All skills
davila7 avatar

/building-blog

@a745dee
by Daniel Aviladavila7/claude-code-templates32k stars
3,662

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.

Use this Skill: https://skilld.dev/gh/davila7/claude-code-templates/building-blog

This session only. Nothing lands on disk.

SKILL.md

β‰ˆ102 tokens always: the name and description. β‰ˆ826 when used: this file. β‰ˆ19k more on demand in 2 files.

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 β€” Β§0 intake questionnaire (30+ questions) β†’ Β§1 Project Profile β†’ Β§2–§20 universal spec β†’ checklist. Edit only Β§0 answers and Β§1 per project.
  • blog-image-style-guide.md β€” 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 β€” 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 β€” Next.js version, next-intl, Sanity packages, Tailwind, framer-motion
  • next.config.{ts,js,mjs} β€” existing images.formats, i18n config
  • src/messages/**, src/i18n/**, messages/** β€” current locale set
  • src/app/[locale]/** or app/[locale]/** β€” routing pattern
  • tailwind.config.*, globals.css, design-system files β€” tokens, fonts
  • CLAUDE.md, AGENTS.md, GEMINI.md β€” project conventions and approved overrides
  • Existing sanity-studio/ or studio/ folder
  • app/layout.{tsx,jsx} β€” fonts, analytics, motion config
  • public/brand/**, public/logo* β€” publisher logo
  • sitemap.ts, robots.ts β€” existing routes
  • .env* files β€” names of already-set env vars (do not log secret values)

Record findings as a brief "Detected" list before the questionnaire.

Step 2 β€” Run the intake questionnaire

Open blog-technical-requirements.md and walk through Β§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 Β§1 "Project Profile" (in a project-local copy under docs/blog/, not in the universal source).

Step 3 β€” Produce the high-level plan

Use the plan template at the end of Β§0. One page. Phases, locked-in scope, out-of-scope items, open decisions. Wait for explicit user approval. Do not start coding.

Step 4 β€” Implement against the spec

Follow Β§2–§20 in order. Β§19 (Pass/Fail Checklist) is the definition of done. The image style guide drives Β§20 if AI-generated hero images are in scope.

When NOT to use this skill

  • Static / MDX-only blogs (no CMS) β€” different stack, different patterns
  • High-velocity news publishers β€” sitemap chunking and editor tooling become primary concerns
  • Documentation sites β€” use a docs framework instead
  • Marketing landing pages that aren't really a blog

Source

Maintained at BuildShipGrowRepeat/nextjs-sanity-blog-skill. MIT licensed.

Source: SKILL.md on GitHub

2 warnings2mo3 checks Β· Risk MEDIUM
  • Gen Agent Trust Hub2mo

    The skill automates the setup of a Next.js blog with Sanity CMS, providing a detailed technical specification and a script for generating article hero images. Security analysis detected that the skill reads local environment variable files to pre-fill configuration data, generates and executes a local asset-management script, and processes project files as input for its code generation workflow.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: MEDIUM Β· 1 issue

Signed by skilld at a745dee. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 12 hours ago.

Activeupdated 4 months ago
risk
safe
source
community
date_added
2026-05-21

README badge

README badge for davila7/claude-code-templates/building-blog