Unified team skill for UX improvement. Systematically discovers and fixes UI/UX interaction issues including unresponsive buttons, missing feedback, and state refresh problems. Uses team-worker agent architecture with roles/ for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team ux improve".
75
70%
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 ./.claude/skills/team-ux-improve/SKILL.mdQuality
Discovery
67%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 provides a reasonable overview of what the skill does (UX issue discovery and fixing) with some concrete examples, and includes an explicit trigger clause. However, it wastes space on implementation details (team-worker agent architecture, coordinator, pipeline) that don't help Claude decide when to select this skill, and the trigger phrase is an artificial command rather than natural user language.
Suggestions
Replace implementation details about agent architecture with more natural trigger terms users would actually say, such as 'fix UI bugs', 'improve user experience', 'broken button', 'UI not responding'.
Expand the 'Use when...' clause beyond the single command 'team ux improve' to include natural language variations like 'when the user reports UI interaction problems, unresponsive elements, or requests UX audits'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (UI/UX) and lists some specific actions like 'discovers and fixes UI/UX interaction issues' with examples (unresponsive buttons, missing feedback, state refresh problems), but also includes implementation details about architecture that don't describe concrete user-facing actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (systematically discovers and fixes UI/UX interaction issues including specific examples) and 'when' (explicitly states 'Triggers on "team ux improve"'), though the trigger is a specific command rather than a natural language pattern. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'UX improvement', 'unresponsive buttons', 'missing feedback', 'state refresh problems', but the explicit trigger 'team ux improve' is an artificial command rather than natural language a user would say. Missing common variations like 'fix UI', 'user experience', 'broken button', 'UI bugs'. | 2 / 3 |
Distinctiveness Conflict Risk | The UX improvement focus provides some distinctiveness, but 'UI/UX interaction issues' could overlap with general debugging, frontend development, or accessibility skills. The specific trigger phrase 'team ux improve' helps reduce conflict but the broader description could still cause overlap. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill that effectively serves as a routing layer for a multi-agent UX improvement pipeline. Its strengths are strong actionability (concrete spawn templates, exact paths, CLI commands) and excellent progressive disclosure (clear references to role-specific and spec files). The main weakness is the lack of explicit validation checkpoints between pipeline stages, which is important for a multi-step destructive workflow involving code modifications.
Suggestions
Add explicit validation/checkpoint steps between pipeline stages (e.g., 'Coordinator verifies scan-report.md exists and contains findings before spawning diagnoser') to create feedback loops in the core workflow.
Consider trimming the ASCII architecture diagram since the Role Registry table already conveys the same information more precisely.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient for a complex multi-agent orchestration skill, but includes some sections that could be tightened (e.g., the ASCII architecture diagram is somewhat redundant given the role registry table, and the user commands table adds little value). The worker spawn template is appropriately detailed since it's a concrete artifact Claude needs. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready Agent() spawn templates, specific CLI commands (ccw cli --mode analysis/write), exact file paths for role specs, precise session directory structures, and explicit message bus function signatures. The role router logic is clear and executable. | 3 / 3 |
Workflow Clarity | The pipeline stages (scan -> diagnose -> design -> implement -> test) are clearly sequenced, and the coordinator/worker dispatch pattern is well-defined. However, there are no explicit validation checkpoints between pipeline stages — e.g., no guidance on verifying scanner output before dispatching diagnoser, or validating implementation before testing. The error handling table covers edge cases but lacks feedback loops for the core pipeline. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: SKILL.md serves as a clear router/overview, with well-signaled one-level-deep references to role specs (roles/<name>/role.md), pipeline specs (specs/pipelines.md), design standards, anti-patterns, and heuristics. The role registry table provides clear navigation to each role's detailed instructions. | 3 / 3 |
Total | 10 / 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 | |
227244f
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.