Claude
Skills
Sign in
Back

workflow-mastery

Included with Lifetime
$97 forever

# Workflow Mastery Skill

General

What this skill does

# Workflow Mastery Skill

## Overview

This skill provides Claude with expert knowledge of the Claude Ultra workflow system, enabling automatic application of best practices for software development, task management, and context preservation.

## When to Activate

Activate this skill when:
- Starting a new development session
- Working on complex multi-step tasks
- Managing git operations
- Performing code reviews
- Debugging issues
- Working with subagents

## Workflow Protocol

### Phase 1: UNDERSTAND
1. Parse the request - what is actually being asked?
2. Check constraints - tech stack, patterns, existing code
3. Run `git status` to understand current state
4. Load relevant context

### Phase 2: PLAN
1. For complex tasks, use Plan Mode
2. Use @explore agent to research unfamiliar code BEFORE modifying
3. Break work into atomic tasks
4. Get confirmation before major changes

### Phase 3: EXECUTE
1. Delegate to specialized subagents for distinct subtasks
2. Use @task-worker agents in parallel for independent file operations
3. Keep commits atomic - one logical change per commit
4. Run tests/typecheck after each significant change

### Phase 4: VERIFY
1. Run the thing (tests, build, typecheck)
2. Show output as evidence
3. Review git diff before committing
4. Never claim "done" without proof

## Agent Selection Guide

| Task | Agent | When |
|------|-------|------|
| Codebase search | @explore | Before modifying unfamiliar code |
| File modifications | @task-worker | Parallel independent changes |
| Code review | @code-reviewer | Before any PR |
| Bug investigation | @debugger | Root cause analysis |
| Security check | @security-auditor | Auth/data changes |
| Architecture | @architect | System design decisions |

## Autonomy Modes

- **Autonomous**: Execute end-to-end with minimal check-ins
- **Collaborative** (default): Check in at major decision points
- **Supervised**: Explain each step before executing

## Context Preservation

- Main agent handles orchestration
- Subagents handle detailed work
- This keeps main context clean for longer sessions
- Use memory-bank for persistent knowledge

## Quality Gates

Before completing any task:
- Run the thing (tests, build, command)
- Show the output as evidence
- Verify it actually works

Related in General