CRO Specialist Agent. 전환율 최적화, A/B 테스트, 랜딩 최적화를 담당합니다.
Install with Tessl CLI
npx tessl i github:shaul1991/shaul-agents-plugin --skill growth-conversion37
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%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 (CRO) and lists relevant capabilities, but lacks explicit trigger guidance ('Use when...') which is critical for skill selection. The Korean-only format limits trigger term coverage, and the actions listed are category-level rather than specific concrete tasks.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user asks about improving conversion rates, running A/B tests, optimizing landing pages, or analyzing funnel performance'
Include both Korean and English trigger terms to improve matching (e.g., 'conversion rate optimization, A/B testing, split testing, 랜딩페이지, 퍼널 분석')
Make capabilities more concrete by specifying actions like 'analyze conversion funnels, design A/B test hypotheses, recommend landing page improvements, interpret test results'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (CRO) and lists some actions (전환율 최적화, A/B 테스트, 랜딩 최적화), but these are high-level categories rather than concrete specific actions like 'analyze conversion funnels' or 'design test variants'. | 2 / 3 |
Completeness | Describes what it does (담당합니다 - 'handles') but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'CRO', 'A/B 테스트', '전환율', '랜딩' that users might mention, but missing common variations and English equivalents (conversion rate, landing page optimization, split testing). | 2 / 3 |
Distinctiveness Conflict Risk | CRO is a specific domain that distinguishes it from general marketing skills, but could overlap with analytics, marketing, or UX optimization skills without clearer boundaries. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is essentially a job description rather than an actionable skill. It lists responsibilities and trigger keywords but provides zero concrete guidance on how to perform conversion rate optimization, A/B testing, or landing page optimization. Claude would gain no practical knowledge from this content.
Suggestions
Add concrete, executable examples for at least one core task (e.g., a step-by-step funnel analysis workflow with specific metrics to examine)
Include a clear multi-step process for CRO analysis with validation checkpoints (e.g., 'Identify drop-off points → Hypothesize causes → Design test → Validate statistical significance')
Provide specific templates or frameworks for deliverables (e.g., optimization hypothesis format, A/B test documentation structure)
Reference or create supporting documentation for complex topics like landing page optimization best practices or form optimization checklists
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is brief and doesn't over-explain concepts Claude knows, but it's essentially just a role description with bullet points rather than actionable skill content. It's lean but lacks substance. | 2 / 3 |
Actionability | The skill provides no concrete guidance, code, commands, or examples. It only lists abstract responsibilities ('전환 퍼널 분석', '마찰 요소 식별') without explaining how to actually perform any of these tasks. | 1 / 3 |
Workflow Clarity | There is no workflow, sequence, or process defined. The bullet points are unordered tasks with no steps, validation checkpoints, or guidance on how to execute CRO activities. | 1 / 3 |
Progressive Disclosure | The skill mentions an output location but provides no actual content to disclose progressively. There are no references to detailed guides, examples, or supporting documentation for the complex topics mentioned. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
Table of Contents
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.