Project development workflow patterns including Plan-Build-Review-Fix cycle and feature development processes.
Provides structured development workflows using Plan-Build-Review-Fix cycles. Triggers when you use `/plan`, `/build`, `/review`, `/fix`, or `/cycle` commands to systematically develop features, fix bugs, or refactor code with quality gates.
/plugin marketplace add az9713/claude-code-agentic-framework/plugin install az9713-codebase-singularity@az9713/claude-code-agentic-frameworkThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This skill defines the development workflow patterns for the Codebase Singularity framework, including the core Plan-Build-Review-Fix cycle and feature development processes.
The foundational workflow for all development:
┌─────────────────────────────────────────────────────────────┐
│ │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐│
│ │ PLAN │───►│ BUILD │───►│ REVIEW │───►│ FIX ││
│ └─────────┘ └─────────┘ └─────────┘ └────┬────┘│
│ ▲ │ │
│ │ Loop until │ │
│ └──────────── quality passes ◄──────────────┘ │
│ │
└─────────────────────────────────────────────────────────────┘
Command: /plan [feature]
Agent: planner
Activities:
Output: specs/[feature]-plan.md
Command: /build
Agent: builder
Activities:
Output: Working code + tests
Command: /review
Agent: reviewer
Activities:
Output: specs/reviews/[date]-review.md
Command: /fix
Agent: fixer
Activities:
Output: Fixed code + verification
1. /prime # Load context
2. /plan # Design feature
3. /build # Implement
4. /review # Quality check
5. /fix # Address issues
6. [Repeat 4-5 until passing]
7. git commit # Save work
1. /prime # Load context
2. [Investigate bug] # Understand issue
3. /plan bugfix # Plan the fix
4. /fix # Implement fix
5. /review # Verify fix
6. git commit # Save work
1. /prime # Load context
2. /review # Identify issues
3. /plan refactor # Plan changes
4. /build # Implement refactor
5. /review # Verify improvement
6. git commit # Save work
Command: /cycle [feature]
Runs the complete Plan-Build-Review-Fix cycle:
Step 1: Planning
├── Read requirements
├── Analyze codebase
├── Create plan
└── Get approval
Step 2: Building
├── Implement plan
├── Create tests
└── Show progress
Step 3: Reviewing
├── Quality check
├── Security check
└── Generate report
Step 4: Fixing (if needed)
├── Address findings
├── Verify fixes
└── Re-review
Step 5: Complete
├── Summary
├── Files changed
└── Next steps
| Task | Agent |
|---|---|
| Create plan | planner |
| Write code | builder |
| Review code | reviewer |
| Fix issues | fixer |
| Write tests | test-writer |
| Fetch docs | doc-fetcher |
| Security check | security-auditor |
| Improve code | refactorer |
Feature Development:
planner → builder → test-writer → reviewer → fixer
Security Audit:
reviewer → security-auditor → fixer → reviewer
Documentation:
doc-fetcher → builder (docs) → reviewer
| Command | Purpose |
|---|---|
/prime | Initialize session |
/plan | Create implementation plan |
/build | Build from plan |
/review | Review code quality |
/fix | Fix review issues |
/cycle | Complete workflow |
/orchestrate | Multi-agent coordination |
/delegate | Direct agent invocation |
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.