kpi-dashboard-design

Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use this skill when building an executive SaaS metrics dashboard tracking MRR, churn, and LTV/CAC ratios; designing an operations center with live service health and request throughput; creating a cohort retention analysis view for a product team; or debugging a dashboard where metrics contradict each other due to inconsistent calculation methodology.

Quality

71%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/business-analytics/skills/kpi-dashboard-design/SKILL.md

Quality

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 an excellent skill description that clearly articulates specific capabilities, provides rich trigger terms that users would naturally use, and explicitly defines both what the skill does and when to use it through concrete scenario examples. The use of third person voice and domain-specific terminology makes it highly distinctive and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: metrics selection, visualization best practices, real-time monitoring patterns, tracking MRR/churn/LTV-CAC ratios, cohort retention analysis, debugging contradictory metrics. Very detailed and actionable.	3 / 3
Completeness	Clearly answers both 'what' (design KPI dashboards with metrics selection, visualization best practices, real-time monitoring) and 'when' with explicit trigger scenarios ('Use this skill when building an executive SaaS metrics dashboard...designing an operations center...creating a cohort retention analysis...debugging a dashboard').	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'KPI dashboard', 'MRR', 'churn', 'LTV/CAC', 'service health', 'request throughput', 'cohort retention', 'metrics', 'real-time monitoring', 'SaaS metrics'. These are terms practitioners naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche around KPI dashboards, SaaS metrics, and monitoring patterns. The specific domain terms (MRR, churn, LTV/CAC, cohort retention, service health) make it very unlikely to conflict with general data visualization or other dashboard skills.	3 / 3
	Total	12 / 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 has strong actionability with executable SQL and Python code, and the troubleshooting section is genuinely valuable with specific problem-solution pairs. However, it is severely bloated — the department KPI catalogs, SMART acronym explanation, and ASCII mockups consume enormous token budget with information Claude already knows or could generate. The content desperately needs restructuring into a concise overview with linked reference files.

Suggestions

Move the department KPI lists (Sales, Marketing, Product, Finance) into a separate KPIS_BY_DEPARTMENT.md reference file and link to it, keeping only 2-3 example KPIs inline to illustrate the pattern.

Remove the SMART KPIs section and the KPI Framework table — these are general business knowledge Claude already has. Focus the overview on what's unique: the implementation patterns and troubleshooting.

Extract the full Streamlit code and SQL queries into separate files (e.g., DASHBOARD_IMPLEMENTATION.md, KPI_QUERIES.sql) and reference them from the main skill, keeping only the most critical query (MRR) inline as an example.

Add a clear end-to-end workflow section with numbered steps and validation checkpoints for building a dashboard from scratch (e.g., 'Step 1: Define 5-7 KPIs with stakeholders → Step 2: Write and validate SQL calculations against known values → Step 3: Build layout → Step 4: Add alerting').

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~350+ lines. It explains basic concepts Claude already knows (SMART KPIs, what MRR/ARR/NPS are), includes exhaustive KPI lists by department that are general knowledge, and has lengthy ASCII art dashboard mockups. The YAML KPI lists alone consume significant tokens without adding actionable value beyond what Claude could generate on its own.	1 / 3
Actionability	The skill provides fully executable SQL queries for MRR, cohort retention, and CAC calculations, plus a complete Streamlit dashboard implementation with Plotly charts. The troubleshooting section includes concrete code fixes for real problems like inconsistent MRR calculations and database-hammering dashboards.	3 / 3
Workflow Clarity	The skill lacks a clear sequential workflow for building a dashboard end-to-end. While individual sections are well-organized, there's no step-by-step process with validation checkpoints (e.g., 'define KPIs → validate with stakeholders → implement queries → verify calculations → build UI → test with real data'). The troubleshooting section partially compensates by addressing common failure modes with fixes.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with everything inline. The extensive KPI lists by department, multiple ASCII dashboard patterns, full SQL queries, and a complete Streamlit app should be split into separate reference files. The only external reference is a single 'Related Skills' link at the bottom. Content like the department KPI catalogs and the full Streamlit implementation would be better as linked files.	1 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

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: wshobson/agents
Commit: 27a7ed9

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.