feature-intake
Feature Intake processes raw feature requests from text, images, and screenshots into structured requirements by extracting explicit and implicit needs, categorizing feature type, estimating complexity, and defining acceptance criteria. Use this when converting informal feature descriptions into standardized specification documents ready for development planning.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/feature-intake && cp -r /tmp/feature-intake/library/methodologies/automaker/skills/feature-intake ~/.claude/skills/feature-intakeSKILL.md
# Feature Intake Parse and normalize features from text descriptions, images, and screenshots into structured requirements. ## Agent Feature Planner - `automaker-feature-planner` ## Workflow 1. Parse feature title and description text 2. Analyze attached images and screenshots for UI requirements 3. Extract explicit and implicit requirements 4. Categorize feature type (UI, API, infrastructure, refactor, bugfix) 5. Estimate initial complexity 6. Extract acceptance criteria ## Inputs - `projectName` - Project name - `feature` - Feature object with id, title, description, attachments ## Outputs - Parsed feature with extracted requirements, type, complexity, and acceptance criteria ## Process Files - `automaker-feature-pipeline.js` - Stage 1 - `automaker-orchestrator.js` - Phase 1
Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
Architect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement