motherduckdb/motherduck-create-dive
skills/motherduck-create-dive/SKILL.md
Create, edit, manage, share, or embed MotherDuck Dives — live React + SQL dashboards, charts, and data apps saved in the workspace. Use for any dashboard, chart, KPI display, or data visualization over MotherDuck data, and for Dive authoring mechanics such as get_dive_guide, useSQLQuery, local preview, version history, Dives-as-code, required resources, team sharing, or embedded Dive sessions.
$ install --global
skillsauthnpx skillsauth add motherduckdb/agent-skills motherduck-create-diveInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 11, 2026, 2:38 AM297.1s2 files scanned
SKILL.md
- name:
- motherduck-create-dive
- description:
- Create, edit, manage, share, or embed MotherDuck Dives — live React + SQL dashboards, charts, and data apps saved in the workspace. Use for any dashboard, chart, KPI display, or data visualization over MotherDuck data, and for Dive authoring mechanics such as get_dive_guide, useSQLQuery, local preview, version history, Dives-as-code, required resources, team sharing, or embedded Dive sessions.
- license:
- MIT
Create and Manage MotherDuck Dives
Use this skill when the user needs a persistent, shareable, editable Dive rather than a one-off chart. Dives are live React + SQL data apps inside MotherDuck; they can be built conversationally, edited from existing workspace content, managed as code, shared with teammates, or embedded in another application.
Source Of Truth
- Prefer current MotherDuck Dive docs first.
- Non-negotiable ordering: when MotherDuck MCP is available, call
get_dive_guidebefore generating Dive code and always beforesave_diveorupdate_dive. The guide defines the current component API and runtime libraries. - Use the blessed Dives example repo as the reference implementation for local preview, Dives-as-code layout, metadata, CI previews, and deploy scripts.
- Use Dives SQL functions when the user wants a scriptable SQL-native create/read/update/delete workflow instead of MCP tools.
- Treat ordinary Dives and embedded Dives separately: current public materials say Dives are available on all plans, while embedding requires a Business plan. Verify plan entitlements against live docs before promising an embed rollout.
Default Posture
- First classify the job: new Dive, existing Dive edit, Dives-as-code workflow, team sharing, or embedding.
- Validate the underlying SQL and schema first with
motherduck-exploreandmotherduck-query; a good Dive starts with a correct query. - Keep Dive queries fully qualified and SQL-heavy; let React handle presentation, not data reshaping.
- Treat the component contract as React +
useSQLQuery, a default export, supported runtime libraries, explicit loading/empty/error states, and no browser-side secrets. - When local preview uses
REQUIRED_DATABASES, keep the export on one line and mirror the real share dependencies in metadata or save/update inputs. Avoid aliases that collide with existing database names. - Start from a named theme direction such as
Corporate Dashboard,Tufte Minimal, orFT Salmoninstead of vague visual prompts. - Prefer one query per visual section or interaction surface rather than one giant cross-purpose query.
- Preview locally before saving when the environment supports it.
- For existing Dives, read the current content and version metadata before overwriting anything. MCP
list_divesreturnscurrent_version, andread_divecan fetch historical versions. - Treat embedded Dives as the first-choice path when a product needs a live read-only Dive surface with a backend-created embed session. Move to
motherduck-build-cfa-appwhen the app needs custom API contracts, writes, non-Dive routing, tenant policy enforcement, or richer authorization. - For shared repos or CI/CD, use a service-account token so Dive ownership is not tied to one human user.
Workflow
- Classify the delivery path: workspace Dive, edit existing Dive, Dives-as-code, share with teammates, or embed in an app.
- Explore the live schema and validate the core SQL first.
- Call
get_dive_guideif MCP is available, then design the story, sections, interactions, and theme. - Build or edit the Dive component, using local preview/hot reload when possible.
- Call
save_dive,update_dive, or deploy only after queries, loading states, required resources, and visual behavior are correct. - If teammates or application users need access, configure the underlying shares or embed-session flow explicitly.
Open Next
- Read
references/DIVE_DESIGN_GUIDE.mdfor authoring workflows,useSQLQuerymechanics, Dives-as-code, editing/version history, sharing, embedding, SQL functions, theming prompts, chart-selection rules, loading/error states, layout patterns, and implementation gotchas
Related Skills
motherduck-explorefor discovering the real tables, views, and dimensions before visualizing themmotherduck-queryfor validating the SQL each Dive section will runmotherduck-build-dashboardwhen the work is really a multi-section dashboard composition problemmotherduck-build-cfa-appwhen the requirement is a fuller product surface with per-customer isolation or backend policy control
Related Skills
motherduckdb/motherduck-create-flight
development
VerifiedTrustedCommunity
Create, schedule, run, and debug MotherDuck Flights — Python jobs that run on MotherDuck compute. Use whenever someone wants to create a flight, schedule a Python script or recurring job on MotherDuck, set up scheduled ingestion from Postgres, dlt sources, S3, BigQuery, Snowflake, or APIs, refresh aggregates or transformations on a cron, or operate flights with get_flight_guide, create_flight, run_flight, flight logs, secrets, schedules, and versions.
30SKILL.mdUpdated Jun 11, 2026
motherduckdb/motherduck-create-flight
development
VerifiedTrustedCommunity
Create, schedule, run, and debug MotherDuck Flights — Python jobs that run on MotherDuck compute. Use whenever someone wants to create a flight, schedule a Python script or recurring job on MotherDuck, set up scheduled ingestion from Postgres, dlt sources, S3, BigQuery, Snowflake, or APIs, refresh aggregates or transformations on a cron, or operate flights with get_flight_guide, create_flight, run_flight, flight logs, secrets, schedules, and versions.
30SKILL.mdUpdated Jun 11, 2026
motherduckdb/motherduck-share-data
data-ai
VerifiedTrustedCommunity
Create and manage MotherDuck data shares for zero-copy, read-only data distribution. Use whenever someone wants to share a database with team members, another organization, or the public — covers CREATE SHARE, access/visibility/update modes, GRANT READ ON SHARE, attaching share URLs, UPDATE SHARE, and REFRESH DATABASE.
30SKILL.mdUpdated May 7, 2026
motherduckdb/motherduck-security-governance
development
VerifiedTrustedCommunity
Explain MotherDuck security, governance, and access-control patterns. Use for any question about SOC 2, GDPR, compliance, data residency, regions, SSO, service accounts, token handling, tenant isolation, sharing boundaries, snapshots and recovery, or governance posture — including when a security_compliance_owner, technical_owner, or application_builder is evaluating MotherDuck.
30SKILL.mdUpdated May 7, 2026