kennetvnkennetvn/nextcore-skills/llms.txt

nextcore-skills

llms.txt4 starsChanged 2 days agoMITView on GitHub

Claude Code plugin marketplace with three plugins distilled from a production product built and run by AI coding agents: nextcore-design (UI), nextcore-dev (frontend ↔ backend contract), nextcore-workflow (running agents). Agents: read AGENTS.md first — it routes "is this useful?" (measure, then recommend), "install it" (one command per agent harness) and "use it on this task" (size the task, open one file).

Create a free account to mount

Files

llms.txt

# nextcore-skills

> Claude Code plugin marketplace with three plugins distilled from a production product built and run by AI coding
> agents: nextcore-design (UI), nextcore-dev (frontend ↔ backend contract), nextcore-workflow (running agents).

Agents: read AGENTS.md first — it routes "is this useful?" (measure, then recommend), "install it" (one command per
agent harness) and "use it on this task" (size the task, open one file).

## Start here
- [AGENTS.md](AGENTS.md): evaluate → install → use, for any AI coding agent
- Measure + recommend: `npx -y -p github:kennetvn/nextcore-skills nextcore measure` · measure + install what fits: `… nextcore all --agent <claude|cursor|codex|gemini|copilot|windsurf|generic>`
- Found an improvement while using them? AGENTS.md §6 — ask the person, post from their account, anonymised
- [README](README.md): overview for people

## Cases
- [cases/](cases/README.md): production incidents and measurement traps, one file each (Symptom · Cause · Fix · How to catch it · Rule), indexed by layer and stack; [taxonomy](cases/taxonomy.json)

## Contributing
- [CONTRIBUTING.md](CONTRIBUTING.md): what goes where, how to make each kind, what gets closed

## Plugins
- [nextcore-design](plugins/nextcore-design/README.md): size → product discovery → draw → critique → build → validate; slop-check, token-audit, design-card, design-review, spec-check (references: product-discovery, validation)
- [nextcore-dev SKILL](plugins/nextcore-dev/skills/nextcore-dev/SKILL.md): field map → API contract → UI state signals; auth, data, jobs, ops
- [nextcore-workflow SKILL](plugins/nextcore-workflow/skills/nextcore-workflow/SKILL.md): diagnose before patch, evidence, parallel agents, living docs

## nextcore-dev references
- [api-contract](plugins/nextcore-dev/skills/nextcore-dev/references/api-contract.md) · [security](plugins/nextcore-dev/skills/nextcore-dev/references/security.md) · [data](plugins/nextcore-dev/skills/nextcore-dev/references/data.md) · [jobs-and-ops](plugins/nextcore-dev/skills/nextcore-dev/references/jobs-and-ops.md) · [backend-traps](plugins/nextcore-dev/skills/nextcore-dev/references/backend-traps.md) · [stacks](plugins/nextcore-dev/skills/nextcore-dev/references/stacks.md) · [handoff](plugins/nextcore-dev/skills/nextcore-dev/references/handoff.md) · [desktop-apps](plugins/nextcore-dev/skills/nextcore-dev/references/desktop-apps.md)

## nextcore-workflow references
- [task-sizing](plugins/nextcore-workflow/skills/nextcore-workflow/references/task-sizing.md) · [enforcement-tiers](plugins/nextcore-workflow/skills/nextcore-workflow/references/enforcement-tiers.md) · [diagnose-before-patch](plugins/nextcore-workflow/skills/nextcore-workflow/references/diagnose-before-patch.md) · [measurement-discipline](plugins/nextcore-workflow/skills/nextcore-workflow/references/measurement-discipline.md) · [parallel-agents](plugins/nextcore-workflow/skills/nextcore-workflow/references/parallel-agents.md) · [autonomy-and-issues](plugins/nextcore-workflow/skills/nextcore-workflow/references/autonomy-and-issues.md) · [multiple-ai-accounts](plugins/nextcore-workflow/skills/nextcore-workflow/references/multiple-ai-accounts.md) · [living-docs](plugins/nextcore-workflow/skills/nextcore-workflow/references/living-docs.md) · [lesson-loop](plugins/nextcore-workflow/skills/nextcore-workflow/references/lesson-loop.md) · [shared-tree-git](plugins/nextcore-workflow/skills/nextcore-workflow/references/shared-tree-git.md) · [shell-traps](plugins/nextcore-workflow/skills/nextcore-workflow/references/shell-traps.md) · [github-workbench](plugins/nextcore-workflow/skills/nextcore-workflow/references/github-workbench.md)
- Machine hygiene: [references/machine-hygiene](plugins/nextcore-workflow/skills/nextcore-workflow/references/machine-hygiene.md)
- Tool: [doc-drift](plugins/nextcore-workflow/skills/nextcore-workflow/scripts/doc-drift.mjs) — re-measure numbers written in docs
- Tool: [github-bootstrap](plugins/nextcore-workflow/skills/nextcore-workflow/scripts/github-bootstrap.mjs) — labels, issue forms, PR template, pinned decision inbox
- Tool: [issue-claim](plugins/nextcore-workflow/skills/nextcore-workflow/scripts/issue-claim.mjs) — claim lock with expiry on an issue, refuses closing with unmoved open items

Download now (ZIP)

In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free