link7373/agentic-bi-team
A complete Agentic BI & data analytics team for Claude Code. Fill out one charter, run /setup-team, and you have 8 specialists, 10 workflows, and a full knowledge base.
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
5/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details
Copy this rig
# review before running: this installs third-party code
$ npx degit link7373/agentic-bi-team/.claude ./rig-agentic-bi-team # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit link7373/agentic-bi-team/.claude/skills/analyze .claude/skills/analyze $ npx degit link7373/agentic-bi-team/.claude/skills/build-dashboard .claude/skills/build-dashboard $ npx degit link7373/agentic-bi-team/.claude/skills/build-model .claude/skills/build-model $ npx degit link7373/agentic-bi-team/.claude/skills/build-pipeline .claude/skills/build-pipeline $ npx degit link7373/agentic-bi-team/.claude/skills/connect-data .claude/skills/connect-data $ npx degit link7373/agentic-bi-team/.claude/skills/define-kpis .claude/skills/define-kpis $ npx degit link7373/agentic-bi-team/.claude/skills/experiment .claude/skills/experiment $ npx degit link7373/agentic-bi-team/.claude/skills/health-check .claude/skills/health-check $ npx degit link7373/agentic-bi-team/.claude/skills/investigate-metric .claude/skills/investigate-metric $ npx degit link7373/agentic-bi-team/.claude/skills/make-deliverable .claude/skills/make-deliverable $ npx degit link7373/agentic-bi-team/.claude/skills/powerbi .claude/skills/powerbi $ npx degit link7373/agentic-bi-team/.claude/skills/research-domain .claude/skills/research-domain $ npx degit link7373/agentic-bi-team/.claude/skills/scorecard .claude/skills/scorecard $ npx degit link7373/agentic-bi-team/.claude/skills/setup-team .claude/skills/setup-team $ npx degit link7373/agentic-bi-team/.claude/skills/tableau .claude/skills/tableau $ npx degit link7373/agentic-bi-team/.claude/skills/triage .claude/skills/triage $ npx degit link7373/agentic-bi-team/.claude/skills/upgrade .claude/skills/upgrade
$ curl -fsSL --create-dirs -o .claude/agents/analytics-engineer.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/analytics-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/bi-analyst.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/bi-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/dashboard-developer.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/dashboard-developer.md $ curl -fsSL --create-dirs -o .claude/agents/data-engineer.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/data-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/data-quality-engineer.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/data-quality-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/data-scientist.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/data-scientist.md $ curl -fsSL --create-dirs -o .claude/agents/insights-communicator.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/insights-communicator.md $ curl -fsSL --create-dirs -o .claude/agents/metrics-steward.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/metrics-steward.md $ curl -fsSL --create-dirs -o .claude/agents/performance-monitor.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/performance-monitor.md $ curl -fsSL --create-dirs -o .claude/agents/powerbi-validator.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/powerbi-validator.md $ curl -fsSL --create-dirs -o .claude/agents/tableau-validator.md https://raw.githubusercontent.com/link7373/agentic-bi-team/main/.claude/agents/tableau-validator.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(.env)",
"Read(.env.*)",
"Read(**/secrets.*)",
"Read(**/credentials.json)",
"Read(**/service-account*.json)",
"Read(**/*.pem)",
"Read(**/*.key)",
"Bash(rm -rf:*)",
"Bash(git push --force:*)",
"Bash(git reset --hard:*)"
],
"ask": [
"Bash(psql:*)",
"Bash(mysql:*)",
"Bash(snowsql:*)",
"Bash(bq:*)",
"Bash(sqlite3:*)",
"Bash(duckdb:*)",
"Bash(clickhouse-client:*)",
"Bash(dbt:*)",
"Bash(git commit:*)",
"Bash(git push:*)",
"Bash(pip install:*)",
"Bash(python -m pip:*)",
"WebFetch"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python scripts/hooks/block_destructive_sql.py"
}
]
}
]
}
} Skills (17)
analyzebuild-dashboardbuild-modelbuild-pipelineconnect-datadefine-kpisexperimenthealth-checkinvestigate-metricmake-deliverablepowerbiresearch-domainscorecardsetup-teamtableautriageupgrade
Subagents (11)
| analytics-engineer | Designs and builds summary/aggregate tables from huge datasets, semantic data models, reusable analytics marts, and the metric computation layer. Use when queries are slow, datasets are too big to sca |
| bi-analyst | Answers business questions with data — ad-hoc analysis, deep dives, cross-database joins, cohort/funnel/segmentation analysis, and short written reports. Use for any "why did X happen", "how many", "w |
| dashboard-developer | Designs and builds dashboards in Tableau, Power BI, Looker, or other BI tools — from requirements through data model, layout, visual design, and publishing. Use for new dashboards, dashboard redesigns |
| data-engineer | Builds and maintains ETL/ELT pipelines, data ingestion from source systems, raw-to-staging transformations, and data quality checks. Use for getting new data into the warehouse, fixing broken pipeline |
| data-quality-engineer model: sonnet | Owns data health and observability — freshness SLAs, volume and schema drift, null/duplicate profiling, reconciliation against source systems, and triage when a pipeline breaks or a number looks impos |
| data-scientist | Builds predictive models and performs advanced analytics — churn/propensity models, forecasting, segmentation/clustering, anomaly detection models, and experiment (A/B test) design and analysis. Use f |
| insights-communicator | Turns analysis results into stakeholder-ready deliverables — executive summaries, PowerPoint/Google Slides decks, Word/Google Docs reports, Excel/Google Sheets workbooks, and data-storytelling narrati |
| metrics-steward model: sonnet | Owns metric and KPI definitions, the metrics catalog, data dictionary, and measurement governance. Use when defining new KPIs, resolving conflicting numbers between reports, choosing industry-standard |
| performance-monitor model: sonnet | Proactively monitors business metrics, produces weekly and monthly performance scorecards, detects anomalies and trend breaks, and runs structured root-cause analysis on underperforming metrics. Use f |
| powerbi-validator model: sonnet | Validates Power BI Project (PBIP) files before they reach Power BI Desktop — PBIR structure and schemas, TMDL syntax, naming rules, theme resources, and field references against the model. Use to chec |
| tableau-validator model: sonnet | Validates Tableau workbooks (.twb) before they reach Tableau — schema conformance against the resolution Tableau actually applies, field and sheet reference integrity, extract and connection wiring, a |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | python scripts/hooks/block_destructive_sql.py |
Permissions
deny (10)
Read(.env)
Read(.env.*)
Read(**/secrets.*)
Read(**/credentials.json)
Read(**/service-account*.json)
Read(**/*.pem)
Read(**/*.key)
Bash(rm -rf:*)
Bash(git push --force:*)
Bash(git reset --hard:*)
ask (13)
Bash(psql:*)
Bash(mysql:*)
Bash(snowsql:*)
Bash(bq:*)
Bash(sqlite3:*)
Bash(duckdb:*)
Bash(clickhouse-client:*)
Bash(dbt:*)
Bash(git commit:*)
Bash(git push:*)
Bash(pip install:*)
Bash(python -m pip:*)
WebFetch
allow (18)
Read
Glob
Grep
Bash(python scripts/*)
Bash(python demo/*)
Bash(python .claude/skills/powerbi/scripts/*)
Bash(python .claude/skills/powerbi/tests/*)
Bash(git status)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git show:*)
Bash(git add:*)
Bash(ls:*)
Bash(cat:*)
Bash(head:*)
Bash(tail:*)
Bash(wc:*)
Similar rigs
alirezarezvani/gaios
Open-source AI Operating System (AIOS) blueprint for Claude Code & Codex — turn any agent into your personal second brain + Chief of Staff: skills, self-verifying workflows, a second-brain wiki, and deterministic tools. Fork it for any role
Skill Collector 4.7k tok ·
stretchcloud/claude-code-unified-agents
—
Orchestrator 1.8k tok ·
bitbonsai/mcpvault
A lightweight Model Context Protocol (MCP) server for safe Obsidian vault access
Pragmatist 2.6k tok ·
narze/dotfiles
macOS / Linux / Codespaces compatible dotfiles with 1-line setup script. Tested on Apple Silicon Macs. Supports both zsh and fish. Managed with Chezmoi
Minimalist 1.3k tok ·