square-automation
Automate Square tasks via Rube MCP (Composio): payments, orders, invoices, locations. Always search tools first for current schemas.
What this skill does
# Square Automation via Rube MCP Automate Square payment processing, order management, and invoicing through Composio's Square toolkit via Rube MCP. ## Prerequisites - Rube MCP must be connected (RUBE_SEARCH_TOOLS available) - Active Square connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `square` - 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 `square` 3. If connection is not ACTIVE, follow the returned auth link to complete Square OAuth 4. Confirm connection status shows ACTIVE before running any workflows ## Core Workflows ### 1. List and Monitor Payments **When to use**: User wants to view payment history or check payment status **Tool sequence**: 1. `SQUARE_LIST_PAYMENTS` - Retrieve payments with optional filters [Required] 2. `SQUARE_CANCEL_PAYMENT` - Cancel a pending payment if needed [Optional] **Key parameters**: - `begin_time` / `end_time`: RFC 3339 timestamps for date range filtering - `sort_order`: 'ASC' or 'DESC' for chronological ordering - `cursor`: Pagination cursor from previous response - `location_id`: Filter payments by specific location **Pitfalls**: - Timestamps must be RFC 3339 format (e.g., '2024-01-01T00:00:00Z') - Pagination required for large result sets; follow `cursor` until absent - Only pending payments can be cancelled; completed payments require refunds - `SQUARE_CANCEL_PAYMENT` requires exact `payment_id` from list results ### 2. Search and Manage Orders **When to use**: User wants to find orders by criteria or update order details **Tool sequence**: 1. `SQUARE_LIST_LOCATIONS` - Get location IDs for filtering [Prerequisite] 2. `SQUARE_SEARCH_ORDERS` - Search orders with filters [Required] 3. `SQUARE_RETRIEVE_ORDER` - Get full details of a specific order [Optional] 4. `SQUARE_UPDATE_ORDER` - Modify order state or details [Optional] **Key parameters**: - `location_ids`: Array of location IDs to search within (required for search) - `query`: Search filter object with date ranges, states, fulfillment types - `order_id`: Specific order ID for retrieve/update operations - `cursor`: Pagination cursor for search results **Pitfalls**: - `location_ids` is required for SEARCH_ORDERS; get IDs from LIST_LOCATIONS first - Order states include: OPEN, COMPLETED, CANCELED, DRAFT - UPDATE_ORDER requires the current `version` field to prevent conflicts - Search results are paginated; follow `cursor` until absent ### 3. Manage Locations **When to use**: User wants to view business locations or get location details **Tool sequence**: 1. `SQUARE_LIST_LOCATIONS` - List all business locations [Required] **Key parameters**: - No required parameters; returns all accessible locations - Response includes `id`, `name`, `address`, `status`, `timezone` **Pitfalls**: - Location IDs are required for most other Square operations (orders, payments) - Always cache location IDs after first retrieval to avoid redundant calls - Inactive locations may still appear in results; check `status` field ### 4. Invoice Management **When to use**: User wants to list, view, or cancel invoices **Tool sequence**: 1. `SQUARE_LIST_LOCATIONS` - Get location ID for filtering [Prerequisite] 2. `SQUARE_LIST_INVOICES` - List invoices for a location [Required] 3. `SQUARE_GET_INVOICE` - Get detailed invoice information [Optional] 4. `SQUARE_CANCEL_INVOICE` - Cancel a scheduled or unpaid invoice [Optional] **Key parameters**: - `location_id`: Required for listing invoices - `invoice_id`: Required for get/cancel operations - `cursor`: Pagination cursor for list results - `limit`: Number of results per page **Pitfalls**: - `location_id` is required for LIST_INVOICES; resolve via LIST_LOCATIONS first - Only SCHEDULED, UNPAID, or PARTIALLY_PAID invoices can be cancelled - CANCEL_INVOICE requires the invoice `version` to prevent race conditions - Cancelled invoices cannot be uncancelled ## Common Patterns ### ID Resolution **Location name -> Location ID**: ``` 1. Call SQUARE_LIST_LOCATIONS 2. Find location by name in response 3. Extract id field (e.g., 'L1234ABCD') ``` **Order lookup**: ``` 1. Call SQUARE_SEARCH_ORDERS with location_ids and query filters 2. Extract order_id from results 3. Use order_id for RETRIEVE_ORDER or UPDATE_ORDER ``` ### Pagination - Check response for `cursor` field - Pass cursor value in next request's `cursor` parameter - Continue until `cursor` is absent or empty - Use `limit` to control page size ### Date Range Filtering - Use RFC 3339 format: `2024-01-01T00:00:00Z` - For payments: `begin_time` and `end_time` parameters - For orders: Use query filter with date_time_filter - All timestamps are in UTC ## Known Pitfalls **ID Formats**: - Location IDs are alphanumeric strings (e.g., 'L1234ABCD') - Payment IDs and Order IDs are longer alphanumeric strings - Always resolve location names to IDs before other operations **Versioning**: - UPDATE_ORDER and CANCEL_INVOICE require current `version` field - Fetch the resource first to get its current version - Version mismatch returns a 409 Conflict error **Rate Limits**: - Square API has per-endpoint rate limits - Implement backoff for bulk operations - Pagination should include brief delays for large datasets **Response Parsing**: - Responses may nest data under `data` key - Money amounts are in smallest currency unit (cents for USD) - Parse defensively with fallbacks for optional fields ## Quick Reference | Task | Tool Slug | Key Params | |------|-----------|------------| | List payments | SQUARE_LIST_PAYMENTS | begin_time, end_time, location_id, cursor | | Cancel payment | SQUARE_CANCEL_PAYMENT | payment_id | | Search orders | SQUARE_SEARCH_ORDERS | location_ids, query, cursor | | Get order | SQUARE_RETRIEVE_ORDER | order_id | | Update order | SQUARE_UPDATE_ORDER | order_id, version | | List locations | SQUARE_LIST_LOCATIONS | (none) | | List invoices | SQUARE_LIST_INVOICES | location_id, cursor | | Get invoice | SQUARE_GET_INVOICE | invoice_id | | Cancel invoice | SQUARE_CANCEL_INVOICE | invoice_id, version | ## When to Use This skill is applicable to execute the workflow or actions described in the overview. ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.