user-journeys
User experience flows - journey mapping, UX validation, error recovery
38
37%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/user-journeys/SKILL.mdQuality
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 is a brief list of UX-related topics rather than a well-formed skill description. It lacks concrete actions describing what the skill does, has no 'Use when...' clause to guide skill selection, and uses terms that could overlap with other skills. It reads more like a category label than an actionable skill description.
Suggestions
Add an explicit 'Use when...' clause with trigger terms, e.g., 'Use when the user asks about user journeys, UX flows, usability validation, or designing error states.'
Replace vague category labels with concrete actions, e.g., 'Creates user journey maps, validates UX flows against usability heuristics, and designs error recovery patterns for user-facing interfaces.'
Include common natural language variations users might say, such as 'user flow', 'usability review', 'user experience', 'UX audit', 'error states', or 'user path analysis'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (UX) and lists some actions like 'journey mapping', 'UX validation', and 'error recovery', but these are more like category labels than concrete, specific actions. It doesn't describe what the skill actually does with these (e.g., 'creates journey maps', 'validates user flows against heuristics'). | 2 / 3 |
Completeness | Provides a partial 'what' (UX flows, journey mapping, validation, error recovery) but has no 'when' clause at all — no 'Use when...' or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also weak/vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'journey mapping', 'UX validation', and 'error recovery' that users might mention, but misses common variations like 'user flow', 'usability', 'wireframe review', 'user journey', 'UX audit', or 'user testing'. | 2 / 3 |
Distinctiveness Conflict Risk | The UX domain provides some specificity, but terms like 'error recovery' and 'validation' are broad enough to overlap with other skills (e.g., error handling skills, testing/QA skills). The description lacks enough precision to clearly carve out a distinct niche. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable content with concrete Playwright tests and journey templates, but is severely undermined by its verbosity and monolithic structure. It explains many UX concepts Claude already knows (journey philosophy, anti-patterns, emotional states) and inlines hundreds of lines of example code that should be in separate referenced files. Cutting this to ~30% of its current size and splitting into referenced files would dramatically improve its effectiveness.
Suggestions
Reduce content by 60-70%: remove the philosophy section, common journey patterns (general UX knowledge), and anti-patterns list. Keep only the template, one example journey, and one test example.
Split into referenced files: move full journey examples to journeys/examples/, Playwright test patterns to journeys/testing.md, UX validation utilities to journeys/ux-validators.md, and metrics tracking to journeys/metrics.md.
Add a validation workflow for journey documentation itself — e.g., a checklist to verify that documented journeys have matching E2E tests and that test assertions align with documented success criteria.
Remove redundant second journey example (checkout) since it follows the same template pattern as the first — or move it to a separate examples file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains concepts Claude already knows (what user journeys are, what emotional states are, what progressive disclosure means). The philosophy section, anti-patterns list, and common journey patterns are all general UX knowledge that doesn't need to be taught. The two full journey examples (signup, checkout) are largely redundant with each other since the template already shows the structure. | 1 / 3 |
Actionability | Provides fully executable Playwright test code, complete journey templates with concrete examples, TypeScript utility functions for UX validation, and specific package.json scripts. The code examples are copy-paste ready and cover both happy paths and error recovery scenarios. | 3 / 3 |
Workflow Clarity | The journey template provides a clear step-by-step structure with success criteria and error scenarios, and the testing workflow is well-sequenced. However, there's no explicit validation workflow for creating/reviewing journeys themselves — no feedback loop for verifying journey documentation completeness or ensuring tests actually match documented steps. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the content clearly warranting separation. The full journey examples, Playwright test code, UX validation utilities, and metrics tracking code could all be in separate referenced files. Everything is inlined in one massive document, making it hard to navigate. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (637 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- alinaqi/claude-bootstrap
- Commit
7e5f7a2
- 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.