When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but don't use the product," "time to value," or "first session experience." Use this whenever users are signing up but not sticking around. For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence.
67
51%
Does it follow best practices?
Impact
92%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/onboarding-cro/SKILL.mdQuality
Discovery
44%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 excels at trigger terms and distinctiveness — it provides extensive natural language keywords and explicitly delineates boundaries with related skills. However, it critically fails to describe what the skill actually does; there are no concrete actions, outputs, or capabilities listed. It reads as a pure 'when to use' clause with no 'what it does' clause.
Suggestions
Add a leading sentence describing concrete actions, e.g., 'Designs onboarding checklists, optimizes empty states, maps activation funnels, and reduces time-to-value for new users.'
Restructure to lead with capabilities (what) before the 'Use when...' clause (when), following the pattern: '[Actions]. Use when [triggers].'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions entirely. It never states what the skill actually does — no verbs like 'designs,' 'analyzes,' 'creates,' or 'optimizes.' It only describes when to use it, not what it does. | 1 / 3 |
Completeness | While the 'when' is thoroughly covered with explicit triggers, the 'what does this do' is essentially missing. The description never explains what concrete actions or outputs the skill provides, making it incomplete on the 'what' dimension. | 1 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'onboarding flow,' 'activation rate,' 'aha moment,' 'empty states,' 'time to value,' 'users sign up but don't use the product,' and many other phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around post-signup onboarding and activation, and explicitly differentiates from related skills (signup-flow-cro for registration, email-sequence for ongoing emails), reducing conflict risk significantly. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent strategic framework for onboarding CRO that is well-organized and covers the domain comprehensively. Its main weaknesses are a lack of concrete, executable examples (specific copy, templates, or detailed deliverable formats) and some unnecessary explanation of concepts Claude already understands. The workflow could benefit from a more explicit step-by-step consulting process with validation checkpoints.
Suggestions
Add concrete examples of deliverables: sample onboarding checklist copy, example empty state copy, or a template email sequence with actual subject lines and body text rather than just trigger descriptions.
Replace the Core Principles section with a brief reminder list or remove it entirely—these are standard UX principles Claude already knows, and the space would be better used for specific, actionable templates.
Add an explicit workflow sequence for conducting an onboarding audit: e.g., '1. Read context file → 2. Ask remaining questions → 3. Map current funnel with drop-off data → 4. Identify top 3 drop-off points → 5. Generate recommendations prioritized by impact/effort → 6. Validate recommendations against activation metric.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-organized but includes some unnecessary explanatory content that Claude already knows (e.g., explaining what empty states are, general concepts about tooltips). Some sections like 'Core Principles' state obvious UX truisms. However, the tables and structured formats keep it from being truly verbose. | 2 / 3 |
Actionability | The skill provides structured frameworks (tables, checklists, output formats) but lacks concrete, executable examples. There's no specific copy, no code snippets, no wireframe descriptions, and recommendations remain at a strategic/conceptual level rather than providing copy-paste-ready deliverables like actual checklist copy or email templates. | 2 / 3 |
Workflow Clarity | The Initial Assessment section provides a clear starting sequence, and the Output Format section defines deliverables. However, the overall workflow for conducting an onboarding audit or designing a flow is implicit rather than explicitly sequenced with validation checkpoints. There's no clear 'do step 1, then validate, then step 2' structure for the consulting process. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and headers, appropriate use of tables for comparison, and a reference to external files (references/experiments.md). Related skills are clearly signaled at the end. The content stays at an overview level without becoming monolithic, and the one external reference is clearly signaled and one level deep. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
1bcff9f
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.