Skip to content

davepoon/buildwithclaude / plugins/all-skills/skills/render-automation

render-automation

Verified

Automate Render tasks via Rube MCP (Composio): services, deployments, projects. Always search tools first for current schemas.

FileKindSize
SKILL.mdskill md6.5 KB
---
name: render-automation
description: "Automate Render tasks via Rube MCP (Composio): services, deployments, projects. Always search tools first for current schemas."
requires:
  mcp: [rube]
category: infrastructure-cloud
---

# Render Automation via Rube MCP

Automate Render cloud platform operations through Composio's Render toolkit via Rube MCP.

**Toolkit docs**: [composio.dev/toolkits/render](https://composio.dev/toolkits/render)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Render connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `render`
- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas

## Setup

**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.


1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `render`
3. If connection is not ACTIVE, follow the returned auth link to complete Render authentication
4. Confirm connection status shows ACTIVE before running any workflows

## Core Workflows

### 1. List and Browse Services

**When to use**: User wants to find or inspect Render services (web services, static sites, workers, cron jobs)

**Tool sequence**:
1. `RENDER_LIST_SERVICES` - List all services with optional filters [Required]

**Key parameters**:
- `name`: Filter services by name substring
- `type`: Filter by service type ('web_service', 'static_site', 'private_service', 'background_worker', 'cron_job')
- `limit`: Maximum results per page (default 20, max 100)
- `cursor`: Pagination cursor from previous response

**Pitfalls**:
- Service types must match exact enum values: 'web_service', 'static_site', 'private_service', 'background_worker', 'cron_job'
- Pagination uses cursor-based approach; follow `cursor` until absent
- Name filter is substring-based, not exact match
- Service IDs follow the format 'srv-xxxxxxxxxxxx'
- Default limit is 20; set higher for comprehensive listing

### 2. Trigger Deployments

**When to use**: User wants to manually deploy or redeploy a service

**Tool sequence**:
1. `RENDER_LIST_SERVICES` - Find the service to deploy [Prerequisite]
2. `RENDER_TRIGGER_DEPLOY` - Trigger a new deployment [Required]
3. `RENDER_RETRIEVE_DEPLOY` - Monitor deployment progress [Optional]

**Key parameters**:
- For TRIGGER_DEPLOY:
  - `serviceId`: Service ID to deploy (required, format: 'srv-xxxxxxxxxxxx')
  - `clearCache`: Set `true` to clear build cache before deploying
- For RETRIEVE_DEPLOY:
  - `serviceId`: Service ID
  - `deployId`: Deploy ID from trigger response (format: 'dep-xxxxxxxxxxxx')

**Pitfalls**:
- `serviceId` is required; resolve via LIST_SERVICES first
- Service IDs start with 'srv-' prefix
- Deploy IDs start with 'dep-' prefix
- `clearCache: true` forces a clean build; takes longer but resolves cache-related issues
- Deployment is asynchronous; use RETRIEVE_DEPLOY to poll status
- Triggering a deploy while another is in progress may queue the new one

### 3. Monitor Deployment Status

**When to use**: User wants to check the progress or result of a deployment

**Tool sequence**:
1. `RENDER_RETRIEVE_DEPLOY` - Get deployment details and status [Required]

**Key parameters**:
- `serviceId`: Service ID (required)
- `deployId`: Deployment ID (required)
- Response includes `status`, `createdAt`, `updatedAt`, `finishedAt`, `commit`

**Pitfalls**:
- Both `serviceId` and `deployId` are required
- Deploy statuses include: 'created', 'build_in_progress', 'update_in_progress', 'live', 'deactivated', 'build_failed', 'update_failed', 'canceled'
- 'live' indicates successful deployment
- 'build_failed' or 'update_failed' indicate deployment errors
- Poll at reasonable intervals (10-30 seconds) to avoid rate limits

### 4. Manage Projects

**When to use**: User wants to list and organize Render projects

**Tool sequence**:
1. `RENDER_LIST_PROJECTS` - List all projects [Required]

**Key parameters**:
- `limit`: Maximum results per page (max 100)
- `cursor`: Pagination cursor from previous response

**Pitfalls**:
- Projects group related services together
- Pagination uses cursor-based approach
- Project IDs are used for organizational purposes
- Not all services may be assigned to a project

## Common Patterns

### ID Resolution

**Service name -> Service ID**:
```
1. Call RENDER_LIST_SERVICES with name=service_name
2. Find service by name in results
3. Extract id (format: 'srv-xxxxxxxxxxxx')
```

**Deployment lookup**:
```
1. Store deployId from RENDER_TRIGGER_DEPLOY response
2. Call RENDER_RETRIEVE_DEPLOY with serviceId and deployId
3. Check status for completion
```

### Deploy and Monitor Pattern

```
1. RENDER_LIST_SERVICES -> find service by name -> get serviceId
2. RENDER_TRIGGER_DEPLOY with serviceId -> get deployId
3. Loop: RENDER_RETRIEVE_DEPLOY with serviceId + deployId
4. Check status: 'live' = success, 'build_failed'/'update_failed' = error
5. Continue polling until terminal state reached
```

### Pagination

- Use `cursor` from response for next page
- Continue until `cursor` is absent or results are empty
- Both LIST_SERVICES and LIST_PROJECTS use cursor-based pagination
- Set `limit` to max (100) for fewer pagination rounds

## Known Pitfalls

**Service IDs**:
- Always prefixed with 'srv-' (e.g., 'srv-abcd1234efgh')
- Deploy IDs prefixed with 'dep-' (e.g., 'dep-d2mqkf9r0fns73bham1g')
- Always resolve service names to IDs via LIST_SERVICES

**Service Types**:
- Must use exact enum values when filtering
- Available types: web_service, static_site, private_service, background_worker, cron_job
- Different service types have different deployment behaviors

**Deployment Behavior**:
- Deployments are asynchronous; always poll for completion
- Clear cache deploys take longer but resolve stale cache issues
- Failed deploys do not roll back automatically; the previous version stays live
- Concurrent deploy triggers may be queued

**Rate Limits**:
- Render API has rate limits
- Avoid rapid polling; use 10-30 second intervals
- Bulk operations should be throttled

**Response Parsing**:
- Response data may be nested under `data` key
- Timestamps use ISO 8601 format
- Parse defensively with fallbacks for optional fields

## Quick Reference

| Task | Tool Slug | Key Params |
|------|-----------|------------|
| List services | RENDER_LIST_SERVICES | name, type, limit, cursor |
| Trigger deploy | RENDER_TRIGGER_DEPLOY | serviceId, clearCache |
| Get deploy status | RENDER_RETRIEVE_DEPLOY | serviceId, deployId |
| List projects | RENDER_LIST_PROJECTS | limit, cursor |

---
*Powered by [Composio](https://composio.dev)*
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall