kpi-dashboard-design
Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use when building business dashboards, selecting metrics, or designing data visualization layouts.
61
41%
Does it follow best practices?
Impact
97%
1.16xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/business-analytics/skills/kpi-dashboard-design/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 has a solid structure with both 'what' and 'when' clauses clearly present, which is its strongest aspect. However, the capabilities listed lean toward topic areas rather than concrete actions, and the trigger terms could be broader to capture more natural user phrasings. The domain is moderately distinct but could overlap with general data visualization or analytics skills.
Suggestions
Replace abstract topic areas with concrete actions, e.g., 'Selects and prioritizes KPIs, designs dashboard layouts with charts and graphs, configures real-time monitoring alerts'.
Expand trigger terms to include common variations like 'charts', 'graphs', 'analytics', 'reporting dashboard', 'key performance indicators', 'business intelligence'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (KPI dashboards) and mentions some actions like 'metrics selection', 'visualization best practices', and 'real-time monitoring patterns', but these are more like topic areas than concrete specific actions. Compare to the level 3 example which lists discrete verbs like 'extract', 'fill', 'merge'. | 2 / 3 |
Completeness | Clearly answers both 'what' (design KPI dashboards with metrics selection, visualization best practices, real-time monitoring patterns) and 'when' with an explicit 'Use when...' clause covering building dashboards, selecting metrics, or designing data visualization layouts. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'dashboards', 'metrics', 'data visualization', and 'KPI', but misses common variations users might say such as 'charts', 'graphs', 'analytics dashboard', 'reporting', 'key performance indicators', or specific tool names. Coverage is partial. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on KPI dashboards provides some specificity, but terms like 'data visualization' and 'metrics' are broad enough to potentially overlap with general data analysis, charting, or reporting skills. The 'real-time monitoring' aspect adds some distinctiveness but could conflict with monitoring/observability skills. | 2 / 3 |
Total | 9 / 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 reads more like a comprehensive reference document or tutorial than an actionable skill for Claude. It is extremely verbose, spending most of its token budget on information Claude already knows (common KPIs, SMART criteria, basic dashboard design principles) and large ASCII art mockups. It lacks a clear workflow for actually designing a dashboard and would benefit enormously from being restructured into a concise overview with references to detailed sub-files.
Suggestions
Restructure into a concise SKILL.md overview (under 80 lines) with a clear step-by-step workflow (e.g., 1. Identify audience/level, 2. Select KPIs, 3. Choose layout pattern, 4. Implement, 5. Validate with stakeholders) and move KPI lists, SQL queries, and code examples into separate referenced files.
Remove content Claude already knows: SMART criteria definitions, lists of common KPIs by department, basic do's/don'ts of dashboard design. Focus on project-specific conventions or non-obvious patterns.
Add explicit validation checkpoints to the workflow, such as 'verify KPI definitions with stakeholders before implementation' and 'test dashboard with sample data before connecting live sources'.
Replace ASCII art dashboard mockups with brief descriptions of layout patterns or move them to a separate LAYOUTS.md reference file to reduce token consumption.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Includes extensive lists of KPIs by department that Claude already knows, explains SMART criteria (basic business knowledge), and provides ASCII art dashboard mockups that consume massive token budgets. The YAML lists of common KPIs add little value Claude couldn't generate on its own. | 1 / 3 |
Actionability | The SQL queries and Streamlit Python code are executable and concrete, which is good. However, much of the content is descriptive rather than instructive (lists of KPI names, ASCII layouts, do's/don'ts). The code examples use hardcoded sample data rather than showing patterns for connecting to real data sources, limiting practical utility. | 2 / 3 |
Workflow Clarity | There is no clear workflow or sequenced process for actually building a dashboard. The content is organized as a reference catalog (KPI lists, layout patterns, code snippets) but lacks a step-by-step process: no 'first do X, then Y, validate Z' sequence. For a design skill involving multiple steps (select KPIs, design layout, implement, validate), this is a significant gap. | 1 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of content with no references to external files. The SQL queries, full Streamlit app code, department KPI lists, and ASCII mockups are all inline when they could easily be split into separate reference files. The Resources section links to external websites rather than companion skill files. | 1 / 3 |
Total | 5 / 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
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.