polygon-automation
by ComposioHQpolygon-automation helps agents run Polygon toolkit actions through Composio Rube MCP by discovering live tool schemas, checking connections, and executing safer workflows.
This skill scores 65/100, which makes it acceptable but limited for directory listing. Directory users get enough evidence to understand that it automates Polygon through Composio/Rube MCP and how an agent should start, but they should expect a schema-discovery wrapper rather than a rich set of concrete Polygon automation workflows.
- Valid skill frontmatter clearly names the skill and declares the required Rube MCP dependency for triggering.
- Prerequisites and setup explain how to connect Rube MCP, manage the Polygon connection, and verify ACTIVE status before running workflows.
- The skill repeatedly instructs agents to call RUBE_SEARCH_TOOLS first, which is useful for current schemas and reduces stale-tool guesswork.
- No support files, scripts, references, or README are present beyond SKILL.md, so adoption depends entirely on the inline instructions and external Composio toolkit docs.
- The workflow is mostly a generic Rube MCP discovery/connection pattern rather than concrete Polygon task playbooks, so agents may still need to infer operation-specific steps after tool search.
Overview of polygon-automation skill
What polygon-automation does
polygon-automation is a Claude skill for running Polygon toolkit actions through Composio’s Rube MCP server. Its main value is not a fixed list of Polygon commands; it teaches the agent to discover the currently available Polygon tools first, check the active connection, then execute with the latest schema returned by Rube.
Use this skill when you want an AI assistant to automate Polygon-related operations without manually copying tool schemas into every prompt. It is best suited for users already working in an MCP-capable client where Rube tools such as RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS are available.
Best-fit users and workflows
The polygon-automation skill fits operators, builders, and analysts who need repeatable Polygon actions inside an AI workflow: checking available toolkit capabilities, preparing a valid tool call, handling connection state, and adapting to schema changes. It is especially useful when your desired Polygon task is clear but you do not know the exact Composio/Rube tool slug or input fields.
It is less useful as a standalone tutorial for Polygon itself. The repository provides a compact execution pattern, not domain education, sample business workflows, or helper scripts.
Key differentiator: schema-first automation
The most important instruction in this skill is: always call RUBE_SEARCH_TOOLS before executing Polygon operations. That matters because MCP tool names, fields, auth requirements, and known pitfalls can change. A generic prompt may guess a tool name or invent parameters; polygon-automation is designed to make the agent inspect the live Rube schema first and build the workflow from that result.
Adoption requirements to check first
Before installing or relying on this skill, confirm three things:
- Your AI client supports MCP servers.
- Rube MCP is configured with
https://rube.app/mcp. - The Polygon toolkit connection can be activated through
RUBE_MANAGE_CONNECTIONS.
The skill has a single source file, SKILL.md, with no bundled scripts, examples, references, or local test harness. That keeps installation lightweight, but it also means your prompts must provide the actual task context.
How to Use polygon-automation skill
polygon-automation install and setup path
Install the skill from the Composio skill collection:
npx skills add ComposioHQ/awesome-claude-skills --skill polygon-automation
Then configure Rube MCP in your client by adding:
https://rube.app/mcp
After setup, verify that RUBE_SEARCH_TOOLS is available. Next, ask the assistant to run RUBE_MANAGE_CONNECTIONS with toolkit polygon. If the connection is not ACTIVE, follow the authentication link returned by Rube and re-check the status before attempting any Polygon action.
Inputs the skill needs from you
For good polygon-automation usage, do not prompt with only “use Polygon” or “run this.” Give the assistant enough information to search the right tools and validate the action. Useful inputs include:
- The exact Polygon task you want completed.
- The object or data you are working with.
- Required filters, identifiers, date ranges, symbols, addresses, or other parameters.
- Output format: summary, table, JSON, saved note, or follow-up action.
- Safety limits: read-only, confirm before execution, do not place orders, do not modify records.
A stronger prompt looks like:
“Use polygon-automation for Workflow Automation. First discover the current Polygon tools through Rube. I need to retrieve recent data for [identifier] from [date range], return a concise table, and do not perform any write or paid action without confirmation.”
Recommended workflow after installation
A reliable polygon-automation guide flow is:
- Read
composio-skills/polygon-automation/SKILL.md. - Confirm Rube MCP is connected.
- Search tools with
RUBE_SEARCH_TOOLSusing your specific use case, not a vague phrase. - Check the Polygon connection with
RUBE_MANAGE_CONNECTIONS. - Ask the assistant to show the selected tool slug, required fields, and planned call before execution.
- Execute only after the schema and connection state are clear.
- Review returned pitfalls or warnings from Rube before chaining additional actions.
Because the repository includes only SKILL.md, that file is the main authority. There are no extra rules/, scripts/, or references/ folders to inspect.
Prompt pattern for better results
Use a prompt that forces discovery, planning, and confirmation:
“Invoke the polygon-automation skill. Search Rube tools for: [specific task]. Use the returned schema only; do not guess fields. Check whether the Polygon connection is active. If active, propose the exact tool call with parameters and explain any missing inputs. Wait for my confirmation before running anything that changes state.”
This works better than a normal request because it aligns with the skill’s schema-first design and reduces hallucinated tool calls.
polygon-automation skill FAQ
Is polygon-automation a Polygon tutorial?
No. polygon-automation is an automation wrapper for using the Polygon toolkit through Rube MCP. It does not teach Polygon concepts in depth, and it does not include worked domain examples. Its value is operational: tool discovery, connection checking, schema-aware execution, and safer prompting.
When should I not use polygon-automation?
Do not use it if you cannot connect Rube MCP, if your client does not support MCP, or if you need offline/local automation. It is also a poor fit when you need a prebuilt business workflow with validation scripts, tests, and example outputs; the repository only supplies the skill instructions.
How is this better than an ordinary prompt?
An ordinary prompt may ask the model to infer Polygon capabilities from memory. The polygon-automation skill tells the agent to query RUBE_SEARCH_TOOLS first, use the live schema, and check RUBE_MANAGE_CONNECTIONS. That makes it more reliable for changing tool APIs and reduces incorrect parameter guesses.
Is polygon-automation beginner-friendly?
It is beginner-friendly only if your MCP environment is already working. The skill’s instructions are short and clear, but beginners may still need help configuring MCP, activating the Polygon connection, and interpreting Rube’s returned schemas.
How to Improve polygon-automation skill
Improve polygon-automation inputs
The fastest way to improve polygon-automation results is to make the initial request specific. Replace “get Polygon data” with a task statement that includes target entity, time window, required fields, output format, and whether the operation must be read-only.
Good input reduces unnecessary tool searches and helps the assistant choose a relevant Rube use case query.
Watch for common failure modes
Common issues include inactive Polygon connections, vague tool discovery queries, missing required fields, and the assistant trying to guess schemas instead of using Rube’s returned fields. If a run fails, ask the assistant to restate:
- The searched use case.
- The selected tool slug.
- Required versus optional schema fields.
- The exact missing input.
- Any known pitfalls returned by Rube.
Iterate after the first output
After the first result, refine the workflow rather than starting over. Ask for narrower filters, a different output shape, validation against returned metadata, or a second tool search if the first tool did not match the task. For multi-step workflows, require the assistant to pause between steps and summarize what was learned before making another call.
Strengthen the skill locally if needed
If your team uses polygon-automation often, create your own companion notes outside the upstream skill: approved prompt templates, known Polygon tasks, preferred output formats, and internal safety rules. The upstream skill is intentionally minimal, so local usage patterns can add the examples and guardrails your team needs without changing the core schema-first workflow.