install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/automaker/skills/feature-intake" ~/.claude/skills/a5c-ai-babysitter-feature-intake && rm -rf "$T"
manifest:
library/methodologies/automaker/skills/feature-intake/SKILL.mdtags
source content
Feature Intake
Parse and normalize features from text descriptions, images, and screenshots into structured requirements.
Agent
Feature Planner -
automaker-feature-planner
Workflow
- Parse feature title and description text
- Analyze attached images and screenshots for UI requirements
- Extract explicit and implicit requirements
- Categorize feature type (UI, API, infrastructure, refactor, bugfix)
- Estimate initial complexity
- Extract acceptance criteria
Inputs
- Project nameprojectName
- Feature object with id, title, description, attachmentsfeature
Outputs
- Parsed feature with extracted requirements, type, complexity, and acceptance criteria
Process Files
- Stage 1automaker-feature-pipeline.js
- Phase 1automaker-orchestrator.js