skills/rulebook-mcp/SKILL.md
MCP server overview and integration guide. Use this for setup, configuration, and discovering available MCP tools for task and skill management.
npx skillsauth add hivellm/rulebook rulebook-mcpInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The Rulebook MCP server exposes 13 tools for programmatic task and skill management via the Model Context Protocol (stdio transport, JSON-RPC 2.0).
rulebook mcp init
rulebook-mcp
| Tool | Description | Skill Reference |
|------|-------------|-----------------|
| rulebook_task_create | Create a new task with directory structure | See rulebook-task-create skill |
| rulebook_task_list | List tasks with status filtering | See rulebook-task-list skill |
| rulebook_task_show | Show complete task details | See rulebook-task-show skill |
| rulebook_task_update | Update task status | See rulebook-task-update skill |
| rulebook_task_validate | Validate task format | See rulebook-task-validate skill |
| rulebook_task_archive | Archive completed task | See rulebook-task-archive skill |
| rulebook_task_delete | Permanently delete task | See rulebook-task-delete skill |
| Tool | Description | Skill Reference |
|------|-------------|-----------------|
| rulebook_skill_list | List available skills by category | See rulebook-skill-list skill |
| rulebook_skill_show | Show skill details and content | See rulebook-skill-show skill |
| rulebook_skill_enable | Enable a skill in project config | See rulebook-skill-enable skill |
| rulebook_skill_disable | Disable a skill | See rulebook-skill-disable skill |
| rulebook_skill_search | Search skills by query | See rulebook-skill-search skill |
| rulebook_skill_validate | Validate skills configuration | See rulebook-skill-validate skill |
// Task workflow
await mcp.rulebook_task_create({ taskId: "add-auth-system" });
await mcp.rulebook_task_update({ taskId: "add-auth-system", status: "in-progress" });
await mcp.rulebook_task_show({ taskId: "add-auth-system" });
await mcp.rulebook_task_validate({ taskId: "add-auth-system" });
await mcp.rulebook_task_archive({ taskId: "add-auth-system" });
// Skill workflow
await mcp.rulebook_skill_list({ category: "languages" });
await mcp.rulebook_skill_search({ query: "typescript" });
await mcp.rulebook_skill_enable({ skillId: "languages/typescript" });
await mcp.rulebook_skill_validate({});
For Cursor (.cursor/mcp.json):
{
"mcpServers": {
"rulebook": {
"command": "rulebook-mcp",
"args": [],
"env": {}
}
}
}
For Claude Code (.claude/mcp.json):
{
"mcpServers": {
"rulebook": {
"command": "rulebook-mcp",
"args": [],
"env": {}
}
}
}
RULEBOOK_MCP_DEBUG=1 for debug output).rulebook config by walking up directoriesresearch
Create structured analyses with numbered findings, execution plans, and task materialization
research
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
development
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
data-ai
Autonomous AI agent loop for iterative task implementation (@hivehub/rulebook ralph)