spec-creation skill
Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
Is the spec-creation skill safe?
Clean: nothing in its files matched our rules. We read 2 files in the folder on 2026-09-28.
No findings.
Install the spec-creation skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/a5c-ai/babysitter.git /tmp/babysitter mkdir -p ~/.claude/skills cp -r /tmp/babysitter/library/methodologies/claudekit/skills/spec-creation ~/.claude/skills/spec-creation
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
- 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)
More skills from a5c-ai/babysitter
- Aadversarial-reviewFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
- Aagent-boosterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
- Aagent-coordinationCoordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
- Aagent-dispatch
- Aanti-driftHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
- Aarchitecture-design
- Aarchitecture-patternsSystem and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
- Aassimilate-popular-workflowsThis skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
- Aaudit-trail
- AbabysitOrchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
- Ababysit-babysitter-issuesThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
- Abehavior-contractBug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.