customer-support

Elite AI-powered customer support specialist mastering conversational AI, automated ticketing, sentiment analysis, and omnichannel support experiences.

Quality

23%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/customer-support/SKILL.md

Quality

Content

10%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 skill reads like a persona description or marketing document rather than an actionable skill file. It is overwhelmingly verbose with extensive lists of capabilities, behavioral traits, and knowledge areas that provide no concrete guidance Claude can act on. There is no executable code, no specific templates, no concrete workflows, and no validation steps—just abstract descriptions of what a customer support specialist should be.

Suggestions

Replace the extensive capability lists with 2-3 concrete, executable workflows (e.g., a step-by-step ticket triage workflow with specific decision criteria and validation checkpoints).

Add concrete templates or code examples, such as a chatbot response template, a ticket categorization schema, or a sentiment analysis prompt pattern that Claude can directly use.

Remove all 'behavioral traits,' 'knowledge base,' and generic capability descriptions—Claude already knows these concepts. Focus only on project-specific conventions, tools, and patterns.

If the referenced `resources/implementation-playbook.md` exists, ensure it contains the actionable content and make the SKILL.md a concise overview pointing to it; if it doesn't exist, create it with concrete implementation details.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and padded. The vast majority of content describes capabilities, behavioral traits, and knowledge areas that Claude already knows or that provide no actionable guidance. Lists like 'Empathy-first approach with genuine care for customer needs' and 'Modern customer support platforms and AI automation tools' are pure filler that waste tokens without teaching Claude anything new.	1 / 5
Actionability	No concrete code, commands, templates, or executable steps anywhere. The entire skill is abstract descriptions and vague bullet points like 'Advanced chatbot development with natural language processing' and 'Listen and understand the customer's issue with empathy and patience.' The 'Response Approach' section lists generic steps without any specifics on how to execute them.	1 / 5
Workflow Clarity	The 'Response Approach' section provides a rough 10-step sequence, but steps are vague and lack any validation checkpoints, concrete tools, or error recovery. There are no verification steps, no feedback loops, and no specific commands or outputs to check against. The instructions section has minimal workflow guidance ('Clarify goals, constraints, and required inputs').	2 / 5
Progressive Disclosure	References `resources/implementation-playbook.md` but no bundle files are provided, so it's unclear if this file exists. The massive amount of content (capabilities lists, behavioral traits, knowledge base) is all inlined in a monolithic fashion when it should either be in separate reference files or, more likely, removed entirely. No clear navigation structure for the extensive content.	2 / 5
	Total	6 / 20 Passed

Description

36%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.

This description reads like a marketing tagline rather than a functional skill description. It uses first-person-adjacent phrasing ('Elite AI-powered... specialist mastering') and buzzwords without specifying concrete actions or when the skill should be triggered. The lack of a 'Use when...' clause and the vague, promotional tone significantly reduce its utility for skill selection.

Suggestions

Replace buzzword-heavy phrasing with concrete actions using third-person verbs, e.g., 'Creates and manages support tickets, analyzes customer sentiment, drafts response templates, and routes inquiries across channels.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions customer support, help desk tickets, customer complaints, support responses, or chat interactions.'

Remove promotional language like 'Elite' and 'mastering' which add no functional value for skill selection and violate the third-person voice guideline.

Dimension	Reasoning	Score
Specificity	Names the domain (customer support) and lists buzzword-level capabilities like 'conversational AI', 'automated ticketing', 'sentiment analysis', and 'omnichannel support', but these read more as marketing fluff than concrete actions. No specific verbs describing what the skill actually does (e.g., 'creates tickets', 'routes inquiries', 'analyzes customer sentiment').	2 / 5
Completeness	Provides a vague 'what' (customer support with AI capabilities) but completely lacks any 'when' clause or trigger guidance. There is no 'Use when...' or equivalent explicit guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 3, and the 'what' is also vague, placing this at 2.	2 / 5
Trigger Term Quality	Contains some relevant keywords like 'customer support', 'ticketing', 'sentiment analysis', and 'omnichannel', but misses natural user phrases like 'help desk', 'customer complaint', 'support ticket', 'chat bot', or 'customer inquiry'. The terms used lean more toward industry jargon than what users would naturally say.	3 / 5
Distinctiveness Conflict Risk	The customer support domain provides some specificity, but terms like 'conversational AI' and 'sentiment analysis' could overlap with general NLP, chatbot, or analytics skills. The broad scope ('omnichannel support experiences') increases overlap risk with multiple related skills.	3 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: skills/customer-support/SKILL.md
Commit: 57c135b

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.