Agent skill
rulebook-task-create
Create a new Rulebook task with standardized directory structure. Use when starting a new feature, breaking change, or architectural work that needs spec-driven planning.
Install this agent skill to your Project
npx add-skill https://github.com/hivellm/rulebook/tree/main/skills/rulebook-task-create
SKILL.md
rulebook_task_create
Create a new Rulebook task with full directory structure.
Input Schema
| Parameter | Type | Required | Description |
|---|---|---|---|
taskId |
string | Yes | Task ID in kebab-case (e.g., add-auth-system) |
Usage
await mcp.rulebook_task_create({ taskId: "add-auth-system" });
Response
{
"success": true,
"taskId": "add-auth-system",
"message": "Task add-auth-system created successfully"
}
Created Structure
rulebook/tasks/add-auth-system/
├── .metadata.json # Status: pending
├── proposal.md # Why + What Changes + Impact
├── tasks.md # Simple checklist items only
├── design.md # Technical design (optional)
└── specs/
└── <module>/
└── spec.md # SHALL/MUST requirements
When to Use
- Starting a new feature or capability
- Planning a breaking change
- Architecture changes requiring specs
- Any work that needs structured planning
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
DAG Workflow
Maintain a clean dependency graph (DAG) to prevent circular dependencies and ensure maintainable architecture.
Documentation Rules
All documentation in English. Root README concise, detailed docs in `/docs`.
Quality Enforcement
These rules are NON-NEGOTIABLE and MUST be followed without exception.
Rulebook Task Management
Spec-driven task management for features and breaking changes with OpenSpec-compatible format
Agent Automation
Mandatory workflow that AI agents MUST execute after EVERY implementation.
C
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
Didn't find tool you were looking for?