spec-creation
npx machina-cli add skill a5c-ai/babysitter/spec-creation --openclawSpec Creation
Overview
Creates comprehensive feature specifications by first deeply researching the codebase, then generating structured specifications with requirements, acceptance criteria, architecture decisions, and phased implementation plans.
Research Phase
- Analyze project structure and module organization
- Identify existing patterns and conventions
- Map dependencies and integration points
- Review existing tests for testing patterns
- Document technical constraints
Specification Components
Scope and Non-Goals
Clear boundaries on what the feature does and does not include.
Functional Requirements
Detailed requirements with unique identifiers for tracking.
Acceptance Criteria
Testable, measurable criteria for each requirement.
Architecture Decisions
Decision records with rationale and alternatives considered.
Implementation Plan
Phased approach ordered by dependency, not priority.
Risk Analysis
Identified risks with probability, impact, and mitigation strategies.
API Contracts and Data Models
Interface definitions and data model schemas.
Test Strategy
Mapping of unit, integration, and E2E tests to requirements.
Output
Specifications are saved to docs/specs/{feature}.md for reference by the execution workflow.
When to Use
/spec:create [feature]slash command- Before starting a new feature implementation
- When planning complex multi-module changes
Processes Used By
claudekit-spec-workflow(create mode)
Source
git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/claudekit/skills/spec-creation/SKILL.mdView on GitHub Overview
Spec Creation analyzes the codebase to produce comprehensive feature specifications. It documents requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis to guide implementation.
How This Skill Works
First, it conducts a research phase to map project structure, patterns, dependencies, and tests. Then it generates a structured spec saved to docs/specs/{feature}.md, including API contracts, data models, test strategy, and a phased implementation plan with risk mitigation.
When to Use It
- Before starting a new feature implementation with /spec:create [feature] to bootstrap the spec
- When planning complex multi-module changes that require clear dependencies
- To clearly define scope, non-goals, and traceable requirements with unique IDs
- To document Architecture Decisions with rationale and alternatives
- To set up a test strategy and risk analysis before coding begins
Quick Start
- Step 1: Run /spec:create [feature] to bootstrap the spec
- Step 2: Research the codebase to map structure, patterns, and tests
- Step 3: Review docs/specs/{feature}.md and fill in requirements, criteria, architecture decisions, and risk analysis
Best Practices
- Begin with a codebase survey: map structure, conventions, and tests
- Clearly define Scope and Non-Goals before drafting requirements
- Create functional requirements with unique identifiers for traceability
- Record Architecture Decisions with rationale and alternatives
- Plan implementation in dependency-ordered phases and note risks
Example Use Cases
- Spec for adding a new OAuth-based login flow
- Spec for refactoring the order fulfillment workflow across modules
- Spec for introducing a feature flag system and rollout plan
- Spec for migrating a service API and updating client contracts
- Spec for implementing centralized error handling and tracing
