CtrlK
BlogDocsLog inGet started
Tessl Logo

escalation-and-reply-tone

When a ticket must go to a human before any reply is sent, and how the first reply should read. Use when drafting a customer reply or setting needs_human_review.

65

Quality

78%

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 ./.agents/playwright_project/skills/197586632641 - escalation-and-reply-tone/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%Weight 40%Scale 1-5

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

A tight, well-structured instruction skill: every line is concrete and actionable, with clear escalation criteria and a useful negative guardrail. The only minor gap is the absence of an explicit ordered sequence linking the escalation decision to the reply drafting.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no padded explanations, no concept overviews, and every line delivers a concrete rule or example.

5 / 5

Actionability

Despite being instruction-only, the guidance is fully actionable: a concrete field to set (needs_human_review = true), explicit escalation categories, and copy-ready reply phrasings covering common cases.

5 / 5

Workflow Clarity

The escalation decision is clearly specified via a criteria list with an explicit guardrail ('Urgency alone is not escalation'), but there is no explicit numbered sequence or validation checkpoint tying the escalate-then-draft flow together.

4 / 5

Progressive Disclosure

At roughly 20 lines with no need for external references, the body is cleanly split into two well-signaled sections (escalation rules, tone rules), satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

19

/

20

Passed

Description

62%Weight 40%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.

A clear, third-person description that answers both what and when with an explicit 'Use when' trigger, occupying a well-scoped niche. It is slightly held back by relying on a field name as a trigger term and by an abstract 'what' statement rather than a fuller enumeration of actions.

Suggestions

Add a natural-language synonym for escalation (e.g., 'escalate a ticket' or 'angry customer') alongside 'needs_human_review' so the trigger matches how users actually phrase the request.

Tighten the 'what' clause by listing the concrete actions in-line (e.g., 'decide whether to escalate a ticket and draft the first customer reply') rather than describing purpose abstractly.

DimensionReasoningScore

Specificity

Names the domain (human escalation + first-reply tone) and two concrete actions ('drafting a customer reply', 'setting needs_human_review'), but does not comprehensively enumerate the skill's capabilities.

3 / 5

Completeness

Both 'what' (when a ticket must go to a human, and how the first reply should read) and 'when' ('Use when drafting a customer reply or setting needs_human_review') are present with an explicit trigger clause, though the 'what' is somewhat abstract.

4 / 5

Trigger Term Quality

Includes relevant terms ('ticket', 'customer reply', 'needs_human_review') but leans on the system field name rather than natural user synonyms like 'escalate', 'complaint', or 'support ticket'.

3 / 5

Distinctiveness Conflict Risk

The escalation-before-reply niche with the specific needs_human_review trigger is mostly distinct, with only minor overlap risk against a generic customer-reply skill.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Kiln-AI/Kiln
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.