agentsclimarketplace
Sign in

Zendesk

Skill jdrhyne/agent-skills/skills/zendesk

Manage Zendesk tickets, users, and support workflows through the Zendesk API. Use when searching tickets, updating support state, checking users, or exporting queue data.From its SKILL.md

Install
npx -y skills add jdrhyne/agent-skills --skill zendesk

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

2.3 KB, 338 tokens by cl100k_base, as published. Nobody here has run it

Zendesk

Manage Zendesk tickets, users, and support workflows through the authenticated Zendesk API.

When to Use

  • search tickets or support history
  • create or update tickets
  • inspect user details
  • export queue data for analysis
  • summarize current support state

Setup

Use these environment variables:

  • ZENDESK_SUBDOMAIN
  • ZENDESK_EMAIL
  • ZENDESK_TOKEN

Build the Zendesk auth context from those variables and confirm access before trying ticket operations.

Workflow Rules

  1. Search before creating a ticket to avoid duplicates.
  2. Use views or targeted search instead of listing entire queues.
  3. Add internal notes when changing status or ownership.
  4. Confirm destructive or customer-visible actions before sending them.
  5. Respect Zendesk rate limits during bulk work.

Common Operations

  • Search tickets by status, priority, assignee, or subject before creating a new one.
  • Create tickets with a clear subject, customer-visible comment, and correct priority.
  • Update status with an internal note that explains what changed and why.
  • Look up users by email before editing ownership, organization, or requester fields.
  • Export queue data only when the user explicitly asked for a saved report.

Safety Boundaries

  • Do not read credentials from ad hoc files, memory stores, or chat history; use only the documented environment variables.
  • Do not close, merge, delete, or publicly reply to tickets without explicit confirmation.
  • Do not export ticket or user data to files unless the user asked for a saved artifact.
  • Do not send Zendesk data to any service other than the authenticated Zendesk API.

What ships with it: 6 files

11.2 KB alongside SKILL.md

.clawhub/

Gives 0 of the 12 instructions most customer support skills give in 338 tokens

Counted across 123 of the 124 authors here whose files we hold, read 2026-08-07

  • Call RUBE_SEARCH_TOOLS first to get current schemasin 12 of 123, across 4 files
  • Confirm connection status is ACTIVE before running workflowsin 12 of 123, across 4 files
  • Stop and ask for clarification if required inputs are missingin 9 of 123, across 2 files
  • Call RUBE_MANAGE_CONNECTIONS with the helpdesk toolkitin 9 of 123, across 2 files
  • Use both timestamp and ID for cursor navigationin 8 of 123, across 1 file
  • Implement backoff on 429 responsesin 8 of 123, across 1 file
  • Parse response data defensively with fallback patternsin 8 of 123, across 1 file
  • Use this skill only when the task clearly matches the scopein 8 of 123, across 1 file
  • Pass a JSON file as the positional argumentin 7 of 123, across 1 file
  • Specify output format with the --format flagin 7 of 123, across 1 file
  • Run health, churn, and expansion scripts togetherin 7 of 123, across 1 file
  • Verify output files contain expected records before continuingin 7 of 123, across 1 file

Said here and by no other author read

  • search before creating a ticket
  • use views or targeted search
  • add internal notes when changing status or ownership
  • confirm destructive or customer-visible actions
  • respect zendesk rate limits
  • build auth context from environment variables

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.