Business Intelligence

What it does

When your agent uses it

• Designing dashboards
• Building KPI frameworks
• Automating reports
• Creating data stories

Example prompts

• “/business-intelligence”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Clarify the reporting need -- Identify the audience (executive, operational, self-service), the key questions the dashboard must answer…
2. 2Define KPIs and metrics -- For each metric, specify the formula, data source, granularity, owner, and RAG thresholds using the KPI…
3. 3Design the dashboard layout -- Apply the visual hierarchy (most important metric top-left, summary-to-detail flow top-to-bottom). Select…
4. 4Build the semantic layer -- Define metric calculations, hierarchies, and row-level security in the BI tool's semantic model so consumers…
5. 5Automate reporting -- Configure scheduled delivery (PDF/email, Slack alerts) and threshold-based alerts with the patterns below.
6. 6Validate and iterate -- Confirm KPI values match source-of-truth queries. Check dashboard load time (<5 s target). Gather stakeholder…

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Business Intelligence loads about 3.1k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 1,088 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~61

When it runs · the whole SKILL.md, loaded when a task matches

~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 1,088 words, ~3,148 tokens.

name

business-intelligence

description

Business intelligence across dashboard design, visualization, and reporting automation. Use when designing dashboards, building KPI frameworks, automating reports, creating data stories, or optimizing BI tool performance.

license

MIT + Commons Clause

metadata.version

1.0.0

metadata.author

borghei

metadata.category

data-analytics

metadata.updated

2026-03-31

metadata.tags

bi, dashboards, visualization, reporting, insights

# Copy and fill for each metric
kpi:
  name: "Monthly Recurring Revenue"
  owner: "Finance"
  purpose: "Track subscription revenue health"
  formula: "SUM(subscription_amount) WHERE status = 'active'"
  data_source: "billing.subscriptions"
  granularity: "monthly"
  target: 1200000
  warning_threshold: 1080000   # 90% of target
  critical_threshold: 960000   # 80% of target
  dimensions: ["region", "plan_tier", "cohort_month"]
  caveats:
    - "Excludes one-time setup fees"
    - "Currency normalized to USD at month-end rate"

+------------------------------------------------------------+
|                   EXECUTIVE SUMMARY                         |
| Revenue: $12.4M (+15% YoY)   Pipeline: $45.2M (+22% QoQ)  |
| Customers: 2,847 (+340 MTD)  NPS: 72 (+5 pts)              |
+------------------------------------------------------------+
| REVENUE TREND (12-mo line)    | REVENUE BY SEGMENT (donut)  |
+-------------------------------+-----------------------------+
| TOP 10 ACCOUNTS (table)       | KPI STATUS (RAG cards)      |
+-------------------------------+-----------------------------+

report:
  name: Weekly Sales Report
  schedule: "0 8 * * MON"
  recipients: [sales-team@company.com, leadership@company.com]
  format: PDF
  pages: [Executive Summary, Pipeline Analysis, Rep Performance]

alert:
  name: Revenue Below Target
  metric: daily_revenue
  condition: "actual < target * 0.9"
  channels:
    email: finance@company.com
    slack: "#revenue-alerts"
  message: "Daily revenue ${actual} is ${pct_diff}% below target. Top factors: ${top_factors}"

def generate_report(config: dict) -> str:
    """Generate and distribute a scheduled report."""
    # 1. Refresh data sources
    refresh_data_sources(config["sources"])
    # 2. Calculate metrics
    metrics = calculate_metrics(config["metrics"])
    # 3. Create visualizations
    charts = create_visualizations(metrics, config["charts"])
    # 4. Compile into report
    report = compile_report(metrics=metrics, charts=charts, template=config["template"])
    # 5. Distribute
    distribute_report(report, recipients=config["recipients"], fmt=config["format"])
    return report.path

-- Before: full table scan
SELECT * FROM large_table WHERE date >= '2024-01-01';

-- After: partitioned, filtered, and column-pruned
SELECT order_id, customer_id, amount
FROM large_table
WHERE partition_date >= '2024-01-01'
  AND status = 'active'
LIMIT 10000;

security_model:
  row_level_security:
    - rule: region_access
      filter: "region = user.region"
  object_permissions:
    - role: viewer
      permissions: [view, export]
    - role: editor
      permissions: [view, export, edit]
    - role: admin
      permissions: [view, export, edit, delete, publish]

python scripts/kpi_tracker.py --definitions kpis.json --data sales.csv
python scripts/kpi_tracker.py --definitions kpis.json --data sales.csv --json
python scripts/dashboard_spec_generator.py --definitions kpis.json --title "Sales Dashboard"
python scripts/dashboard_spec_generator.py --definitions kpis.json --layout 3-column --json
python scripts/metric_validator.py --definitions metrics.json --strict
python scripts/metric_validator.py --definitions metrics.json --json

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in data-analytics/business-intelligence of borghei/Claude-Skills.

• SKILL.md
• scripts/dashboard_spec_generator.py
• scripts/kpi_tracker.py
• scripts/metric_validator.py

Open the folder on GitHubat commit 4a698e8