Publish your stack to Cables (automated)
Install a skill or read the field note below to see how we apply this pattern in real Claude Code projects.
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.json`, no fiddling with PRs. Run this command to install a skill and start from a working baseline instead of rebuilding the setup from scratch.
Files this command writes (1 file)
.claude/skills/publish-your-stack/SKILL.md← artifact/SKILL.md
Skill installed. In Claude Code, say 'publish my stack' to start the automated flow.
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.json, no fiddling with PRs.
One command to install
npx -y frenxt-cables add publish-your-stack
Then in Claude Code
Just say:
"publish my stack"
The skill activates and walks through:
- Detect your current plugins + skills (reads
claude plugins list,~/.claude/skills/) - Collect metadata — slug, title, purpose, which subset to ship
- Create or use a public GitHub repo for your stack content
- Generate a valid
.cables/stack.jsonfrom your setup - Bundle the skills you want to share (with a privacy check before each one)
- Validate locally with
frenxt stack-publish - Tag a reproducible release (
v0.1.0) - Open the submission PR against
frenxt/cableson your behalf — with the reviewed SHA pinned
You confirm before anything publishes externally. Local validation is mandatory — the skill won't skip it.
What it won't do
- Won't push sensitive skills. Skips any skill containing credentials, internal paths, or obvious company references, and asks before bundling the rest.
- Won't skip validation. If the validator rejects (stale date, undeclared marketplace, typo-squat), the skill stops and helps you fix the root cause — never suggests
--force. - Won't use floating refs. Every install resolves to a tagged version. No
mainpins.
Works well with
stack-fullstack,stack-ai-agent,stack-ux— if you start from one of these and customize, the skill picks up your additions and helps you ship your variantskill-stack-replication— for publishing a full-stack baseline as your own flavor
Why use the skill instead of the CLI path
The manual CLI path is fine if you like doing Git work yourself. The skill collapses 8 steps into a conversation and handles the common mistakes — missing last_verified date, undeclared marketplaces, forgetting to tag — before they become PR-review bounces.
Both paths hit the same review pipeline on merge. Same security bar, same outcomes.
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 10 min. The cable is marked beginner.
How do I install the artifact?
Run npx frenxt-cables add publish-your-stack. 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
Replicate Ragav's stack (skills + plugins + scripts)
Pick the stack that matches what you're building. Each one is a single `npx` command — plugins installed, skills synced, marketplaces configured, no bash scr…
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.