motherduck-partner-delivery
A workflow tool for consultants to deliver repeatable, isolated MotherDuck data architectures.
Install
mkdir -p .claude/skills/motherduck-partner-delivery && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11715" && unzip -o skill.zip -d .claude/skills/motherduck-partner-delivery && rm skill.zipInstalls to .claude/skills/motherduck-partner-delivery
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Deliver repeatable MotherDuck architectures across multiple clients. Use when a consultancy, agency, or multi-client product team needs to standardize isolation, provisioning, regional deployment, sharing boundaries, and client-specific exceptions across client engagements.Key capabilities
- →Inspect active MotherDuck servers or supplied client contexts
- →Classify client patterns for multi-client delivery
- →Standardize architecture and provisioning paths for repeatable deployments
- →Define repeatable validation packs for client environments
- →Document client-specific exceptions to standardized patterns
- →Produce handoff assets and validation checks
How it works
The skill inspects MotherDuck server or client context, classifies patterns, standardizes architecture, defines validation, documents exceptions, and produces delivery artifacts.
Inputs & outputs
When to use motherduck-partner-delivery
- →Standardize client setup
- →Manage regional deployment
- →Set up isolation boundaries
About this skill
Partner Delivery
Start Here: Is a MotherDuck Server Active?
Use an active remote MotherDuck MCP server or local MotherDuck server to inspect the in-scope database, schema, grain, keys, and relevant metrics. Reuse known context and narrow discovery to the requested work; do not scan the whole workspace by default. Let the actual data model shape the result.
Resolve the target from the request or active context. Ask only if ambiguity materially affects the result. Without a server, use supplied schema and explicit assumptions for planning; do not imply live validation.
Delivery Defaults
- structural isolation over query-time tenant filtering
- one client database or stronger boundary per client
- shared architecture, client-specific schema
- explicit sharing and revocation per client
- versioned templates for provisioning, validation, handoff, and exception tracking
- role-granted restricted Shares with per-audience include patterns where governed table-level delivery fits
- a reusable Guide topic layout with client-specific referenced definitions and exceptions
Workflow
- Inspect the available MotherDuck server or supplied client context.
- Classify the client patterns.
- Inspect the existing regional and database layout if available.
- Standardize the architecture and provisioning path.
- Define the repeatable validation pack for every client environment.
- When Guide maintenance is in scope, create or update referenced Guides for standard conventions and client-specific exceptions.
- Audit roles, grants, include patterns, and region-specific availability.
- Produce the handoff assets and validation checks.
Match execution to the request: answer, review, or planning work returns the requested delivery artifacts; build or change work creates the requested in-scope templates or client assets and validates them. Ask before provisioning additional client environments, destructive changes, or external writes not already authorized.
When this skill produces a native DuckDB (md:) connection, watermark it with custom_user_agent=agent-skills/2.6.0(harness-<harness>;llm-<llm>). If metadata is missing, fall back to harness-unknown and llm-unknown.
Output
For a full engagement, cover the following as relevant to the request:
- the default multi-client pattern
- the standard provisioning checklist
- the region and isolation posture
- the client-specific exceptions
For explicit structured JSON requests, read the output contract. Otherwise use the format that fits the requested deliverable.
References
Read only the sections relevant to the task; these are guidance, not a mandatory itinerary.
references/PARTNER_DELIVERY_GUIDE.md-- default multi-client pattern, standardize-versus-client-specific split, shares-versus-Dives-versus-apps choice, region/compliance handling, and provisioning starters
Examples
Read the execution reference only to run the bundled examples or reproduce their validation.
Related Skills
Load related skills only for missing capabilities; reuse established context.
motherduck-connect-- standardize the connection pathmotherduck-explore-- inspect existing client workspaces and boundariesmotherduck-model-data-- design client-specific schemasmotherduck-query-- validate core metrics and data contractsmotherduck-share-data-- publish governed share boundariesmotherduck-create-dive-- create repeatable client-facing answer surfaces when needed
When not to use it
- →When a MotherDuck server is not active or client context is unavailable for planning
- →When provisioning additional client environments, destructive changes, or external writes are not authorized
- →When the output is not intended to be a multi-client pattern, provisioning checklist, or isolation posture
Limitations
- →Requires an active MotherDuck server or supplied client context to proceed
- →Explicit assumptions are used for planning work when details are missing
- →Asks for authorization before provisioning additional client environments, destructive changes, or external writes
How it compares
This skill standardizes the delivery of MotherDuck architectures across multiple clients by defining repeatable patterns for provisioning, validation, and exception handling, unlike a manual, client-by-client setup.
Compared to similar skills
motherduck-partner-delivery side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| motherduck-partner-delivery (this skill) | 0 | 3mo | Review | Advanced |
| estoque-inventory | 0 | 3mo | Review | Beginner |
| azure-data-explorer | 0 | 3mo | No flags | Advanced |
| backend-development | 17 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
estoque-inventory
migueldsants
Gerencia o inventário do mini-ERP Estoque — listar/buscar itens, criar/editar, ajustar quantidade, sinalizar estoque baixo e somar totais via a API REST local.
azure-data-explorer
vinodrex
Expert knowledge for Azure Data Explorer development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring ADX clusters, KQL/T-SQL queries, ingestion p
backend-development
skillcreatorai
Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.
laravel-specialist
Jeffallan
Use when building Laravel 10+ applications requiring Eloquent ORM, API resources, or queue systems. Invoke for Laravel models, Livewire components, Sanctum authentication, Horizon queues.
writing-hashql-jexpr
hashintel
HashQL J-Expr syntax for writing queries. Use when writing J-Expr code, using #literal/#struct/#list constructs, understanding function call syntax, or working with HashQL query files (.jsonc).
supabase-python
alinaqi
FastAPI with Supabase and SQLAlchemy/SQLModel