Getting Started
Install Claude Launchpad and score your Claude Code setup in 10 seconds.
Claude Code follows your CLAUDE.md rules about 80% of the time. Hooks run at 100%. Most projects have zero hooks configured. Claude Launchpad fixes that.
Install
npx claude-launchpadOr install globally:
npm i -g claude-launchpadpnpm add -g claude-launchpadyarn global add claude-launchpadClaude Launchpad has 4 CLI commands (init, doctor, eval, memory) and 2 skills (/lp-enhance, /lp-migrate-memory). Memory is optional.
Why hooks matter: CLAUDE.md rules are ~80% reliable. Hooks are 100% enforced. A SessionStart hook that runs cat TASKS.md means Claude sees your tasks at every session start. A PostCompact hook re-surfaces tasks after context compression, keeping work on track.
Recommended Flow
New project
Scaffold
claude-launchpad initGenerates baseline config files in-project (CLAUDE.md, TASKS.md, .claude/settings.json) and creates .claudeignore, .claude/.gitignore, and .claude/rules/conventions.md when missing. It also offers /lp-enhance install (project/global/skip) when not already installed.
Let Claude perfect it
/lp-enhanceInside Claude Code, run the skill. Claude reads your codebase, restructures CLAUDE.md, and fills in architecture, conventions, and guardrails with real content.
Existing project
Fix the structure
claude-launchpad doctor --fixAdds missing hooks/rules/sections, security defaults, and creates /lp-enhance only when no project/global/legacy install already exists. Jumps to ~86%.
Let Claude clean it up
/lp-enhanceInside Claude Code, type /lp-enhance. The fixer appends sections mechanically - the skill has Claude restructure and rewrite CLAUDE.md into clean, project-specific content.
Prove it works
claude-launchpad evalKeep your config healthy
init runs once. Everything else is designed for repeat use as your project evolves.
| When | Run |
|---|---|
| Added dependencies, changed frameworks, modified hooks | doctor --fix |
| Major refactor, new modules, CLAUDE.md feels stale | /lp-enhance |
| Before a release, after config changes, Claude ignoring rules | eval |
| You want cross-session memory with local SQLite + MCP tools | memory |
Your codebase changes. Your config should keep up. Run doctor periodically. If the score drops, --fix and /lp-enhance bring it back.
Who does what
Each tool handles one job. No overlap.
| Responsibility | init | doctor --fix | /lp-enhance | eval | memory |
|---|---|---|---|---|---|
| Detect stack and framework | ✓ | ||||
| Generate CLAUDE.md, TASKS.md, BACKLOG.md | ✓ | ||||
| Generate settings.json and hooks | ✓ | ✓ | |||
| Generate .claudeignore | ✓ | ✓ | |||
| Score config 0-100 | ✓ | ||||
| Fix missing sections, rules, permissions | ✓ | ||||
| Rewrite CLAUDE.md with real project content | ✓ | ||||
| Suggest hooks, MCP servers, path-scoped rules | ✓ | ||||
| Overflow conventions to .claude/rules/ | ✓ | ||||
| Prove Claude follows your rules | ✓ | ||||
| Run sandbox test scenarios | ✓ | ||||
| Persistent cross-session memory | ✓ | ||||
| Memory dashboard, sync, migration | ✓ |
init scaffolds. doctor maintains. /lp-enhance makes it smart. eval proves it works. memory remembers.
Command reference
| Command | Runs |
|---|---|
claude-launchpad init | Locally, free |
claude-launchpad / doctor | Locally, free |
claude-launchpad doctor --fix | Locally, free |
claude-launchpad doctor --watch | Locally, free |
/lp-enhance (skill) | Inside Claude Code |
claude-launchpad eval | Via Claude CLI |
claude-launchpad memory | Locally |
claude-launchpad memory --dashboard | Locally |
claude-launchpad memory push/pull | Via GitHub API |
claude-launchpad memory sync status | Locally |
claude-launchpad memory sync clean | Locally |
Commands marked Locally run offline with zero API calls. Commands marked Via Claude CLI require Claude Code installed and authenticated. Memory is optional.