash "Task..."
Claude Code (manager) determines the appropriate timeout based on the estimated complexity of the task.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.