CtrlK
BlogDocsLog inGet started
Tessl Logo

zendesk-automation

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

52

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/zendesk-automation/SKILL.md

The canonical home for this skill is zendesk-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid, well-organized Zendesk automation skill that provides genuinely useful domain-specific knowledge (tag replacement semantics, pagination behavior, ticket lifecycle). Its main weaknesses are repetition of key warnings across multiple sections, lack of executable call examples, and a monolithic structure that could benefit from splitting into overview and reference files. The workflow sequences are clear but could strengthen validation checkpoints for destructive operations.

Suggestions

Consolidate repeated pitfalls (tags replacement, deletion warnings) into the 'Known Pitfalls' section only, and reference it from workflows instead of duplicating the information.

Add at least one concrete MCP call example showing the actual JSON/parameters format for a common operation like creating a ticket.

Add an explicit confirmation/verification step in the delete workflow (e.g., 'Verify ticket ID and confirm with user before calling DELETE') rather than just noting irreversibility in pitfalls.

DimensionReasoningScore

Conciseness

The skill contains useful Zendesk-specific knowledge (tag replacement behavior, pagination details, ticket lifecycle) but is noticeably verbose. The repeated pitfalls across sections (tags behavior appears 3 times), the 'When to use' labels that are self-evident, and the final 'When to Use' section add unnecessary bulk. The quick reference table largely duplicates information already covered in the workflows.

3 / 5

Actionability

The skill provides concrete tool names, specific parameter names with valid values, and clear tool sequences for each workflow. However, there are no executable code examples or copy-paste ready MCP call examples — the guidance is specific but expressed as structured documentation rather than executable snippets. The setup steps are concrete and actionable.

4 / 5

Workflow Clarity

Each workflow has a clear numbered tool sequence with prerequisite/required/optional labels, and the setup section includes a verification step. The ticket lifecycle diagram is helpful. However, for destructive operations (DELETE), while the pitfall warns it's irreversible, there's no explicit validation/confirmation checkpoint in the workflow sequence itself — just a note in pitfalls. The tag merge pattern mentions fetching current tags first but doesn't embed this as a formal validation step in the update workflow.

4 / 5

Progressive Disclosure

The content is well-structured with clear sections and headers, but everything is in a single monolithic file with no bundle files. The repeated pitfalls (tags behavior, deletion warnings) across multiple sections and the summary section suggest the content could benefit from being split into a quick-start overview and detailed reference. The quick reference table at the end is good but the overall file is long for a single SKILL.md.

3 / 5

Total

14

/

20

Passed

Description

53%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a clear domain (Zendesk automation) and lists relevant entity types, but lacks concrete action verbs and an explicit 'Use when...' clause. The inclusion of implementation details ('Rube MCP', 'Composio', 'search tools first for current schemas') takes up space that could be used for natural trigger terms and clearer capability descriptions.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user asks about Zendesk, support tickets, customer support workflows, or help desk automation.'

Replace vague 'automate tasks' with concrete actions like 'Create, update, and search Zendesk tickets; manage users and organizations; send replies to support requests.'

Move implementation details ('Rube MCP', 'Composio', 'search tools first') into the skill body rather than the description, and use that space for user-facing synonyms like 'support tickets', 'help desk', 'customer service'.

DimensionReasoningScore

Specificity

Names the domain (Zendesk) and lists several entity types (tickets, users, organizations, replies) but these are nouns rather than concrete actions. It mentions 'automate tasks' which is vague, and 'search tools first for current schemas' is an implementation detail rather than a capability description.

3 / 5

Completeness

The 'what' is partially addressed (automate Zendesk tasks involving tickets, users, organizations, replies), but there is no explicit 'when' clause. There's no 'Use when...' guidance telling Claude when to select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 3.

3 / 5

Trigger Term Quality

Includes 'Zendesk', 'tickets', 'users', 'organizations', and 'replies' which are relevant keywords. However, it misses natural user phrases like 'support tickets', 'customer support', 'help desk', 'ticket management', or 'Zendesk API'. 'Rube MCP (Composio)' is technical jargon unlikely to be used by end users.

3 / 5

Distinctiveness Conflict Risk

The description is fairly distinct by specifying Zendesk and the specific integration method (Rube MCP/Composio). It clearly targets Zendesk automation specifically, which reduces overlap with generic support or CRM skills. Minor overlap risk exists with other Zendesk-related or Composio-related skills.

4 / 5

Total

13

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

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.