Replicate Ragav's stack (skills + plugins + scripts)
Install a skill or read the field note below to see how we apply this pattern in real Claude Code projects.
Pick the stack that matches what you're building. Each one is a single `npx` command — plugins installed, skills synced, marketplaces configured, no bash scripts. Run this command to install a skill and start from a working baseline instead of rebuilding the setup from scratch.
Files this command writes (21 files)
.claude/skills/replicate-frenxt-stack/SKILL.md← artifact/SKILL.md.claude/commands/replicate-frenxt-stack.md← artifact/commands/replicate-frenxt-stack.md.claude/stacks/frenxt/install-category-plugins.sh← artifact/scripts/install-category-plugins.sh.claude/stacks/frenxt/sync-category-skills-to-profiles.sh← artifact/scripts/sync-category-skills-to-profiles.sh.claude/stacks/frenxt/categories/skills-developer-workflow-systems.txt← artifact/categories/skills-developer-workflow-systems.txt.claude/stacks/frenxt/categories/skills-reasoning-frameworks.txt← artifact/categories/skills-reasoning-frameworks.txt.claude/stacks/frenxt/categories/skills-domain-playbooks.txt← artifact/categories/skills-domain-playbooks.txt.claude/stacks/frenxt/categories/plugins-developer-workflow-systems.txt← artifact/categories/plugins-developer-workflow-systems.txt.claude/stacks/frenxt/categories/plugins-reasoning-frameworks.txt← artifact/categories/plugins-reasoning-frameworks.txt.claude/stacks/frenxt/categories/plugins-domain-playbooks.txt← artifact/categories/plugins-domain-playbooks.txt.claude/stacks/frenxt/categories/codex-plugins-developer-workflow-systems.txt← artifact/categories/codex-plugins-developer-workflow-systems.txt.claude/stacks/frenxt/categories/codex-plugins-reasoning-frameworks.txt← artifact/categories/codex-plugins-reasoning-frameworks.txt.claude/stacks/frenxt/categories/codex-plugins-domain-playbooks.txt← artifact/categories/codex-plugins-domain-playbooks.txt.claude/skills/analyse-langsmith-trace/SKILL.md← artifact/skills/analyse-langsmith-trace/SKILL.md.claude/skills/benchmark/SKILL.md← artifact/skills/benchmark/SKILL.md.claude/skills/e2e-review/SKILL.md← artifact/skills/e2e-review/SKILL.md.claude/skills/qa/SKILL.md← artifact/skills/qa/SKILL.md.claude/skills/bugfix-cycle/SKILL.md← artifact/skills/bugfix-cycle/SKILL.md.claude/skills/debug-prompt-caching/SKILL.md← artifact/skills/debug-prompt-caching/SKILL.md.claude/skills/qa-release/SKILL.md← artifact/skills/qa-release/SKILL.md.claude/skills/voice-test/SKILL.md← artifact/skills/voice-test/SKILL.md
Full stack installed — plugins, skills, and skill sync all complete. For selective installs by taxonomy, use the focused cables: `frenxt stack stack-fullstack`, `stack-ai-agent`, or `stack-ux`.
Replicate Ragav's stack
Pick the stack that matches what you're building. Each one is a single npx command — plugins installed, skills synced, marketplaces configured, no bash scripts.
🧱 Full-stack development (Next.js + Vercel)
For typed Next.js apps on Vercel or Netlify — the full shipping loop from scaffold to prod with CI/CD, observability, and release review.
npx -y frenxt-cables stack stack-fullstack --force
Plugins (15 Claude · 3 Codex): superpowers, claude-md-management, claude-code-setup, feature-dev, code-review, code-simplifier, commit-commands, github, security-guidance, frontend-design, vercel, netlify-skills, sentry, posthog, linear · Codex: build-web-apps, vercel, github
Skills: e2e-review
🤖 AI agent development (LangGraph + LangSmith)
For building, debugging, and evaluating multi-step LLM agents. Trace-first debugging, cache forensics, manual eval review.
npx -y frenxt-cables stack stack-ai-agent --force
Plugins (4 Claude): superpowers, claude-md-management, vercel, sentry
Skills: analyse-langsmith-trace, debug-prompt-caching, benchmark
🎨 UX design
For designing, shipping, and validating product UI — distinctive components and browser-QA.
npx -y frenxt-cables stack stack-ux --force
Plugins (3 Claude): frontend-design, vercel, superpowers
Skills: e2e-review, qa, voice-test
🧰 Everything (the full stack)
All 17 Claude plugins, 3 Codex plugins, 8 skills, and the marketingskills marketplace. Use when you want the complete baseline or when you're setting up a generalist workstation.
npx -y frenxt-cables stack skill-stack-replication --force
Plugins (17 Claude · 3 Codex): everything above + skill-creator, netlify-skills, posthog, commit-commands, marketing-skills
Skills (8): analyse-langsmith-trace, benchmark, e2e-review, qa, bugfix-cycle, debug-prompt-caching, qa-release, voice-test
What each command actually does
- Writes the skill files into
.claude/skills/ - Adds any required marketplaces via
claude plugins marketplace add - Installs each Claude plugin via
claude plugins install - Enables Codex plugins in
~/.codex/config.toml - Syncs the skills to every
~/.claude*profile you have - Prints a summary of what installed, what was skipped, what failed
No bash scripts. No two-step flow. One command per stack.
Flags
--dry-run— show what would happen without touching disk or running claude plugins--skip-plugins— only install files + marketplaces--skip-skills— don't sync to~/.claude*/skills/--skip-marketplaces— assume marketplaces are already configured--force— overwrite existing files without prompting
Selective install by taxonomy (advanced)
If you want to layer by the original category taxonomy (developer-workflow-systems · reasoning-frameworks · domain-playbooks), the mono cable still ships the category scripts:
npx -y frenxt-cables add skill-stack-replication
bash .claude/stacks/frenxt/install-category-plugins.sh developer-workflow-systems
bash .claude/stacks/frenxt/sync-category-skills-to-profiles.sh reasoning-frameworks
Most users don't need this. The four stacks above cover 95% of setups.
Quick answers
What do I get from this cable?
You get a skill plus a dated field note that explains how we use it in real Claude Code workflows.
How much time should I budget?
Typical effort is 15 min. The cable is marked intermediate.
How do I install the artifact?
Run npx frenxt-cables add skill-stack-replication. The install block shows the files it writes and any prerequisites before you run it.
How fresh is the guidance?
The cable is explicitly last verified on 2026-04-18, and includes source links for traceability.
Work with FRE|Nxt
We build the production AI systems we write about.
Cables are the field notes. The playbooks come from client engagements — multi-agent systems, RAG pipelines, and LLM cost cuts that ship and hold up in production. If something here maps to a problem on your roadmap, two ways in:
Audit capacity: 5 slots/month · No pitch deck · NDA on request
Publish your stack to Cables (automated)
A skill that walks Claude Code through publishing your Claude stack to the Cables community in one conversation. No manual repo setup, no hand-written `stack…
AI agent dev stack (LangGraph + LangSmith)
For building, debugging, and evaluating multi-step LLM agents. The skills that catch the problems traces-first: cache misses, regression in eval scores, trac…
Full-stack dev stack (Next.js + Vercel)
The plugins and skills you want on day one of a typed Next.js app — from scaffold to prod, with CI/CD, observability, and release review baked in.