Settings file Claude Code
Drop-in, SEO-ready MDX blog and docs for Next.js App Router: server components for the post grid, articles, and a tabbed docs site, plus Claude Code skills that research and write them.
Instructions file
Claude Code instructions for daanvandenbergh/scribekit, covering project: scribekit, directory architecture, web testing, demo dev server and git.
Skill Claude CodeCodex
Write or rewrite a state-of-the-art, thoroughly-researched blog post for the current project's website (MDX), optimized for both classic search and AI answer engines (Google AI Overviews, ChatGPT, Perplexity). Use when the user wants to create/write/draft a new post or article, or…
Skill Claude CodeCodex
Publish a scribekit docs site to GitHub Pages as a static export - whether it already has a Next.js app or is just a bare docs/ /.mdx corpus. It learns the project; SCAFFOLDS the Next.js host app when the corpus has none; patches the config for output: 'export'; writes the deploy workflow; sets siteUrl to the Pages…
Skill Claude CodeCodex
Write, rewrite, reorganize, or deep-verify documentation for the current project's docs site (MDX), sourced entirely from the project's own code so every documented fact, option, default, and code sample is true. Use when the user wants to create/write/draft/document a new docs/reference/guide page…
Skill Claude CodeCodex
Generate polished, on-brand hero images - rendered deterministically from HTML/CSS (no AI image generator) - for a project's blog posts, docs pages, and its README. One skill for all hero work: create or update a single post/page hero, regenerate every post/page hero after a design change, tune the shared gradient…
Instructions file
Claude Code instructions for daanvandenbergh/claudekit, covering project: claudekit, layout, conventions and releasing.
Skill Claude CodeCodex
Persist an agent's memory into a chosen directory as a clean, de-duplicated, agent-readable Markdown store, and keep it organized over time. Memory here is any durable thing worth remembering across sessions - a learned fact, a user preference or working convention, a decision and its rationale, an ongoing project…
Skill Claude CodeCodex
Top-down, whole-system audit of a codebase's DEEP LOGIC - the bugs that live in the SEAMS between modules, not inside any one file. Finds contracts that drift across module boundaries, invariants enforced on one path but broken on a sibling path, cross-cutting responsibilities (deletion cascade, tenant-scope…
Skill Claude CodeCodex
A project-agnostic, WHOLE-PROJECT security audit - the "subscribe to a security firm" skill. It runs the real scanners (osv-scanner for dependency CVEs, gitleaks for secrets in the working tree AND full git history, semgrep for SAST, trivy for IaC), then performs its OWN LLM-driven whole-repository security review (a…
Skill Claude CodeCodex
Hunt untested and under-tested logic in whatever project this runs in and write meticulous, edge-case-exhaustive unit tests until coverage is total. Learns the project's stack, test runner, and house style first, measures real coverage (installing the tool if missing), triages every source file, then writes tests that…
Skill Claude CodeCodex
Run a phased, production-grade audit of a code module - security, code quality, deep call-chain logic, and test coverage - then fix what it finds, verify the build and tests, and emit a versioned audit report (inline by default, or written to a file with --out). Use when the user wants to audit, security-review…
Skill Claude CodeCodex
Audit an entire website for SEO and auto-fix what it finds - crawlability, indexability, canonical/robots/sitemap/redirects/hreflang, titles and meta descriptions, headings, structured data (JSON-LD/Schema.org), Open Graph and Twitter/social cards, image alt, internal linking, Core Web Vitals, E-E-A-T content quality…