claudekit / tools / claude-code-setup
[ Plugin · Productivity ]

Claude Code Setup

Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.

$ /plugin install claude-code-setup copy

Anthropic official marketplace plugin

What it does

Claude Code exposes five extensibility surfaces — hooks, skills, MCP servers, subagents, and slash commands — each with dozens of viable options. Picking the right combination from cold is hard.

This plugin scans the codebase read-only and surfaces the top 1–2 automations per category, grounded in real signals from package.json, framework choices, database, CI, and issue tracker references — rather than the generic shortlist a blog post would suggest.

How it works

Phase 1 — codebase analysis. The skill inspects package.json, pyproject.toml, Cargo.toml, go.mod, framework imports, dependency lists, and existing .claude/ / CLAUDE.md configuration. It captures language and framework, frontend and backend stack, database, external APIs (Stripe, OpenAI, AWS SDKs, etc.), testing setup, CI/CD, and issue tracker references.

Phase 2 — recommendations. Based on what it found, it generates ranked recommendations across all five categories. By default it returns the top 1–2 per category to avoid overwhelming the output. Ask for a specific category to widen it to 3–5.

What it recommends

CategoryExample recommendations
MCP serverscontext7 (live docs), Playwright (browser/UI testing), Supabase / PostgreSQL MCP, GitHub MCP, Linear MCP
Skillsfrontend-design, commit, feature-dev, plus custom skill templates scoped to the codebase
HooksPostToolUse auto-format, lint on edit, block sensitive files, run tests pre-commit
SubagentsSpecialized reviewers — security, performance, accessibility
Slash commands/test, /pr-review, /explain and similar quick workflows

Each recommendation comes with a short rationale tying it back to a specific signal in the codebase, so you can adopt the full list or cherry-pick.

Use cases

  1. First time on a fresh project — Run recommend automations for this project to get a full five-category diagnostic in one pass.
  2. Going deeper on one category — Ask “recommend more MCP servers for this codebase” to expand a single category to 3–5 candidates.
  3. Switching codebases — Re-run the diagnostic on a new repo instead of copying your previous setup wholesale, so unused automations don’t tag along.
§ 5

See also

same category · curated
[01]
[Tool] Paperclip · Open-source orchestration for teams of AI agents. A Node.js server and React UI where you bring your own agents, assign goals, and track work and costs from one dashboard.
tool · claudekit.io / tools / paperclip
[02]
[Plugin] AI Job Search · The job search that runs on your machine. An AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews — all driven by slash commands, running locally. Fork it and own it.
tool · claudekit.io / tools / ai-job-search
[03]
[Tool] Career-Ops · Open-source AI job search that runs locally in your AI coding CLI: scan job portals, score listings A-F, tailor your CV, track applications. It generates ATS-optimized resumes and cover letters, and never auto-submits.
tool · claudekit.io / tools / career-ops
§ 6

Frequently Asked Questions

frequently asked
§ 6.1
What is Claude Code Setup?
An Anthropic official marketplace plugin. It scans the current codebase read-only and recommends the top 1–2 automations in each of five categories: MCP servers, skills, hooks, subagents, and slash commands.
§ 6.2
Where does it run?
Claude Code only. It is not available in the desktop app or other IDEs.
§ 6.3
How do I install it?
In Claude Code, run `/plugin install claude-code-setup`. It ships in the Anthropic official marketplace (claude-plugins-official), so no extra marketplace registration is required.
§ 6.4
How do I invoke it?
In natural language. Phrases like "recommend automations for this project", "help me set up Claude Code", or "what hooks should I use?" activate the skill, which then scans the codebase.
§ 6.5
Does it create or modify files automatically?
No. The skill is read-only — it analyzes the codebase and outputs recommendations. Users implement the recommendations themselves or ask Claude separately to help build them.
§ 6.6
Who is this for?
Users adopting Claude Code on a new project, or re-evaluating automations on an existing one. It pays off most when you are unsure which of the available hooks, skills, or MCP servers actually fit your codebase.