CtrlK
BlogDocsLog inGet started
Tessl Logo

ticket-classification

Classify support tickets by urgency and category. Use when analyzing tickets, determining priority, routing customer requests, or when user asks to classify, triage, or categorize support tickets.

91

1.37x
Quality

87%

Does it follow best practices?

Impact

99%

1.37x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, highly actionable instruction-only skill with clear sequencing and a usable output schema. Its main weakness is token inefficiency from repeating the same keyword and routing guidance across multiple sections.

Suggestions

Remove the redundant keyword and routing guidance in the Tips section, since the same indicators already appear in the Classification Matrix and Urgency Keywords lists.

Consolidate the escalation triggers so they appear once rather than in both the Special Cases and Routing Decisions sections.

Consider moving the long per-level keyword lists into a reference file and keeping the matrix as the SKILL.md overview to reduce inline bulk.

DimensionReasoningScore

Conciseness

The body restates the same indicators multiple times — urgency keywords appear in the matrix table, again as keyword lists, and again in the Tips section, and routing/escalation triggers are duplicated across Special Cases and Tips — which is mostly efficient but padded with unnecessary repetition.

2 / 3

Actionability

Concrete keyword indicators, an explicit classification matrix, a defined 7-step process, worked examples with reasoning, and a copy-paste-ready JSON output schema give fully executable guidance.

3 / 3

Workflow Clarity

A clearly sequenced 7-step process plus a Quality Checklist checkpoint provides explicit sequencing; classification is a read-only task so destructive-operation validation caps do not apply.

3 / 3

Progressive Disclosure

A single SKILL.md with no bundle files is organized into clearly headed, navigable sections, which meets the simple-skill allowance for a top score without external references.

3 / 3

Total

11

/

12

Passed

Description

90%

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

A strong, third-person description that clearly defines the task and provides explicit, natural trigger terms. Its only weakness is a slightly narrow set of concrete actions listed in the 'what' clause.

DimensionReasoningScore

Specificity

"Classify support tickets by urgency and category" names the domain and two actions, but does not enumerate a comprehensive set of concrete actions like the score-3 example does.

2 / 3

Completeness

It states both what it does ("Classify support tickets by urgency and category") and when to use it via an explicit "Use when..." clause, satisfying both halves.

3 / 3

Trigger Term Quality

Phrases like "analyzing tickets, determining priority, routing customer requests" and "classify, triage, or categorize support tickets" are natural terms users would actually say, with good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

The support-ticket triage niche with domain-specific triggers ("triage", "routing customer requests") is clearly distinct and unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
udacity/cd14715-claude-code-classroom
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.