Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Freshservice ITSM tasks via Rube MCP (Composio): create/update tickets, bulk operations, service requests, and outbound emails. Always search tools first for current schemas.
.claude/skills/freshservice-automation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✓→✓ | = Same ✓ | — | — |
| case-11 | ✗→✗ | = Same ✗ | — | — |
| case-21 | ✗→✗ | = Same ✗ | — | — |
| case-10 | ✗→✗ | = Same ✗ | — | — |
Automate Freshservice IT Service Management operations through Composio's Freshservice toolkit via Rube MCP.
RUBE_MANAGE_CONNECTIONS with toolkit freshserviceRUBE_SEARCH_TOOLS first to get current tool schemasGet 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.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit freshserviceWhen to use: User wants to find, list, or search for tickets
Tool sequence:
FRESHSERVICE_LIST_TICKETS - List tickets with optional filtering and pagination Required]FRESHSERVICE_GET_TICKET - Get detailed information for a specific ticket Optional]Key parameters for listing:
filter: Predefined filter ('all_tickets', 'deleted', 'spam', 'watching')updated_since: ISO 8601 timestamp to get tickets updated after this timeorder_by: Sort field ('created_at', 'updated_at', 'status', 'priority')order_type: Sort direction ('asc' or 'desc')page: Page number (1-indexed)per_page: Results per page (1-100, default 30)include: Additional fields ('requester', 'stats', 'description', 'conversations', 'assets')Key parameters for get:
ticket_id: Unique ticket ID or display_idinclude: Additional fields to includePitfalls:
updated_since to retrieve older ticketsinclude value consumes additional API creditspage is 1-indexed; minimum value is 1per_page max is 100; default is 30When to use: User wants to log a new incident or request
Tool sequence:
FRESHSERVICE_CREATE_TICKET - Create a new ticket Required]Key parameters:
subject: Ticket subject line (required)description: HTML description of the ticket (required)status: Ticket status - 2 (Open), 3 (Pending), 4 (Resolved), 5 (Closed) (required)priority: Ticket priority - 1 (Low), 2 (Medium), 3 (High), 4 (Urgent) (required)email: Requester's email address (provide either email or requester_id)requester_id: User ID of the requestertype: Ticket type ('Incident' or 'Service Request')source: Channel - 1 (Email), 2 (Portal), 3 (Phone), 4 (Chat), 5 (Twitter), 6 (Facebook)impact: Impact level - 1 (Low), 2 (Medium), 3 (High)urgency: Urgency level - 1 (Low), 2 (Medium), 3 (High), 4 (Critical)Pitfalls:
subject, description, status, and priority are all requiredemail or requester_id must be provided to identify the requesterWhen to use: User wants to update multiple tickets at once
Tool sequence:
FRESHSERVICE_LIST_TICKETS - Find tickets to update Prerequisite]FRESHSERVICE_BULK_UPDATE_TICKETS - Update multiple tickets Required]Key parameters:
ids: Array of ticket IDs to update (required)update_fields: Dictionary of fields to update (required)Pitfalls:
When to use: User wants to create a ticket by sending an outbound email notification
Tool sequence:
FRESHSERVICE_CREATE_TICKET_OUTBOUND_EMAIL - Create ticket with email notification Required]Key parameters:
email: Requester's email address (required)subject: Email subject / ticket subject (required)description: HTML email body contentstatus: Ticket status (2=Open, 3=Pending, 4=Resolved, 5=Closed)priority: Ticket priority (1=Low, 2=Medium, 3=High, 4=Urgent)cc_emails: Array of CC email addressesemail_config_id: Email configuration ID for the sender addressname: Requester namePitfalls:
email_config_id determines which email address the notification appears to come fromWhen to use: User wants to submit a service catalog request
Tool sequence:
FRESHSERVICE_CREATE_SERVICE_REQUEST - Create a service request for a catalog item Required]Key parameters:
item_display_id: Display ID of the catalog item (required)email: Requester's email addressquantity: Number of items to request (default: 1)custom_fields: Custom field values for the service item formparent_ticket_id: Display ID of a parent ticket (for child requests)Pitfalls:
item_display_id can be found in Admin > Service Catalog > item URL (e.g., /service_catalog/items/1)| Code | Status | |------|--------| | 2 | Open | | 3 | Pending | | 4 | Resolved | | 5 | Closed |
| Code | Priority | |------|----------| | 1 | Low | | 2 | Medium | | 3 | High | | 4 | Urgent |
page (1-indexed) and per_page (max 100) parameterspage by 1 each requestper_page1. Call FRESHSERVICE_LIST_TICKETS with updated_since='2024-01-01T00:00:00Z'
2. Optionally add order_by='updated_at' and order_type='desc'
3. Paginate through resultsNumeric Codes:
Date Filtering:
updated_since parameter for older ticketsRate Limits:
include option consumes additional API creditsResponse Parsing:
data or data.data| Task | Tool Slug | Key Params | |------|-----------|------------| | List tickets | FRESHSERVICE_LIST_TICKETS | filter, updated_since, page, per_page | | Get ticket | FRESHSERVICE_GET_TICKET | ticket_id, include | | Create ticket | FRESHSERVICE_CREATE_TICKET | subject, description, status, priority, email | | Bulk update | FRESHSERVICE_BULK_UPDATE_TICKETS | ids, update_fields | | Outbound email ticket | FRESHSERVICE_CREATE_TICKET_OUTBOUND_EMAIL | email, subject, description | | Service request | FRESHSERVICE_CREATE_SERVICE_REQUEST | item_display_id, email, quantity |
This skill is applicable to execute the workflow or actions described in the overview.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 6 counted toward the lift figure. The other 17 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 6 comparable cases. 5 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.