0-8 point scoring system for feature complexity assessment. Auto-invoke when assessing complexity, determining architecture advisor involvement, or scoring features. Do NOT load for implementation or code review tasks.
Automatically scores feature complexity 0-8 based on scope, patterns, integration, and breaking changes. Triggers when assessing complexity or architecture needs, but skips for implementation tasks.
/plugin marketplace add L-Sypniewski/claude-code-toolkit/plugin install development-workflow@claude-code-toolkitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Automated 0-8 point scoring system for determining feature complexity and architecture advisor involvement.
| Score | Criteria |
|---|---|
| 0 | Single file modification |
| 1 | 2-4 files |
| 2 | 5+ files or new directory structure |
Signals:
| Score | Criteria |
|---|---|
| 0 | Using existing patterns |
| 1 | Minor pattern variation |
| 2 | New architectural pattern |
Signals:
| Score | Criteria |
|---|---|
| 0 | Isolated feature |
| 1 | Integration with 1-2 systems |
| 2 | Integration with 3+ systems or external APIs |
Signals:
| Score | Criteria |
|---|---|
| 0 | Backward compatible |
| 1 | Minor breaking changes (internal) |
| 2 | Major breaking changes or public API modifications |
Signals:
| Total Score | Action |
|---|---|
| 0-4 | Proceed with senior-engineer only |
| 5-8 | Invoke technical-architecture-advisor |
Complexity Assessment:
- File Scope: X/2
- Pattern Introduction: X/2
- Integration Complexity: X/2
- Breaking Changes: X/2
- TOTAL: X/8
Architecture Advisor: [Will be involved | Not needed]
Feature: "Add CSV export button to user list"
Feature: "Add dark mode toggle with persistence"
Feature: "Real-time notifications with WebSockets"
Feature: "Replace REST API with GraphQL"
When uncertain, score higher - Better to involve architecture advisor unnecessarily than miss issues.
Look for keywords:
Consider implicit complexity:
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.