Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Generates Mermaid diagrams for visual representation. Triggers: architecture overview, project structure, module diagram, dependency graph, code structure, directory structure.
/plugin marketplace add thkt/claude-config/plugin install complete-workflow-system@thkt-development-workflowsThis skill is limited to using the following tools:
EVALUATIONS.mdscripts/analyze-structure.shscripts/extract-modules.shscripts/generate-mermaid.shAuto-generate architecture documentation from codebase analysis.
| Section | Description |
|---|---|
| Project Overview | Tech stack, framework detection |
| Directory Structure | tree command output |
| Module Composition | Mermaid relationship diagrams |
| Key Components | Classes, functions with statistics |
| Dependencies | External/internal visualization |
| Statistics | File count, line count, etc. |
| Phase | Actions |
|---|---|
| 1. Init | Identify root, detect language/framework |
| 2. Structure | tree command, classify directories |
| 3. Code | tree-sitter-analyzer: classes, functions, imports |
| 4. Dependencies | Parse imports, map relationships |
| 5. Generate | Mermaid diagrams, populate templates |
# Directory structure
tree -L 3 -I 'node_modules|.git|dist|build|__pycache__|.venv' --dirsfirst
# Code structure (per file)
tree-sitter-analyzer {file} --structure --output-format json
# Dependencies - TypeScript/JavaScript
grep -r "^import\|^export" --include="*.ts" --include="*.tsx"
# Dependencies - Python
grep -r "^import\|^from.*import" --include="*.py"
| Error | Resolution |
|---|---|
| Root not found | Use current directory |
| tree-sitter unavailable | Fallback to Grep/Read |
| Large project | Sample top 100 files |
After generation, validate output with:
~/.claude/skills/scripts/validate-markdown.sh {output-file}
Non-blocking (warnings only) - style issues don't block document creation.
/docs:architectureThis 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.