Feature Intake
Scannednpx machina-cli add skill a5c-ai/babysitter/feature-intake --openclawFeature 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
projectName- Project namefeature- 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 1automaker-orchestrator.js- Phase 1
Source
git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/automaker/skills/feature-intake/SKILL.mdView on GitHub Overview
Feature Intake standardizes how new features are captured by extracting explicit and implicit requirements from text descriptions and attached images. It also categorizes the feature type (UI, API, infrastructure, refactor, bugfix), estimates initial complexity, and outputs acceptance criteria for downstream planning.
How This Skill Works
Inputs include projectName and a feature object with id, title, description, and attachments. The workflow parses the feature text, analyzes attached images for UI requirements, extracts explicit and implicit requirements, assigns a feature type, and estimates initial complexity, then outputs a parsed feature with requirements, type, complexity, and acceptance criteria. The process is implemented in automaker-feature-pipeline.js (Stage 1) and automaker-orchestrator.js (Phase 1).
When to Use It
- When a new feature is proposed from product docs or emails and needs formalization.
- When a feature includes UI mockups or screenshots that reveal UI requirements.
- When explicit acceptance criteria are missing or unclear.
- When backlog items require an early technology/type categorization (UI, API, infrastructure, refactor, bugfix).
- When preparing features for handoff to engineering with initial effort estimates.
Quick Start
- Step 1: Provide projectName and a feature object with id, title, description, and attachments.
- Step 2: Run the automaker feature pipeline to parse text, analyze images, categorize type, and estimate complexity.
- Step 3: Review the parsed feature output (requirements, type, complexity, acceptance criteria) and adjust as needed.
Best Practices
- Provide a clear feature title and a detailed description to anchor parsing.
- Include at least one attachment or screenshot to capture UI requirements.
- Ensure acceptance criteria are stated or implied in the description for extraction.
- Verify feature type categorization with stakeholders to prevent misclassification.
- Review the initial complexity estimate with the team to calibrate planning.
Example Use Cases
- Feature: Redesigned login flow with two-factor authentication, UI mockups in attachments, and new API endpoints for token refresh.
- Feature: Dashboard widget to display quarterly revenue with UI adjustments inferred from screenshots.
- Feature: API rate limiting and circuit breaker added to protect services, with acceptance criteria extracted from specs document.
- Feature: Refactor authentication service to a new microservice architecture, leveraging attachment notes for migration steps.
- Feature: Bugfix to image thumbnail rendering in gallery based on UI screenshots showing incorrect scaling.