⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
building-blog
Use when adding a blog to a Next.js + Sanity site, building a blog section from scratch, integrating Sanity CMS for editorial content, or setting up an SEO-optimized article surface. Triggers on phrases like "add a blog", "build the blog", "create blog section", "set up blog with Sanity", "integrate Sanity CMS", "blog architecture", or any new-blog scoping conversation on a Next.js project.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
// README
Next.js + Sanity Blog (Claude Code skill)
An opinionated, batteries-included spec for adding a blog to a Next.js website backed by Sanity CMS. Built as a Claude Code skill: install it, say "add a blog", and the agent walks 40 intake questions, scans your project, drafts a one-page plan for your approval, and then implements against a ~1100-line technical spec that already covers SEO, i18n, performance, accessibility, AI hero image generation, and a pass/fail checklist.
Aimed at corporate blogs. Organic-search-first. Optional AI authoring with human review inside Sanity Studio.
What you actually get
- A 40-question intake that covers every fork that meaningfully changes the spec: locales, author model, category count, CMS workflow, analytics, consent, AI imagery, comments, search, sharing, dark mode, scheduled publishing, and the rest.
- A one-page plan template the agent fills from your answers and stops at, waiting for explicit sign-off before any code change.
- A 20-section technical spec to implement against: Sanity schema, URL structure, smart 404 for missing-locale slugs, hreflang rules, BlogPosting and FAQPage JSON-LD, OG, Atom feeds, sitemap, performance budgets tighter than Google's "good" baseline, WCAG 2.2 AA targets, font and motion rules, deletion webhook handling.
- A working TypeScript generator for AI hero images via Gemini 3 Pro Image (Nano Banana Pro), with locale-keyed slugs, idempotent re-runs, and a per-project style guide template.
- A pass/fail checklist that is the definition of done.
Install
Two ways.
As a Claude Code plugin (recommended):
/plugin marketplace add BuildShipGrowRepeat/nextjs-sanity-blog-skill
/plugin install building-blog@nextjs-sanity-blog
Manual:
Clone the repo and drop the skill folder into your local Claude skills directory.
git clone https://github.com/BuildShipGrowRepeat/nextjs-sanity-blog-skill.git
cp -R nextjs-sanity-blog-skill/skills/building-blog ~/.claude/skills/
How to use it
Once installed, say one of:
- "add a blog to this project"
- "set up a blog with Sanity"
- "build the blog section"
Claude will:
- Scan your project (
package.json,next.config.*, message files, design tokens,CLAUDE.md, existing Sanity studio folder if any) and pre-fill anything it can detect. - Walk the 40 intake questions, showing recommended defaults so you can move quickly. The agent groups related questions and uses interactive picks where the host environment supports them.
- Hand you a one-page implementation plan and wait for your sign-off.
- Build against the spec, phase by phase, finishing on the pass/fail checklist.
What's in the spec
Three files, each readable on its own:
skills/building-blog/SKILL.md— the orchestrator. Workflow, scan checklist, fallbacks for non-interactive environments.skills/building-blog/blog-technical-requirements.md— the engineering spec. §0 holds the intake questionnaire, §1 is the per-project profile filled from the answers, §2 to §20 is the universal spec that reads from §1, §21 is the pass/fail checklist.skills/building-blog/blog-image-style-guide.md— a brand-tailorable template for AI-generated hero images. The intake sits on top, and the agent helps you populate the topic table and worked examples for your domain.
Stack assumptions
- Next.js, App Router. Tested against 14 and 15; Next.js 16 gotchas are documented inline (async
params, uncachedfetch, Turbopack,stegaoutside draft mode). - Sanity v3. Studio either hosted at
*.sanity.studioor embedded under/studio. next-intlfor i18n on multilingual projects. Single-locale projects skip the i18n section entirely.- Tailwind is assumed but not strictly required. The spec locks Tailwind-style classes in a handful of typography rules only.
If your stack is meaningfully different (Contentful, Payload, MDX-only, Astro, Remix), this skill is the wrong tool for direct execution. The questionnaire structure and the SEO section still work as a checklist. The rest does not transfer cleanly.
What this is not
- Not a docs site generator. Use Nextra, Docusaurus, or Starlight.
- Not for high-velocity news publishers, where sitemap chunking and editorial workflow become primary concerns and this spec gets thin.
- Not a marketing landing page builder dressed up as a blog.
- Not a UI library or design system. It assumes you already have one.
Why this exists
Every time you ask an AI to "add a blog to my Next.js site", you get a slightly different answer. Some answers ship without alt text on hero images. Some include tags by default even though tags will fragment a small archive into thin pages Google ignores. Some forget hreflang on listing pages. Some over-engineer with @sanity/document-internationalization when the site's articles don't even share topics across locales.
This skill is what a careful, opinionated implementation looks like, written down once so you don't relitigate it on every project. The opinions have rationale inline. Where you disagree, override via the §0 intake. That is exactly what §0 is for.
Roadmap (loose)
- Stack adapters as sibling skills: Payload, Contentful, MDX-only.
- Better recommended defaults for FR / DE / ES / IT / PT locale combinations.
- A small examples folder showing the spec applied to a real project (sanitized).
- A short walkthrough video.
Contributing
Issues and PRs welcome. The spec is opinionated on purpose. Specifically interested in:
- Real-world results: "I shipped a blog with this and here is what broke or what I had to change."
- Counter-examples where a default in §2 to §20 is provably wrong for a common case.
- Translations of the questionnaire to other languages so non-English-speaking teams can use it natively.
See CONTRIBUTING.md once added; in the meantime, open an issue first to discuss.
License
MIT. See LICENSE.
Author
Vladimir Terekhov · BuildShipGrowRepeat · attractgroup.com · [email protected]
Keywords for search: next.js sanity blog, claude code skill, claude skill, nextjs sanity cms, blog seo checklist, next-intl blog, nano banana blog images, gemini 3 pro image blog, sanity studio blog, hreflang next.js, blog jsonld blogposting, ai blog generator, opinionated blog spec.
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
skills/building-blog/SKILL.md5.8 KBupstream ↗
--- name: building-blog description: Use when adding a blog to a Next.js + Sanity site, building a blog section from scratch, integrating Sanity CMS for editorial content, or setting up an SEO-optimized article surface. Triggers on phrases like "add a blog", "build the blog", "create blog section", "set up blog with Sanity", "integrate Sanity CMS", "blog architecture", or any new-blog scoping conversation on a Next.js project. --- # Building a Blog (Next.js + Sanity) ## Overview Universal workflow for adding a blog to a Next.js site backed by Sanity CMS. Targets a corporate blog: SEO-first, i18n-ready, performance-budgeted, accessibility-compliant. **SKILL.md is the orchestrator. The spec lives in the two reference files.** ## Files - `blog-technical-requirements.md` — §0 intake questionnaire (30+ questions) → §1 Project Profile → §2–§20 universal spec → checklist. Edit only §0 answers and §1 per project. - `blog-image-style-guide.md` — universal template for AI-generated hero imagery via Gemini 3 Pro Image (Nano Banana Pro). Intake questions on top, aesthetic skeleton in the middle, three example slots at the bottom. ## Workflow ### Step 1 — Scan the host project (before asking anything) Read what's already there. Pre-filling answers from detected values is much better than asking the user. Look for: - `package.json` — Next.js version, `next-intl`, Sanity packages, Tailwind, `framer-motion` - `next.config.{ts,js,mjs}` — existing `images.formats`, i18n config - `src/messages/**`, `src/i18n/**`, `messages/**` — current locale set - `src/app/[locale]/**` or `app/[locale]/**` — routing pattern - `tailwind.config.*`, `globals.css`, design-system files — tokens, fonts - `CLAUDE.md`, `AGENTS.md`, `GEMINI.md` — project conventions and approved overrides - Existing `sanity-studio/` or `studio/` folder - `app/layout.{tsx,jsx}` — fonts, analytics, motion config - `public/brand/**`, `public/logo*` — publisher logo - `sitemap.ts`, `robots.ts` — existing routes - `.env*` files — names of already-set env vars (do not log secret values) Record findings as a brief "Detected" list before the questionnaire. ### Step 1.5 — Fetch the latest docs for the stack you'll touch Spec opinions can drift from upstream reality. Before implementing, pull current docs for the libraries you will actually use on this project. Do not skip this — the spec was last audited at a fixed point in time, and Next.js / Sanity / next-intl ship breaking changes more often than this skill is updated. Use [`context7`](https://context7.com) if it is available in the environment (it is the fastest way to read current library docs); otherwise fall back to the library's official docs site via `WebFetch`. Cross-check against the spec when you reach the matching section. Minimum docs to read for any blog build: - **Next.js** — App Router, `generateStaticParams`, `generateMetadata`, dynamic `params` (sync vs Promise in 15/16), image config, `revalidateTag`, `unstable_cache` deprecation status - **Sanity v3** (`@sanity/client`, `next-sanity`) — `client.fetch` options, draft mode + `stega` rules, `defineQuery`, GROQ projection patterns, image URL builder - **next-intl** (only if multi-locale) — App Router setup, `getTranslations`, `getMessages`, `setRequestLocale`, hreflang patterns - **@portabletext/react** — current component override API, plugin packages - **@sanity/image-url** — params, hotspot/crop behaviour, `auto=format` Also check, just-in-time, when you hit the matching spec section: - **Hero image generator** — Gemini 3 Pro Image (Nano Banana Pro) — current model name, image generation endpoint, supported sizes/aspect ratios, JSON schema for `responseModalities` - **JSON-LD** — Google's [Article structured data](https://developers.google.com/search/docs/appearance/structured-data/article) page for current required fields - **CWV thresholds** — `web.dev` Core Web Vitals page for current LCP/INP/CLS "good" cutoffs If the docs contradict the spec, the docs win. Note the contradiction in the project profile (§1) and proceed against the docs. ### Step 2 — Run the intake questionnaire Open `blog-technical-requirements.md` and walk through §0. - **Claude Code:** use `AskUserQuestion`. Group related questions into single calls (max 4 per call). Pre-fill recommended answers from the scan. - **Codex / CLIs without an interactive picker:** list questions numerically in plain text, ask the user to answer in batches of 5–10. Show recommended answers from the scan. - **Headless / non-interactive:** apply universal defaults to whatever the prompt did not explicitly cover; list every assumption. Write the answers into §1 "Project Profile" (in a project-local copy under `docs/blog/`, not in the universal source). ### Step 3 — Produce the high-level plan Use the plan template at the end of §0. One page. Phases, locked-in scope, out-of-scope items, open decisions. **Wait for explicit user approval. Do not start coding.** ### Step 4 — Implement against the spec Follow §2–§20 in order. §19 (Pass/Fail Checklist) is the definition of done. The image style guide drives §20 if AI-generated hero images are in scope. ## When NOT to use this skill - Static / MDX-only blogs (no CMS) — different stack, different patterns - High-velocity news publishers — sitemap chunking and editor tooling become primary concerns - Documentation sites — use a docs framework instead - Marketing landing pages that aren't really a blog ## Recommended companion skills - `frontend-design` — if the visual identity is unclear or the site is mid-greenfield, brainstorm direction first - `superpowers:brainstorming` — for scope conversations beyond what §0 captures - `superpowers:writing-plans` — to expand the high-level plan into a per-phase implementation plan before codingREADME.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/buildshipgrowrepeat-nextjs-sanity-blog-skill-skills-building-blog.md