Execute mcloud environments commands to list, get, create, delete, redeploy, or trigger builds for Cloud environments. Use when managing environment lifecycle, redeploying after variable changes, or starting new builds from source.
npx skills add https://github.com/medusajs/medusa-agent-skills --skill mcloud-environments
Execute mcloud environments commands to manage environment lifecycle and deployments.
type via environments get --json before attempting delete in automation.--yes for destructive operations (delete) in non-interactive contexts.redeploy vs trigger-build are not interchangeable — choose the right one based on where the fix is.List all environments in a project.
mcloud environments list --organization <org-id> --project <project-id-or-handle> --json
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)--json — Output as JSONRetrieve a single environment by its ID or handle.
mcloud environments get <environment-id-or-handle> --organization <org-id> --project <project-id-or-handle> --json
Arguments:
environment — Environment ID or handle (required)Options:
-o/--organization <id>, -p/--project <id-or-handle>, --jsonCreate a new long-lived environment.
mcloud environments create \
--organization <org-id> \
--project <project-id-or-handle> \
--name "Staging" \
--branch develop \
--json
Options:
-o/--organization <id>, -p/--project <id-or-handle>-n/--name <name> — Environment name (required)-b/--branch <branch> — Git branch to track (required)--custom-subdomain <subdomain> — Optional custom subdomain--json — Output as JSONDelete an environment. Cannot delete production environments.
mcloud environments delete <environment-id-or-handle> \
--organization <org-id> \
--project <project-id-or-handle> \
--yes
Arguments:
environment — Environment ID or handle (required)Options:
-o/--organization <id>, -p/--project <id-or-handle>-y/--yes — Skip confirmation prompt (required in non-interactive mode)--json — Output as JSONRe-run an existing build for the active deployment. Use when the fix is environment-side (variable change, infra issue) — does NOT start a new build.
mcloud environments redeploy <environment-id-or-handle> \
--organization <org-id> \
--project <project-id-or-handle> \
--json
Arguments:
environment — Environment ID or handle (required)Options:
-o/--organization <id>, -p/--project <id-or-handle>, --json> Requires the environment to have an active deployment. If it doesn't, use trigger-build first.
Start a new build from the tracked branch. Use when the fix is committed code — creates a new deployment.
mcloud environments trigger-build <environment-id-or-handle> \
--organization <org-id> \
--project <project-id-or-handle> \
--json
Arguments:
environment — Environment ID or handle (required)Options:
-o/--organization <id>, -p/--project <id-or-handle>, --json| Command | When to use |
|---------|-------------|
| redeploy | Fix is environment-side (variable change, infra config) — reruns existing build |
| trigger-build | Fix is in source code on the tracked branch — starts a new build |
# List all environments
mcloud environments list --json
# Get environment details and check type before deleting
mcloud environments get staging --json | jq '{id, name, type, status}'
# Create a new environment tracking the develop branch
mcloud environments create --name "Staging" --branch develop --json
# Delete a non-production environment
mcloud environments delete staging --yes
# Redeploy after a variable change
mcloud environments redeploy production --json
# Trigger a fresh build from source
mcloud environments trigger-build production --json
# Find environment handles by name
mcloud environments list --json \
| jq -r '.[] | select(.name == "Production") | .handle'
# Verify new build started
mcloud deployments list --environment production --limit 5 --json \
| jq '.[] | {id, backend_status, updated_at}'
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take medusajs/mcloud-environments from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.