skills/rulebook-task-validate/SKILL.md
Validate a Rulebook task format and structure against OpenSpec requirements. Use before archiving or to verify task quality.
npx skillsauth add hivellm/rulebook rulebook-task-validateInstall 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.
Validate a Rulebook task's format and structure.
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| taskId | string | Yes | Task ID to validate |
await mcp.rulebook_task_validate({ taskId: "add-auth-system" });
{
"valid": true,
"errors": [],
"warnings": ["Consider adding more scenarios to specs/auth/spec.md"]
}
proposal.md must exist with ## Why section (min 20 characters)tasks.md must contain only checklist itemsSHALL or MUST keywords#### headers (4 hashtags)research
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)