epic-generation
The epic-generation skill converts product requirement documents into detailed technical implementation plans by parsing requirements, documenting architecture decisions using ADR format, specifying technology choices, and mapping internal, external, and cross-team dependencies. Use this when transitioning from product planning to technical execution to ensure architectural alignment and dependency clarity across engineering teams.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/epic-generation && cp -r /tmp/epic-generation/library/methodologies/ccpm/skills/epic-generation ~/.claude/skills/epic-generationSKILL.md
# Epic Generation Transform PRD into a technical implementation plan with architecture decisions and dependency mapping. ## Agent Architect - `architect` ## Workflow 1. Parse PRD and extract structured requirements 2. Define architecture decisions with ADR format 3. Specify technology approach and stack choices 4. Map internal, external, and cross-team dependencies 5. Assemble complete epic document 6. Validate epic covers all PRD requirements ## Inputs - `projectName` - Project name - `featureName` - Feature identifier - `prd` - Finalized PRD from Phase 1 - `existingCodebase` - Codebase analysis for brownfield (optional) ## Outputs - Epic document with architecture, tech approach, dependencies - Architecture Decision Records (ADRs) - Dependency graph - Validation report ## Process Files - `ccpm-epic-planning.js` - Standalone epic planning - `ccpm-orchestrator.js` - Phase 2 of full lifecycle
Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
>-
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.