onboard
Designs and improves onboarding flows, empty states, and first-run experiences to help users reach value quickly. Use when the user mentions onboarding, first-time users, empty states, activation, getting started, or new user flows.
74
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.gemini/skills/onboard/SKILL.mdQuality
Discovery
100%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 is a well-crafted skill description that follows best practices closely. It uses third person voice, lists specific capabilities, includes a comprehensive 'Use when...' clause with natural trigger terms, and occupies a clearly defined niche. It closely mirrors the good examples provided in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Designs and improves onboarding flows, empty states, and first-run experiences' with a clear outcome 'help users reach value quickly'. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (designs and improves onboarding flows, empty states, first-run experiences) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'onboarding', 'first-time users', 'empty states', 'activation', 'getting started', 'new user flows'. These are all terms a user would naturally use when seeking help with this topic. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around onboarding and first-run UX design. The trigger terms like 'empty states', 'activation', 'first-time users', and 'new user flows' are distinct and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a comprehensive UX design guide rather than a focused, token-efficient skill for Claude. It over-explains standard design concepts (empty states, tooltips, progressive disclosure) that Claude already understands, while lacking the concrete, executable specificity that would make it truly actionable. The content would benefit significantly from aggressive trimming and splitting detailed subsections into referenced files.
Suggestions
Cut the content by 60-70% — remove explanations of standard UX concepts Claude already knows (what empty states are, what tooltips do, 'Show Don't Tell' principle) and focus only on project-specific patterns and decisions.
Split detailed subsections (Empty State Design, Guided Tours, Interactive Tutorials, Implementation Patterns) into separate referenced files to keep SKILL.md as a concise overview.
Replace descriptive advice with more concrete, copy-paste-ready code examples — e.g., a complete React empty state component, a Shepherd.js tour configuration, or a full onboarding flow component skeleton.
Add explicit validation checkpoints in the workflow — e.g., 'After designing the welcome screen, verify it communicates value prop in under 10 words and includes skip option before proceeding to account setup.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines, with significant content Claude already knows (UX design principles, what empty states are, what tooltips are). Sections like 'Respect User Intelligence' and 'Show, Don't Tell' are standard UX knowledge. The empty state types list, help patterns, and many bullet points explain concepts rather than providing novel, actionable guidance. | 1 / 3 |
Actionability | There is some concrete guidance (empty state example markup, localStorage code snippet, library recommendations), but most content is descriptive design advice rather than executable instructions. The skill reads more like a UX design textbook chapter than a step-by-step skill Claude can execute. Code examples are minimal and basic. | 2 / 3 |
Workflow Clarity | There is a general sequence (Assess → Principles → Design → Verify), but the workflow lacks explicit validation checkpoints between steps. The 'Verify Onboarding Quality' section lists metrics but doesn't integrate verification into the design workflow as actionable checkpoints. The mandatory preparation step is clear, but the rest is more of a reference than a guided workflow. | 2 / 3 |
Progressive Disclosure | The skill references an external dependency (/frontend-design, /teach-impeccable) which is good, but then dumps all onboarding content inline in one massive file. The various onboarding types (product onboarding, feature discovery, guided tours, interactive tutorials, empty states) could be split into separate reference files. The structure has headers but the volume is overwhelming for a single SKILL.md. | 2 / 3 |
Total | 7 / 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.
- Repository
- pbakaus/impeccable
- Commit
db1add7
- 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.