Skills for Real Engineers. Straight from my .agents directory.
feature-intake
Agent skill froma5c-ai/babysitter
Parse and normalize features from text descriptions, images, and screenshots into structured requirements.
How to install feature-intake
npx skills add a5c-ai/babysitter# or add only this skill to Claude Code: copy the folder
library/methodologies/automaker/skills/feature-intake/
# into
~/.claude/skills/feature-intake/ (all projects)
.claude/skills/feature-intake/ (one project)
1# Feature Intake23Parse and normalize features from text descriptions, images, and screenshots into structured requirements.45## Agent6Feature Planner - `automaker-feature-planner`78## Workflow91. Parse feature title and description text102. Analyze attached images and screenshots for UI requirements113. Extract explicit and implicit requirements124. Categorize feature type (UI, API, infrastructure, refactor, bugfix)135. Estimate initial complexity146. Extract acceptance criteria1516## Inputs17- `projectName` - Project name18- `feature` - Feature object with id, title, description, attachments1920## Outputs21- Parsed feature with extracted requirements, type, complexity, and acceptance criteria2223## Process Files24- `automaker-feature-pipeline.js` - Stage 125- `automaker-orchestrator.js` - Phase 1
Excerpt shown under the repository's MIT license.
More skills in babysitter
Similar skill repositories
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
