medusajs/medusa-agent-skills

mcloud-local

Execute mcloud local build to reproduce a Cloud build on the local machine.

Vedi sorgente
Documento Skill originale

Contenuto dal repository con titoli, esempi, codice, tabelle, link e immagini preservati.

Cloud CLI: Local Command

Execute mcloud local build to run a Cloud build on the local machine, mirroring how Cloud builds the project. Use it to debug build-failed deployments without pushing changes and waiting for a full Cloud build.

Constraints

  • No `--json` flag. local build streams plaintext build output and signals the result through its exit code (0 = success). Do not parse its output as JSON.
  • Requires Docker installed and running, and must run from inside the project's Git repository.
  • Reproduces build-failed (build) failures only — not deployment-failed (runtime) failures. For runtime failures, use mcloud logs --deployment <id>.
  • Available since mcloud CLI v0.1.10.
  • The Docker build cache is disabled by default so variable changes always invalidate the cache; pass --docker-cache to enable it.

Command

local build

Run a Cloud build locally. Infers the root path and build variables from the linked Cloud project and environment. Builds the backend by default; pass --type storefront for the storefront.

bash
mcloud local build \
  --organization <org-id> \
  --project <project-id-or-handle> \
  --environment <environment-handle>

Options:

  • -o/--organization <id> — Organization ID (falls back to active context)
  • -p/--project <id-or-handle> — Project ID or handle (falls back to active context)
  • -e/--environment <handle> — Environment whose variables are used (falls back to active context)
  • -t/--type <backend|storefront> — Build type (default: backend)
  • --root-path <path> — Backend root path relative to the repo root (inferred if omitted; . if no Cloud project found)
  • --storefront-path <path> — Storefront path relative to the repo root, for --type storefront (inferred if omitted)
  • --env-file <path> — Use a local .env file instead of the Cloud environment's variables
  • -v/--var <KEY=VALUE> — Override a single build variable; repeatable
  • --docker-cache — Enable the Docker build cache (default: false)

Output:

  • On success (exit 0), the backend image is tagged <repository-name>:cloud-local-build-<commit-hash>; a storefront build writes its output directory and prints the path.
  • On failure (non-zero exit), the command exits with the failing step's error — debug it as you would a Cloud build.

Reproduce a Build Failure

Check out the same commit the failed deployment built so the local build matches, then route on the exit code:

bash
# Identify the failing deployment and the commit it built
DEPLOYMENT_ID=$(
  mcloud deployments list --json \
    | jq -r '[.[] | select(.backend_status == "build-failed")][0].id'
)
COMMIT=$(mcloud deployments get "$DEPLOYMENT_ID" --json | jq -r '.commit_hash')

git checkout "$COMMIT"

if mcloud local build; then
  echo "Build succeeded locally; failure not reproducible from this commit."
else
  echo "Build failed locally; inspect the streamed output for the failing step."
fi

Once the local build exits 0, push the fix to the tracked branch and start a fresh Cloud build with mcloud environments trigger-build <env>.

Examples

bash
# Reproduce the backend build for the active context
mcloud local build

# Reproduce the storefront build
mcloud local build --type storefront --storefront-path apps/storefront

# Test a build-variable fix without editing code
mcloud local build --var NODE_ENV=production

# Build against a local .env file
mcloud local build --env-file .env

# Reuse the Docker cache for a faster rebuild
mcloud local build --docker-cache
dallo stesso repository

Altri Skills

Tutti gli Skills
medusajs
Ufficiale

building-admin-dashboard-customizations

Load automatically when planning, researching, or implementing Medusa Admin dashboard UI (widgets, custom pages, forms, tables, data loading, navigation). REQUIRED for all admin UI work in ALL modes (planning, implementation, exploration). Contains design patterns, component usage, and data loading patterns that MCP servers don't provide.

installazioni
1
GitHub Stars
218
Aggiornato
9 set
medusajs
Ufficiale

building-storefronts

Load automatically when planning, researching, or implementing Medusa storefront features (calling custom API routes, SDK integration, React Query patterns, data fetching). REQUIRED for all storefront development in ALL modes (planning, implementation, exploration). Contains SDK usage patterns, frontend integration, and critical rules for calling Medusa APIs.

installazioni
1
GitHub Stars
218
Aggiornato
9 set
medusajs
Ufficiale

building-with-medusa

Load automatically when planning, researching, or implementing ANY Medusa backend features (custom modules, API routes, workflows, data models, module links, business logic). REQUIRED for all Medusa backend work in ALL modes (planning, implementation, exploration). Contains architectural patterns, best practices, and critical rules that MCP servers don't provide.

installazioni
1
GitHub Stars
218
Aggiornato
9 set
medusajs
Ufficiale

creating-agents-in-medusa

Use when building an internal admin-facing AI agent in a Medusa project. These agents are operated by merchants and store operators — not customers. Covers data models, module service, agent runtime (tools, system prompt, streamText), streaming API routes (NDJSON), and admin UI chat extensions. Load for any internal agent type: store operations assistant, product audit, cohort analysis, customer service tooling for support staff, etc. Do NOT use for customer-facing agents (storefront chatbots, buyer-side assistants).

installazioni
3
GitHub Stars
217
Aggiornato
9 set