spotlightr-automation
by ComposioHQspotlightr-automation is a Claude skill for automating Spotlightr through Composio Rube MCP. It guides agents to search tools first, verify an active Spotlightr connection, and use current schemas before executing workflows.
Score: 64/100. This is an acceptable but limited directory listing: it gives agents a recognizable trigger and a workable Rube MCP setup/discovery pattern for Spotlightr automation, but directory users should understand that most execution detail is delegated to live tool discovery rather than documented workflows in the repository.
- Valid skill frontmatter clearly declares the `spotlightr-automation` name, description, and required `rube` MCP dependency.
- Prerequisites and setup explain that users need Rube MCP, `RUBE_SEARCH_TOOLS`, and an active Spotlightr connection via `RUBE_MANAGE_CONNECTIONS`.
- The skill explicitly instructs agents to search tools first for current schemas, reducing risk from stale Spotlightr API assumptions.
- Workflow guidance is mostly generic Rube MCP discovery/connection flow, with little evidence of Spotlightr-specific task examples or schemas in the repository excerpt.
- No support files, scripts, references, README, or install command are present beyond the SKILL.md, so adoption depends on live Rube tool discovery.
Overview of spotlightr-automation skill
What spotlightr-automation does
spotlightr-automation is a Claude skill for automating Spotlightr actions through Composio’s Rube MCP server. It is designed for workflows where an AI agent needs to discover the current Spotlightr tool schema, verify an authenticated Spotlightr connection, and then execute actions using Rube MCP tools rather than relying on guessed API parameters.
The core value is not a large script library; the repository contains a focused SKILL.md. Its main differentiator is the operating pattern: search tools first, check the Spotlightr connection, then call the discovered tool with the current schema.
Best-fit users and workflows
This skill is a good fit if you use Claude or another MCP-capable agent to handle Spotlightr work such as video library operations, account-level automation, or repeatable admin tasks exposed through Composio’s Spotlightr toolkit.
It is especially useful for teams that want workflow automation without hand-writing direct Spotlightr API calls. The skill is also a fit when schemas may change, because it explicitly instructs the agent to call RUBE_SEARCH_TOOLS before execution.
What to know before installing
The spotlightr-automation skill depends on Rube MCP being available in your client and on an active Spotlightr connection created through RUBE_MANAGE_CONNECTIONS. If your environment cannot use MCP servers, or if you need offline-only automation, this skill will not be enough by itself.
There are no bundled scripts, reference files, or helper assets in the skill folder. Treat it as an agent procedure for safe tool discovery and execution, not as a standalone Spotlightr automation package.
How to Use spotlightr-automation skill
spotlightr-automation install context
Install the skill from the Composio skills repository in the way your skill-enabled client supports. For Claude-style skill managers, the expected source is:
ComposioHQ/awesome-claude-skills, skill path composio-skills/spotlightr-automation
A typical install command may look like:
npx skills add ComposioHQ/awesome-claude-skills --skill spotlightr-automation
After installation, add Rube MCP as a server in your client configuration using:
https://rube.app/mcp
Then verify that RUBE_SEARCH_TOOLS is available. Use RUBE_MANAGE_CONNECTIONS with toolkit spotlightr and complete the returned authorization flow until the connection status is ACTIVE.
Inputs the skill needs to work well
The skill performs best when your request names the exact Spotlightr outcome, the target objects, and any constraints. A weak prompt is:
“Update my Spotlightr videos.”
A stronger prompt is:
“Use spotlightr-automation to find the current Rube MCP tools for Spotlightr, confirm my Spotlightr connection is active, then look for a tool that can update metadata for videos in project X. Before executing, show the discovered tool name, required fields, and any missing values.”
That prompt improves output quality because it forces tool discovery, connection validation, schema inspection, and a pause before mutation.
Recommended workflow pattern
Use this sequence for most spotlightr-automation usage:
- Ask the agent to call
RUBE_SEARCH_TOOLSfor the specific Spotlightr task. - Review the returned tool slugs, schemas, execution plan, and pitfalls.
- Confirm the Spotlightr connection with
RUBE_MANAGE_CONNECTIONS. - Provide missing IDs, titles, folders, project names, or filter criteria.
- Ask the agent to execute only after it has mapped your request to the discovered schema.
- For destructive or bulk operations, require a preview or confirmation step.
The most important repository file to read first is SKILL.md. It contains the prerequisite checks, Rube MCP setup guidance, tool discovery requirement, and core workflow pattern.
Practical prompt template
Use this template for reliable spotlightr-automation for Workflow Automation:
“Use the
spotlightr-automationskill. First callRUBE_SEARCH_TOOLSfor this use case:[describe task]. Then check my Spotlightr connection withRUBE_MANAGE_CONNECTIONS. Do not guess fields. Show the selected tool, required inputs, optional inputs, and any missing information. After I confirm, execute the tool and summarize what changed.”
This is better than asking for “Spotlightr automation” broadly because it aligns the agent with the skill’s main safety rule: current schemas must come from Rube MCP discovery.
spotlightr-automation skill FAQ
Is spotlightr-automation a direct Spotlightr API client?
No. It is a skill that guides an agent to use Composio’s Spotlightr toolkit through Rube MCP. The agent should discover available tools with RUBE_SEARCH_TOOLS and use those returned schemas instead of inventing direct API calls.
Can beginners use this skill?
Yes, if they are comfortable connecting an MCP server and completing an OAuth-style app connection flow. Beginners should start with connection verification and read SKILL.md before attempting bulk changes. The skill’s workflow is simple, but MCP setup is still required.
How is this better than an ordinary prompt?
An ordinary prompt may cause the agent to guess available Spotlightr actions or parameters. The spotlightr-automation skill explicitly requires tool discovery first, which makes it more reliable when Composio tool schemas change or when the agent does not know which Spotlightr operations are currently exposed.
When should I not use this skill?
Do not use it if you need a complete local automation framework, prebuilt scripts, scheduled jobs, or non-MCP execution. Also avoid it for high-risk bulk edits unless your prompt requires a dry run, schema review, and explicit confirmation before execution.
How to Improve spotlightr-automation skill
Improve inputs before running spotlightr-automation
Better inputs produce better automation. Include the business goal, the Spotlightr object type, known IDs or names, selection criteria, and whether the operation is read-only or mutating.
Instead of:
“Organize my videos.”
Use:
“Find tools for listing Spotlightr videos and updating video metadata. I want to identify videos with titles containing ‘Webinar 2024’ and add a consistent tag if the tool supports tagging. Show the schema before making changes.”
Common failure modes to prevent
The main failure mode is skipping tool discovery and assuming a tool name or input shape. Prevent this by explicitly saying “call RUBE_SEARCH_TOOLS first.” Another common issue is running a write operation without verifying the active Spotlightr connection. Require RUBE_MANAGE_CONNECTIONS before execution.
For bulk actions, ask the agent to process a small sample first, summarize the intended changes, and wait for approval.
Iterate after the first output
After the agent returns discovered tools, refine the request using the actual schema. If a required field is missing, provide it directly rather than asking the agent to infer it. If several tools seem relevant, ask for a comparison based on required inputs, risk level, and whether the operation is reversible.
A good second prompt is:
“Use the discovered schema only. Map each field to the value I provided, list unresolved fields, and propose the safest execution order.”
Extend the skill for team workflows
If your team uses spotlightr-automation regularly, consider adding internal runbooks outside the upstream skill: approved task templates, naming conventions, confirmation rules for bulk updates, and examples of successful prompts. The upstream skill is intentionally minimal, so your biggest improvement will come from documenting your own Spotlightr object naming, permission model, and review process.