helpdesk-automation
Automate HelpDesk tasks via Rube MCP (Composio): list tickets, manage views, use canned responses, and configure custom fields. Always search tools first for current schemas.
Install with Tessl CLI
npx tessl i github:Lingjie-chen/MT5 --skill helpdesk-automation71
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
100%
48%Bulk Ticket Export for SLA Audit
Cursor-based ticket pagination
RUBE_SEARCH_TOOLS first
20%
100%
Uses HELPDESK_LIST_TICKETS
100%
100%
Correct silo
100%
100%
sortBy parameter
100%
100%
pageSize within bounds
100%
100%
next.value extracted
0%
100%
next.ID extracted
0%
100%
Both cursor fields passed together
0%
100%
Stops when no cursor
70%
100%
No cursor mixing documented
100%
100%
ISO 8601 cursor awareness
0%
100%
Defensive response parsing
60%
100%
Without context: $0.4919 · 2m 7s · 26 turns · 30 in / 6,925 out tokens
With context: $0.4976 · 1m 59s · 23 turns · 279 in / 6,479 out tokens
100%
82%New Support Team Onboarding: HelpDesk Environment Audit
HelpDesk setup and multi-tool exploration
RUBE_SEARCH_TOOLS first
0%
100%
RUBE_MANAGE_CONNECTIONS call
0%
100%
Auth link handling
0%
100%
ACTIVE status check
0%
100%
Uses HELPDESK_LIST_VIEWS
0%
100%
Uses HELPDESK_LIST_CANNED_RESPONSES
0%
100%
Uses HELPDESK_LIST_CUSTOM_FIELDS
0%
100%
Canned response variables/HTML noted
100%
100%
Custom fields schema extension noted
100%
100%
Views are read-only
0%
100%
Defensive response parsing
60%
100%
No API key for Rube setup
0%
100%
Without context: $0.8313 · 3m 3s · 40 turns · 198 in / 10,904 out tokens
With context: $1.2663 · 4m 43s · 48 turns · 57 in / 16,280 out tokens
93%
54%Spam and Archive Ticket Cleanup Report
Silo filtering and response parsing
RUBE_SEARCH_TOOLS first
0%
0%
silo='spam' query
0%
100%
silo='trash' query
0%
100%
silo='archive' query
0%
100%
Separate queries per silo
100%
100%
Cross-silo independence noted
100%
100%
Rate limit backoff
100%
100%
Ticket IDs as strings
0%
100%
Defensive data parsing
0%
100%
Reasonable page size
100%
100%
Rate limit handling documented
100%
100%
Uses HELPDESK_LIST_TICKETS
0%
100%
Without context: $0.5701 · 2m 3s · 21 turns · 159 in / 6,833 out tokens
With context: $0.4299 · 1m 57s · 19 turns · 24 in / 6,311 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.