customer-support

Elite AI-powered customer support specialist mastering conversational AI, automated ticketing, sentiment analysis, and omnichannel support experiences. Integrates modern support tools, chatbot platforms, and CX optimization with 2024/2025 best practices. Use PROACTIVELY for comprehensive customer experience management.

Quality

41%

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

21%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 skill body is a verbose persona-and-capability catalog that restates widely known support concepts, gives no executable guidance, and presents an abstract workflow without validation checkpoints.

Suggestions

Cut the restatement of known concepts (Capabilities catalogs, Behavioral Traits, Knowledge Base) and keep only guidance Claude would not already know, targeting well under 50 lines.

Add concrete, executable guidance: example tool invocations or API calls for named platforms (Zendesk, Intercom, Salesforce), and specific prompt/output templates for chatbot flows and CSAT analysis.

Turn the Response Approach into a real workflow with explicit validation checkpoints (e.g., 'verify ticket status changed', 'confirm SLA breach flagged') rather than abstract labels, and move detailed reference material into reference files linked from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~160-line body is noticeably verbose and padded: it extensively enumerates concepts Claude already knows (CSAT, NPS, SLAs, ticket routing) across ten capability subsections plus restatement-heavy 'Behavioral Traits' and 'Knowledge Base' sections, with buzzword traits like 'Empathy-first' and 'Innovation-focused'.	2 / 5
Actionability	The body offers no concrete code, commands, or specific tool usage; it only describes capabilities abstractly ('Intelligent ticket routing and prioritization algorithms', 'Sentiment analysis and emotional intelligence') and the Response Approach is generic labels ('Listen and understand', 'Analyze the context') rather than executable steps.	1 / 5
Workflow Clarity	A rough 10-step Response Approach sequence exists but its steps are poorly defined abstractions with no concrete commands, and there are no validation checkpoints or feedback loops anywhere in the body.	2 / 5
Progressive Disclosure	The body has thorough section headers giving it real structure, but the large capability catalog, traits, and knowledge base are all inlined in one monolithic SKILL.md with no reference files and no offloaded detail (no references/ or scripts/ bundles exist).	3 / 5
	Total	8 / 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.

The description covers a clear domain with both a what and a when clause, but it leans on capability-category language and buzzwords rather than concrete actions, and its trigger guidance is generic instead of user-natural.

Suggestions

Replace buzzword clusters ('Elite', 'CX optimization') with 2-4 concrete actions the skill performs (e.g., 'routes and prioritizes support tickets, drafts responses, analyzes CSAT/NPS trends').

Rewrite the 'when' clause as a user-natural trigger, e.g. 'Use when handling customer support tickets, chatbot flows, help-desk automation, or CSAT/NPS analysis'.

Add common synonyms users actually say — 'customer service', 'support tickets', 'help desk' — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names the customer-support domain and several capability clusters ('conversational AI, automated ticketing, sentiment analysis, and omnichannel support experiences'), but these are categories the specialist 'masters' rather than concrete executable actions, and they are padded with buzzwords like 'Elite' and 'CX optimization'.	3 / 5
Completeness	It states both a 'what' (an AI-powered customer support specialist mastering named domains) and a 'when' ('Use PROACTIVELY for comprehensive customer experience management'), but the 'when' is generic rather than offering concrete trigger phrases, keeping it below a 5.	4 / 5
Trigger Term Quality	It includes some relevant natural keywords ('customer support', 'customer experience', 'chatbot', 'ticketing') but misses common variations users actually say ('customer service', 'support tickets', 'help desk'), and the 'Use PROACTIVELY' trigger is an internal instruction rather than user-natural language.	3 / 5
Distinctiveness Conflict Risk	Customer support is a mostly distinct niche with only minor overlap risk against closely related CRM/customer-success/sales skills, though the broad 'customer experience management' trigger and tool-integration framing leave some overlap risk that prevents a 5.	4 / 5
	Total	14 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/customer-support/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.