Skip to content
Automation
Skill

/zendesk-automation

Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.

From plugin
lihongwei-cn
5200 skills1 agent
Install
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill zendesk-automation --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/zendesk-automation

Context preview

The summary Claude sees to decide when to auto-load this skill.

Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.

SKILL.md

zendesk-automation.SKILL.md
name: zendesk-automation
description: "Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas."
risk: critical
source: community
date_added: "2026-02-27"

Zendesk Automation via Rube MCP

Automate Zendesk operations through Composio's Zendesk toolkit via Rube MCP.

Prerequisites

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Zendesk connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `zendesk`
  • 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 `zendesk` 3. If connection is not ACTIVE, follow the returned auth link to complete Zendesk auth 4. Confirm connection status shows ACTIVE before running any workflows

Core Workflows

1. List and Search Tickets

**When to use**: User wants to view, filter, or search support tickets

**Tool sequence**: 1. `ZENDESK_LIST_ZENDESK_TICKETS` - List all tickets with pagination [Required] 2. `ZENDESK_GET_ZENDESK_TICKET_BY_ID` - Get specific ticket details [Optional]

**Key parameters**:

  • `page`: Page number (1-based)
  • `per_page`: Results per page (max 100)
  • `sort_by`: Sort field ('created_at', 'updated_at', 'priority', 'status')
  • `sort_order`: 'asc' or 'desc'
  • `ticket_id`: Ticket ID for single retrieval

**Pitfalls**:

  • LIST uses `page`/`per_page` pagination, NOT offset-based; check `next_page` in response
  • Maximum 100 results per page; iterate with page numbers until `next_page` is null
  • Deleted tickets are not returned by LIST; use GET_BY_ID which returns status 'deleted'
  • Ticket comments and audits are included in GET_BY_ID but not in LIST responses

2. Create and Update Tickets

**When to use**: User wants to create new tickets or modify existing ones

**Tool sequence**: 1. `ZENDESK_SEARCH_ZENDESK_USERS` - Find requester/assignee [Prerequisite] 2. `ZENDESK_CREATE_ZENDESK_TICKET` - Create a new ticket [Required] 3. `ZENDESK_UPDATE_ZENDESK_TICKET` - Update ticket fields [Optional] 4. `ZENDESK_DELETE_ZENDESK_TICKET` - Delete a ticket [Optional]

**Key parameters**:

  • `subject`: Ticket subject line
  • `description`: Ticket body (for creation; becomes first comment)
  • `priority`: 'urgent', 'high', 'normal', 'low'
  • `status`: 'new', 'open', 'pending', 'hold', 'solved', 'closed'
  • `type`: 'problem', 'incident', 'question', 'task'
  • `assignee_id`: Agent user ID to assign
  • `requester_id`: Requester user ID
  • `tags`: Array of tag strings
  • `ticket_id`: Ticket ID (for update/delete)

**Pitfalls**:

  • Tags on UPDATE REPLACE existing tags entirely; merge with current tags to preserve them
  • Use `safe_update` with `updated_stamp` to prevent concurrent modification conflicts
  • DELETE is permanent and irreversible; tickets cannot be recovered
  • `description` is only used on creation; use REPLY_ZENDESK_TICKET to add comments after creation
  • Closed tickets cannot be updated; create a follow-up ticket instead

3. Reply to Tickets

**When to use**: User wants to add comments or replies to tickets

**Tool sequence**: 1. `ZENDESK_GET_ZENDESK_TICKET_BY_ID` - Get current ticket state [Prerequisite] 2. `ZENDESK_REPLY_ZENDESK_TICKET` - Add a reply/comment [Required]

**Key parameters**:

  • `ticket_id`: Ticket ID to reply to
  • `body`: Reply text content
  • `public`: Boolean; true for public reply, false for internal note
  • `author_id`: Author user ID (defaults to authenticated user)

**Pitfalls**:

  • Set `public: false` for internal notes visible only to agents
  • Default is public reply which sends email to requester
  • HTML is supported in body text
  • Replying can also update ticket status simultaneously

4. Manage Users

**When to use**: User wants to find or create Zendesk users (agents, end-users)

**Tool sequence**: 1. `ZENDESK_SEARCH_ZENDESK_USERS` - Search for users [Required] 2. `ZENDESK_CREATE_ZENDESK_USER` - Create a new user [Optional] 3. `ZENDESK_GET_ABOUT_ME` - Get authenticated user info [Optional]

**Key parameters**:

  • `query`: Search string (matches name, email, phone, etc.)
  • `name`: User's full name (required for creation)
  • `email`: User's email address
  • `role`: 'end-user', 'agent', or 'admin'
  • `verified`: Whether email is verified

**Pitfalls**:

  • User search is fuzzy; may return partial matches
  • Creating a user with an existing email returns the existing user (upsert behavior)
  • Agent and admin roles may require specific plan features

5. Manage Organizations

**When to use**: User wants to list, create, or manage organizations

**Tool sequence**: 1. `ZENDESK_GET_ALL_ZENDESK_ORGANIZATIONS` - List all organizations [Required] 2. `ZENDESK_GET_ZENDESK_ORGANIZATION` - Get specific organization [Optional] 3. `ZENDESK_CREATE_ZENDESK_ORGANIZATION` - Create organization [Optional] 4. `ZENDESK_UPDATE_ZENDESK_ORGANIZATION` - Update organization [Optional] 5. `ZENDESK_COUNT_ZENDESK_ORGANIZATIONS` - Get total count [Optional]

**Key parameters**:

  • `name`: Organization name (unique, required for creation)
  • `organization_id`: Organization ID for get/update
  • `details`: Organization details text
  • `notes`: Internal notes
  • `domain_names`: Array of associated domains
  • `tags`: Array of tag strings

**Pitfalls**:

  • Organization names must be unique; duplicate names cause creation errors
  • Tags on UPDATE REPLACE existing tags (same behavior as tickets)
  • Domain names can be used for automatic user association

Common Patterns

Pagination

**List endpoints**:

  • Use `page` (1-based) and `per_page` (max 100)
  • Check `next_page` URL in response; null means last page
  • `count` field gives total results

Ticket Lifecycle

new -> open -> pending -> solved -> closed
                  |          ^
                  v          |
Read more
Ships withlihongwei-cn

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

Get the whole plugin
Stats
5
Stars
1
Forks
Maintained
Maintenance
Python
Language
MIT
License
1mo ago
Last commit
4mo ago
Created

Repo: LiHongwei-cn/lihongwei-cn

Other skills on lihongwei-cn.

cheat-on-content
Skill

cheat-on-content

给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…

cheat-bump
Skill

cheat-bump

提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind…

cheat-init
Skill

cheat-init

cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的…

cheat-migrate
Skill

cheat-migrate

把老用户的 .cheat-state.json 升级到当前 schema_version。读 migrations/registry.md 算迁移链,按顺序应用每一步迁移文件。幂等:跑两次结果一样。失败停在中间版本不前进。触发词:"迁移"/"升级 state"/"migrate"/"我的 state…

cheat-persona
Skill

cheat-persona

从复盘评论数据派生 / 刷新账号的受众画像,写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分",persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号,cheat-score-blind…