customer-support-agent

Use this skill when building a customer support agent with knowledge base lookup, ticket creation, and human escalation logic.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./external/anthropic-official/customer-support-agent/SKILL.md

Quality

Content

68%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.

The body delivers concrete, mostly executable code for a customer support agent with a clear agentic loop and tidy structure. Its main weaknesses are the lack of validation/verification checkpoints around state-changing actions and the placeholder tool stubs.

Suggestions

Add a validation/verification checkpoint after tool execution (e.g., confirm ticket fields before create_ticket, and verify escalation criteria before escalate_to_human) so the agent loop includes an explicit feedback loop rather than blindly returning tool output.

Replace the undefined stub functions in execute_tool with concrete, runnable implementations or clearly mark them as integration points requiring user-supplied functions.

Parameterize the hardcoded model 'claude-opus-4-6' (e.g., a MODEL constant or config value) to avoid embedding a time-sensitive, version-specific literal in the skill body.

Dimension	Reasoning	Score
Conciseness	The body avoids preamble about what a support agent is and stays mostly lean code plus a compact table, but the hardcoded model literal 'claude-opus-4-6' and placeholder comments add minor noise, fitting the 4 anchor rather than 5.	4 / 5
Actionability	Real tool schemas, a system prompt, an agent loop, and a dispatch function provide mostly executable guidance, but execute_tool calls undefined functions with 'implement with your docs' placeholders, leaving minor gaps that keep it from a 5.	4 / 5
Workflow Clarity	The agentic loop is coherently sequenced, but ticket creation and human escalation are batch/ destructive-style actions affecting a customer's account state and the loop has no validation, error-recovery, or verification checkpoint; per the rubric this caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Section headers (Overview, Agent Architecture, Tool Implementation Stubs, Quick Reference) and a reference table give good structure, but all content is inlined with no bundle files or one-level-deep references, so it fits the 4 anchor rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

75%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.

The description clearly answers both what the skill does and when to use it, with concrete capabilities and a natural trigger phrase. It is strong but stops short of comprehensive synonyms, multiple trigger phrases, and full coverage of in-skill actions.

Dimension	Reasoning	Score
Specificity	Names the domain (customer support agent) plus three concrete capabilities — 'knowledge base lookup', 'ticket creation', and 'human escalation logic' — matching the 'several specific actions; minor gaps' anchor; it omits other in-skill actions like order status, so it is not a 5.	4 / 5
Completeness	It states both the 'what' (KB lookup, ticket creation, escalation) and the 'when' ('Use this skill when building a customer support agent'), but the trigger is a single phrase rather than multiple concrete trigger phrases, fitting the 4 anchor rather than 5.	4 / 5
Trigger Term Quality	'building a customer support agent' is a phrase a user would naturally say, supplemented by 'knowledge base lookup', 'ticket creation', and 'human escalation'; coverage is good but lacks common synonyms like 'help desk' or 'chatbot', so not 5.	4 / 5
Distinctiveness Conflict Risk	'Customer support agent' with ticket creation and escalation is a fairly distinct niche with low conflict risk, though it could mildly overlap with generic agent-building skills, keeping it at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ProwlrBot/prowlr-marketplace
Path: external/anthropic-official/customer-support-agent/SKILL.md
Commit: 32f0050

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.