kpi-dashboard · genspark-ai — Claude Code skill: what it does, how to install
Builds an Excel KPI dashboard from operating data, with definitions, targets, actuals, attainment and trend charts. Useful for recurring metric reviews.
Apache-2.0 ★ 12,746 updated 2026-10-29
npx skills add genspark-ai/genoffice --skill kpi-dashboard -a claude-codeWhat kpi-dashboard does
This skill turns sales, user, finance or operations data into an Excel workbook. It first settles the reporting cadence, time range, comparison baseline and metric list, then records each KPI’s formula, source fields, period, direction and exclusion rules.
The workbook has Definitions, Data, Dashboard and Trends sheets. Actuals, attainment, MoM and YoY are formulas linked to Data; core metrics get line charts with their definition and unit in the title. Lower-is-better metrics use reverse attainment. If targets are not supplied, the attainment column stays blank, so the user must provide them before target performance can be assessed.
What it helps with
- turn operating data into an Excel KPI dashboard
- map metrics against targets and actuals
- document formulas and source fields
- show month-over-month and year-over-year movement
- flag abnormal swings in the data
Example prompts for the agent
- Build a monthly KPI dashboard from this operating data.
- Define these metrics and arrange them in an Excel dashboard workbook.
- Review the results, flag unusual periods, and identify the best and worst-performing metrics.
How to install kpi-dashboard
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill kpi-dashboard -a claude-code2Manually: put the files in place
~/.claude/skills/kpi-dashboard/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/kpi-dashboard/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill kpi-dashboard -a codex2Manually: put the files in place
.agents/skills/kpi-dashboard/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill kpi-dashboard -a cursor2Manually: put the files in place
.cursor/skills/kpi-dashboard/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install genspark-ai/genoffice skills/recommended/kpi-dashboard2Manually: put the files in place
.github/skills/kpi-dashboard/SKILL.md1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill kpi-dashboard -a gemini-cli2Platform CLI
gemini skills install https://github.com/genspark-ai/genoffice --path skills/recommended/kpi-dashboardManually: put the files in place
.devin/skills/kpi-dashboard/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about kpi-dashboard
How do I install kpi-dashboard in Claude Code?
Run npx skills add genspark-ai/genoffice --skill kpi-dashboard -a claude-code, then use ~/.claude/skills/kpi-dashboard/SKILL.md.
What does kpi-dashboard do?
It creates an Excel workbook with metric definitions, source data, a KPI dashboard and trend charts. Actuals, attainment, MoM and YoY are calculated with formulas.
How does the skill handle missing KPI targets?
It does not invent targets. The attainment column remains blank until the user supplies them.
Source text
SKILL.md · Apache-2.0
--- name: kpi-dashboard description: Turn operating data into a KPI dashboard workbook with metric definitions, target vs actual, attainment rates and trend charts, delivered as an Excel workbook category: data scenarios: Operating dashboard | KPI tracking | Monthly review quickPrompts: Build a monthly KPI dashboard from this operating data | Define these metrics and lay them out as a dashboard workbook metadata: version: 1.0.0 --- You are a KPI-dashboard specialist. The user gives you operating data (sales, user, finance or operations detail or summaries) and the metrics they care about; you deliver a dashboard workbook with metric definitions. ## Workflow 1. Settle the purpose and granularity first: the audience (executives / department / front line), refresh cadence (daily / weekly / monthly), time range, and the comparison baseline (target / prior period / same period last year). Without a metric list, propose 6-10 north-star plus process metrics for the business type and let the user choose. 2. Define each metric: definition / formula / source fields / reporting period / exclusion rules (such as whether refunds are included or whether to deduplicate). 3. When one name has several possible calculations in the data (for example average order value per order versus per customer), list the options and let the user decide; never pick silently. 4. Check the data: confirm fields match the definitions, and tell the user which metrics cannot be computed when fields are missing. Targets come from the user; if none, leave them blank, say the attainment column will be empty, and never make targets up. 5. Build the workbook as an Excel workbook with the spreadsheet tools available here. Title it "<Business> KPI Dashboard YYYY-MM". 6. After delivering, give three readings: the worst- and best-performing metrics, periods with abnormal swings, and which metric definitions still need the business owner's confirmation. ## Workbook structure - Sheet "Definitions": Metric / Category / Definition / Formula / Source / Period / Direction (higher is better or lower is better) / Owner. - Sheet "Data": the cleaned detail or per-period aggregated raw data. It is the single source; other sheets reference it and never copy it. - Sheet "Dashboard": Metric / Unit / Target / Actual / Attainment / MoM / YoY / Status. - Actual, attainment, MoM and YoY are all formulas referencing the Data sheet (SUMIFS / INDEX and so on), never typed numbers. - The Status column uses conditional formatting on attainment: >=100% green, 80-100% yellow, <80% red. - Sheet "Trends": each metric as a series by period with a line chart, one chart per core metric; chart titles state the definition and unit. ## Rules - "Lower is better" metrics (cost, churn) have attainment computed in reverse, with the direction noted on the Definitions sheet. - MoM / YoY show an em dash when the prior period is missing; never substitute 0. - Aggregate metrics (GMV, revenue) and ratio metrics (conversion rate) cannot simply be summed or averaged; ratios across periods are recomputed from numerator and denominator. - Financial definitions (revenue recognition timing, tax-inclusive or not) follow the company's finance policy; the dashboard computes only on the definitions the user confirmed. - The Dashboard sheet holds at most 15 metric rows; more go to per-department sub-sheets. A dashboard that cannot be read at a glance is not read at all. - Clear outliers in the data (such as a negative daily sales figure) are flagged and raised with the user first, never silently removed. ## Output One Excel workbook (Definitions / Data / Dashboard / Trends, four sheets). The reply holds only the three readings and the definitions still to confirm.
© genspark-ai · Apache-2.0 · genspark-ai/genoffice
Similar skills
All skills for Data and databases →kpi-dashboard by other authors comes first.