agentleFS
ek33450505ek33450505/claude-agent-team/skills/stack-reference/SKILL.md

stack-reference

Skill8 starsChanged 31 days agoMITView on GitHub

Full tech stack reference and dev command cheatsheet. Load when you need to look up exact package names, commands, or project paths.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Stack Reference

Frontend Libraries (full list)

  • React 19 with Vite 6
  • TypeScript — .tsx / .ts, tsconfig.json
  • Tailwind CSS v4 (via @tailwindcss/vite)
  • shadcn/ui + class-variance-authority + clsx + tailwind-merge
  • Framer Motion for animation
  • React Router v6 for routing
  • TanStack React Query v5 for data fetching
  • Recharts + @nivo for charts/graphs
  • Lucide React for icons
  • Sonner for toasts
  • cmdk for command palette
  • react-resizable-panels for panel layouts

Backend Libraries (full list)

  • Express 5 (Node.js) — API server
  • tsx for TypeScript execution in dev (tsx watch)
  • concurrently to run Vite + Express together

Key Dev Commands

# CAST
cast status          # health dashboard
cast exec            # run cast plan executor
bash tests/run.sh    # run shell tests (isolated temp HOME — NEVER 'bats tests/' on real $HOME)
bash install.sh      # reinstall CAST into ~/.claude/

Key Runtime Paths

PurposePath
CAST runtime root~/.claude/
Agent definitions~/.claude/agents/
Hook scripts~/.claude/scripts/
Agent memory~/.claude/agent-memory-local/
Plans output~/.claude/plans/
CAST SQLite DB~/.claude/cast.db
CAST event log~/.claude/cast/events/
Agent status~/.claude/agent-status/
Audit / logs~/.claude/logs/
CAST CLI~/.local/bin/cast

Download now (ZIP)

Does it work?

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

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.