Name: customer-support
Rating: 34.4 (1 reviews)
Author: administrakt0r

customer-support

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

Quality

30%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/customer-support/SKILL.md

The canonical home for this skill is customer-support in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

10%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 padded persona document rather than actionable guidance: it lists capabilities and behavioral traits Claude already understands, offers no executable code or commands, and its one detailed reference points to a file that does not exist. It reads as marketing copy, not an operational skill.

Suggestions

Cut the Capabilities, Behavioral Traits, and Knowledge Base sections to a short overview and move detail into reference files that actually exist.

Replace abstract directives with concrete, executable steps or code examples for the common support tasks listed in 'Example Interactions'.

Fix the broken reference: create 'resources/implementation-playbook.md' or change the path to match an existing file, and add explicit validation/checkpoint steps to the Response Approach workflow.

Dimension	Reasoning	Score
Conciseness	The body is ~160 lines of persona and capability-list padding ('You are an elite AI-powered customer support specialist', extensive Capabilities/Behavioral Traits/Knowledge Base sections) that largely restates domain knowledge Claude already has, matching the 'severely verbose; extensively explains concepts Claude already knows' anchor.	1 / 5
Actionability	It provides no concrete code, commands, or executable steps, only abstract directives ('Clarify goals', 'Apply relevant best practices') and capability inventories, and its one detailed reference points to a nonexistent file ('resources/implementation-playbook.md').	1 / 5
Workflow Clarity	A 10-step 'Response Approach' sequence exists but the steps are abstract ('Listen and understand', 'Analyze the context') with no validation checkpoints or concrete commands, fitting the 'rough sequence present but many gaps; validation absent' anchor.	2 / 5
Progressive Disclosure	It is a single monolithic file with capability content inlined that belongs in separate reference files, and its only external reference ('resources/implementation-playbook.md') is a broken path with no 'resources/' directory present.	2 / 5
	Total	6 / 20 Passed

Description

50%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 names a clear domain and several capability areas but lacks any explicit 'Use when...' trigger guidance and leans on marketing language ('Elite', 'mastering') rather than concrete actions or natural trigger phrases. It is borderline-acceptable on most dimensions but never rises above a clear mid-level match.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when designing chatbot flows, ticket routing rules, or customer satisfaction measurement').

Replace marketing adjectives ('Elite AI-powered', 'mastering') with concrete verbs that describe actions Claude will take.

Include common user-facing synonyms (e.g., 'help desk', 'support tickets', 'CSAT/NPS') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the customer support domain and several concrete capability areas ('conversational AI, automated ticketing, sentiment analysis, and omnichannel support'), but these are capability categories rather than the concrete actions Claude would perform, leaving it just below the 'several specific actions' anchor.	3 / 5
Completeness	It conveys a 'what' (an AI-powered customer support specialist across several domains) but includes no 'when' / 'Use when...' trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant terms like 'customer support', 'ticketing', and 'sentiment analysis' appear, but they are framed as marketing language ('Elite AI-powered', 'mastering') rather than natural phrases a user would say, and common variations are missing.	3 / 5
Distinctiveness Conflict Risk	'Customer support specialist' is a recognizable niche, but the broad phrasing ('AI-powered', 'omnichannel support experiences') creates overlap risk with general chatbot and AI assistant skills.	3 / 5
	Total	12 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/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.