Interactively scaffold a new Sanity Schema Document or Object type using best-practice templates. Use when user wants to create new content types.
/plugin marketplace add sanity-io/agent-toolkit/plugin install sanity-plugin@sanity-agent-toolkitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
templates/document.tstemplates/object.tstemplates/singleton.tsThis skill guides the user to create a new Sanity document type, ensuring it follows the "Data > Presentation" philosophy and strict typing rules.
Discovery
ls -R src/schemaTypes (or schemas) to understand the project structure.src/schemaTypes/index.ts (or equivalent) to see how schemas are registered.Input Gathering
Drafting (Template Based)
templates/document.ts (or templates/object.ts / templates/singleton.ts).{{name}} and {{title}} placeholders in the template with the user's input.icon import is preserved or updated to a relevant icon from @sanity/icons.singleton.ts, remind user that singletons require Desk Structure configuration (see template comments). Offer to help set up the structure.Execution
src/schemaTypes/documents/).src/schemaTypes/index.ts.Verification
npm run typegen (if available) to verify syntax.This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.