sanity-labs

Port the agent-ready content pattern (markdown routes, content negotiation, sitemap.md, llms.txt) from the agent-ready-content starter into an existing Sanity project. Use when someone wants their site's content served as markdown for AI agents, wants to add llms.txt, wants "Accept: text/markdown" content negotiation, or asks to make their docs or site agent-readable.

Overview of the analytics-informed content operations starter — how performance signal flows from an analytics platform into Sanity as derived signal, and how Studio, GROQ, and Content Agent turn it into editorial action. Trigger on: analytics content ops, performance signal, articlePerformance, triage views, trending rail, content intelligence, stale content, editorial signal.

Build analytics-platform-agnostic sync providers. Core AnalyticsProvider interface, fixture reference implementation, GA4 skeleton, and how to add Amplitude/Heap/Plausible. Trigger on: analytics provider, add analytics source, GA4 integration, fetchMetrics, provider adapter, sync classification, tier tuning.

Automate content improvement with Content Agent (Agent Actions) safely. The queued → staged review pipeline, draft-as-review-gate pattern, instruction design, and the Content Release upgrade. Trigger on: content agent, agent actions, agent.action.generate, triage, agentReview, stale content refresh, SEO drafting, review queue.

Add localized content rendering to a frontend project using the Sanity l10n plugin. The starter includes a complete Next.js reference implementation at apps/frontend/ — use this skill to understand those patterns, adapt them, or scaffold a frontend for a different framework (Astro, SvelteKit). Trigger on: add frontend, localized rendering, i18n routing, locale switcher, fallback content, frontend translation.

Work with a Sanity starter that uses structured content (glossaries, style guides, locale metadata) to make AI translation enterprise-grade. Covers prompt assembly, automated stale detection via Sanity Functions, translation quality evals, and the Agent Actions Translate API. Trigger on: customize glossary, add terminology, translation style guide, run evals, deploy functions, prompt assembly, debug translation, extend l10n plugin, Agent Actions Translate, blueprint deploy, stale detection, pre-translation, field-level translation, field translation, internationalizedArray, field workflow, publish gate, field matrix, per-field translate, field approve, review workflow, translate field action. Complements sanity-best-practices (general i18n) and add-l10n-frontend (frontend rendering).

Add a new scoped AI surface (audience) to a Sanity knowledge base — an Agent Context config that filters which content an agent can see, plus a server-side chat endpoint that holds the token. Use when adding a partner portal, reseller view, regional surface, or any new audience to this starter, or when applying the one-dataset-many-surfaces pattern to an existing Sanity project.

Add an AI chatbot that operates on your Content Lake to an existing Next.js + Sanity project. Use when adding a chat assistant to a site that already has the Studio and a Next.js frontend. Covers dependency installation, API route setup, chat UI components, Studio plugin configuration, and system prompt design.

Content experimentation and A/B testing guidance covering experiment design, hypotheses, metrics, sample size, statistical foundations, CMS-managed variants, and common analysis pitfalls. Use this skill when planning experiments, setting up variants, choosing success metrics, interpreting statistical results, or building experimentation workflows in a CMS or frontend stack.

Structured content modeling guidance for schema design, content architecture, content reuse, references versus embedded objects, separation of concerns, and taxonomies across Sanity and other headless CMSes. Use this skill when designing or refactoring content types, deciding field shapes, debating reusable versus nested content, planning omnichannel content models, or reviewing whether a schema is too page-shaped or presentation-driven.

Build AI agents with structured access to Sanity content via Agent Context. Use when setting up a Sanity-powered chatbot, connecting an AI assistant to Sanity content, or adding client-side tools to an agent. Covers Studio setup, agent implementation, and advanced patterns. Always use this skill when users mention building a chatbot with Sanity, creating an AI assistant for their content, setting up Agent Context MCP, integrating Sanity with Claude/GPT/any LLM, making content searchable by AI, implementing semantic search over Sanity data, or connecting their CMS to an AI agent.

Interactive session to create Instructions field content for a Sanity Agent Context MCP. Use this skill whenever users mention tuning agent context, improving agent responses to Sanity data, configuring MCP instructions, setting up content filters, or when their agent gives wrong results from Sanity queries. Also trigger when users say their agent is confused about schema relationships, needs data-specific guidance, or wants to optimize which content the agent can access.

SEO and AEO best practices for metadata, Open Graph, sitemaps, robots.txt, hreflang, JSON-LD structured data, EEAT, and content optimized for search engines and AI answer surfaces. Use this skill when implementing page SEO, technical SEO, schema markup, international SEO, AI-overview readiness, or improving content for Google, ChatGPT, Perplexity, and similar assistants.

Run tests and report results. Use when you need to verify code changes work correctly.

Set up, configure, and update Schema Mapper — a visual Sanity org/schema explorer using App SDK and React Flow.

Build AI agents with structured access to Sanity content via Agent Context. Use when setting up a Sanity-powered chatbot, connecting an AI assistant to Sanity content, or adding client-side tools to an agent. Covers Studio setup, agent implementation, and advanced patterns. Always use this skill when users mention building a chatbot with Sanity, creating an AI assistant for their content, setting up Agent Context MCP, integrating Sanity with Claude/GPT/any LLM, making content searchable by AI, implementing semantic search over Sanity data, or connecting their CMS to an AI agent.

Install and wire sanity-plugin-studio-tour into an existing Sanity Studio: add tourPlugin to chosen workspaces, choose schemaTypeName(s) (isolating tours when workspaces share a dataset), patch custom desk structures so the Guided Tour type is browsable, author a starter published tour, and verify selectors against the running Studio. Use when adding guided product tours to a Sanity Studio, or reproducing the install in a new project.

Miriad platform reference: execute (JavaScript tool chaining — primary surface for multi-step work), list_tools/document_tool (discover tools), workers (cheap fast sub-agents — use by default), board filesystem with optimistic locking, plan system (specs + tasks with CAS), sandboxes (shell, git, tunnels, GPU), datasets (GROQ queries, real-time listeners), board apps (HTML served as iframes with window.__miriad), secrets (auto-redact, transfer_secret, 15min TTL), environment vars, GitHub (gh CLI, App + PAT modes), skills, custom MCP servers, stdio MCPs (run any MCP server from a sandbox via mcpcli), cross-thread bridging, long-term memory, web search, browser automation., embedded LLM functions (reason/comprehend for inline data processing)