**Purpose**: Provide deep knowledge about organizing software development commands into phased workflows for parallel execution and clear dependency management.
/plugin marketplace add vanman2024/dev-lifecycle-marketplace/plugin install foundation@dev-lifecycle-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
scripts/generate-workflow-doc.pyPurpose: Provide deep knowledge about organizing software development commands into phased workflows for parallel execution and clear dependency management.
Philosophy: Software development commands should be organized into distinct phases that can be:
Why Phases Matter:
Phase 1: Foundation (Always first, no dependencies)
Phase 2: Planning (Requires: Foundation complete)
Phase 3: Implementation (Requires: Planning + Foundation)
Phase 4: Quality (Can run parallel with late Implementation)
Phase 5: Deployment (Requires: Quality passed)
Phase 6: Iteration (Ongoing, throughout process)
Foundation Indicators:
init, setup, detect, validate, env, structure/foundation:init-structure, /foundation:env-checkPlanning Indicators:
wizard, spec, architecture, decide, roadmap, plan/planning:wizard, /planning:architectureImplementation Indicators:
add, create, integrate, build, generate/nextjs-frontend:add-component, /fastapi-backend:add-endpointQuality Indicators:
test, validate, security, performance, quality/testing:test, /quality:validate-codeDeployment Indicators:
deploy, prepare, cicd, validate, monitor/deployment:deploy, /deployment:prepareIteration Indicators:
enhance, refactor, adjust, sync, improve/iterate:enhance, /iterate:refactorFoundation → Planning → Implementation → Quality → Deployment
Within Foundation:
Within Implementation:
Quality and Late Implementation:
.claude/project.json (MUST READ FIRST)
docs/architecture/ (If exists)
docs/adr/ (If exists)
specs/ (If exists)
Current file state (File existence checks)
From project.json:
From ADRs:
From architecture docs:
From specs:
From file existence:
Project Overview
Phased Commands
Progress Indicators
Project-Specific Context
Next Steps
Context from ADRs:
Phase Organization:
Phase 1: Foundation
- /foundation:init-structure
- /foundation:github-init
- /foundation:doppler-setup
Phase 2: Planning
- /planning:wizard
- /planning:architecture
- /planning:decide
Phase 3: Implementation (Monolithic)
- /fastapi-backend:init (single service)
- /nextjs-frontend:init
- /supabase:init
- Implement study partner as embedded library (NOT microservice)
Phase 4-6: Standard (Quality, Deployment, Iteration)
Key Insight: Architecture decision (monolithic) directly affects implementation phase.
Slash Command (/foundation:generate-workflow)
↓
Loads THIS SKILL (knowledge about phasing)
↓
Runs Python script (bulk Airtable query)
↓
Uses skill knowledge to organize commands
↓
Outputs workflow markdown
This skill provides:
The slash command applies:
The Python script provides:
When generating a workflow, ensure:
Always include regeneration command in output:
# To regenerate this workflow with latest Airtable data:
/foundation:generate-workflow "Your Tech Stack Name"
This allows users to:
This skill enables intelligent, project-aware workflow generation that respects architecture decisions and enables parallel execution.
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 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 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.