CtrlK
BlogDocsLog inGet started
Tessl Logo

customer-support

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

37

Quality

35%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/customer-support/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

17%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 is a verbose persona document: it lists capabilities and traits abstractly with no executable guidance, no validation checkpoints, and a single reference to a non-existent file rather than a real progressive-disclosure bundle.

Suggestions

Cut the 'Expert Purpose', 'Behavioral Traits', and 'Knowledge Base' sections — they restate what Claude already knows — and replace the capability bullet lists with concrete, copy-paste-ready examples (sample chatbot flow JSON, a ticket-routing rule, a CSAT survey template).

Convert the 'Response Approach' into a concrete workflow with explicit validation checkpoints (e.g. 'Verify the ticket category against the routing table before escalating') rather than abstract verbs.

Either create the referenced 'resources/implementation-playbook.md' (and move the capability detail there) or remove the dangling reference; organize detailed material into one-level-deep reference files with clearly signaled links.

DimensionReasoningScore

Conciseness

The body is padded with persona fluff Claude already knows ('Elite AI-powered customer support specialist...', 'Empathy-first approach...', a 10-item 'Knowledge Base' of generic truths) and long capability bullet lists; noticeably verbose with several padded sections.

2 / 5

Actionability

No code, commands, schemas, or concrete artifacts appear anywhere; instructions like 'Clarify goals', 'Apply relevant best practices', and the 'Response Approach' steps only describe at an abstract level rather than instructing executable action.

1 / 5

Workflow Clarity

The 'Response Approach' gives a 10-step sequence, but steps are abstract ('Listen and understand', 'Analyze the context') with no concrete commands, inputs, or validation/checkpoint steps; sequence is rough and poorly defined.

2 / 5

Progressive Disclosure

Content is a monolithic wall of inlined capability/trait/knowledge lists that belong in separate files, and the lone reference 'resources/implementation-playbook.md' points to a path that does not exist (no references/scripts/assets bundles present), so navigation is effectively broken.

2 / 5

Total

7

/

20

Passed

Description

53%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 identifies a clear domain and lists several relevant sub-areas, but it reads as a persona headline rather than an action/trigger specification and omits any explicit 'Use when' guidance.

Suggestions

Rewrite in third-person action voice naming concrete capabilities (e.g., 'Routes, drafts, and triages customer support tickets; runs sentiment analysis on conversations') instead of 'Elite ... specialist mastering ...'.

Append an explicit trigger clause, e.g. 'Use when the user needs to build or optimize customer support workflows, chatbot flows, ticketing, or CSAT/NPS measurement.'

Add natural synonyms users actually say (help desk, live chat, support tickets, CSAT, NPS) to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('customer support') and enumerates four sub-areas ('conversational AI, automated ticketing, sentiment analysis, and omnichannel support'), but these are domains/capability buckets rather than concrete actions, and 'Elite'/'mastering' are buzzwords rather than verbs.

3 / 5

Completeness

Has a clear 'what' (an AI-powered customer support specialist mastering the listed areas) but no 'when'/'Use when...' trigger clause, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms a user might say ('customer support', 'ticketing', 'sentiment analysis'), but offers only a single phrasing with no synonyms or common variations such as 'help desk', 'live chat', or 'CSAT'.

3 / 5

Distinctiveness Conflict Risk

The 'customer support specialist' framing carves a clear niche with low overlap risk against unrelated skills; only minor overlap with generic communication/crm skills keeps it just below 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.