Instructions
When To Use This Skill
Before ANY Honeydew work, set up your session and discover the model:
Step 0: Set workspace and branch
Use get_session_workspace_and_branch to check the current session context. If no workspace/branch is set, use list_workspaces, list_workspace_branches, and set_session_workspace_and_branch to select the right workspace and branch. All subsequent tool calls use this context. See the workspace-branch skill for the full tool reference including branch creation, deletion, history, and PRs.
Step 1: List entities
Use the list_entities MCP tool to see all entities in the model.
Step 2: Explore entity details
Use the get_entity MCP tool with the relevant entity name to list its attributes, metrics, datasets, and relations.
Step 3: Search the model
Use the search_model MCP tool to find specific fields, entities, or other objects by name.
Overview
Honeydew is the Semantic Layer for AI and BI. Honeydew enables a shared source of truth for data teams, providing consistency, flexibility, governance and performance.
It provides metrics and attributes over data warehouse tables and views (Snowflake, Databricks, BigQuery) that have relationships defined between them.
Use the Honeydew MCP tools to interact with the model.
MCP Tools
Session & Workspace
See the workspace-branch skill for the full reference. Key tools:
list_workspaces - List all available workspaces (name + warehouse type)
list_workspace_branches - List branches for a workspace
get_session_workspace_and_branch - Get current session workspace/branch
set_session_workspace_and_branch - Set session workspace/branch
create_workspace_branch - Create a branch (session switches automatically)
delete_workspace_branch - Delete a branch (destructive — confirm with user first)
get_branch_history - Get change history for the current branch
create_pr_for_working_branch - Create a PR for the current working branch
Typical flow:
get_session_workspace_and_branch — check if a workspace/branch is already set
- If not set:
list_workspaces → pick a workspace → set_session_workspace_and_branch
- For development work:
create_workspace_branch (session switches to the new branch automatically)
Discovery
list_entities - List all entities in the model (names, keys, descriptions)
get_entity - Get detailed info for a specific entity (attributes, metrics, datasets, relations, YAML)
get_field - Get detailed info for a specific field (attribute or metric) within an entity
list_domains - List all domains with their names, descriptions, and entities
get_domain - Get detailed info for a specific domain (entities, filters, parameters, YAML)
search_model - Search across all model objects (entities, attributes, metrics, datasets, dynamic datasets, domains, parameters). Requires query and search_mode:
OR — splits by whitespace, returns objects matching any word
AND — splits by whitespace, returns only objects matching all words
EXACT — uses the full string as-is, matches name or display name exactly
- Use
entity.field syntax to scope to fields within an entity (e.g. customers.balance finds balance on entities matching customers; customers. returns all fields of matching entities)
Agents & Context
Honeydew has two layers: the semantic layer (entities, metrics, attributes, relations, domains — the data model and business logic such as metric calculations) and the context layer (agents and their associated context items — instructions, skills, knowledge, and memory — that shape how the AI analyst behaves).
list_agents — List all agents with their names, descriptions, domains, and context references
get_agent — Get detailed info for a specific agent (domain, context items, welcome message, sample questions)
list_context_items — List all context items with their types, names, titles, and subtypes
get_context_item — Get detailed info for a specific context item
Warehouse Discovery
list_databases - List all databases in the connected data warehouse
list_schemas - List schemas in a specific database
list_tables - List tables in the connected data warehouse (requires database and schema parameters)
get_table_info - Get column-level details for a specific warehouse table
Query Execution
get_data_from_fields - Execute a query from field parameters and return data (supports limit and offset for pagination)
get_sql_from_fields - Generate SQL from field parameters without executing
Example Usage
Structured Query Execution
Use get_data_from_fields to run structured queries in the context of model exploration — e.g. spot-check field values, verify counts, check a metric's computed value, or sample rows after discovering fields.
Call get_data_from_fields with:
attributes: ["order_header.order_year_month"]
metrics: ["order_header.total_revenue"]
filters: ["order_header.order_year_month LIKE '2021%'"]
order_by: ["\"order_header.order_year_month\" ASC"] — field references must be wrapped in double quotes, like SQL identifiers
domain: "my_domain" (optional)
limit: max rows to return (default: 100)
offset: rows to skip (for pagination)
get_sql_from_fields (SQL Preview)
Same field parameters as get_data_from_fields, but returns the generated SQL without executing it — useful for investigating how Honeydew resolves a specific query.
Analysis Questions
For natural language questions, trends, "why", or multi-step investigation — use the query skill (initiate_analysis + monitor_analysis).
Discovery Examples
- Use
list_entities to list all entities
- Use
get_entity with an entity name to see its attributes, metrics, datasets, and relations
- Use
get_field with entity name and field name to get detailed info about a specific field
- Use
list_domains to list all domains
- Use
get_domain with a domain name to see its entities, filters, parameters, and YAML definition
- Use
search_model with a query string and search_mode (OR, AND, or EXACT) to find any model object by name. Use EXACT when you know the precise name; use OR or AND for broad discovery
Documentation Lookup
Use the honeydew-docs MCP tools to search the Honeydew documentation when:
- The user asks conceptual questions ("what is an entity?", "how do metrics work?", "what is a semantic layer?")
- You need to explain Honeydew concepts, architecture, or terminology
- The user is new to Honeydew and needs orientation on capabilities
- You need to understand how a feature works beyond what the MCP tool descriptions provide
- The user asks about advanced modeling concepts or patterns
- The user asks about integrations, setup, or configuration
Search for topics like: "entities", "metrics", "attributes", "domains", "relations", "semantic layer", "governance", or any Honeydew-specific concept.
Best Practices
- Use
get_entity to explore fields on a specific entity
- Reference fields using
entity.field_name syntax
- Use discovery tools before any creation tasks
- For creating entities, metrics, attributes, or relations - use the specialized skills listed above
1---2name: model-exploration3description: Use when exploring Honeydew semantic layer, discovering entities/fields, setting up workspace and branch context, or running simple structured queries to inspect data. For analysis questions use the query skill. For creating metrics use metric-creation skill. For creating attributes use attribute-creation skill.4metadata:5 source: https://skillmd.com/skills/zuoguyoupan2023/model-exploration6---78# Instructions910## When To Use This Skill1112Before ANY Honeydew work, set up your session and discover the model:1314**Step 0: Set workspace and branch**15Use `get_session_workspace_and_branch` to check the current session context. If no workspace/branch is set, use `list_workspaces`, `list_workspace_branches`, and `set_session_workspace_and_branch` to select the right workspace and branch. All subsequent tool calls use this context. See the `workspace-branch` skill for the full tool reference including branch creation, deletion, history, and PRs.1617**Step 1: List entities**18Use the `list_entities` MCP tool to see all entities in the model.1920**Step 2: Explore entity details**21Use the `get_entity` MCP tool with the relevant entity name to list its attributes, metrics, datasets, and relations.2223**Step 3: Search the model**24Use the `search_model` MCP tool to find specific fields, entities, or other objects by name.2526---2728## Overview2930Honeydew is the Semantic Layer for AI and BI. Honeydew enables a shared source of truth for data teams, providing consistency, flexibility, governance and performance.31It provides metrics and attributes over data warehouse tables and views (Snowflake, Databricks, BigQuery) that have relationships defined between them.32Use the Honeydew MCP tools to interact with the model.3334## MCP Tools3536### Session & Workspace3738See the `workspace-branch` skill for the full reference. Key tools:3940- `list_workspaces` - List all available workspaces (name + warehouse type)41- `list_workspace_branches` - List branches for a workspace42- `get_session_workspace_and_branch` - Get current session workspace/branch43- `set_session_workspace_and_branch` - Set session workspace/branch44- `create_workspace_branch` - Create a branch (session switches automatically)45- `delete_workspace_branch` - Delete a branch (destructive — confirm with user first)46- `get_branch_history` - Get change history for the current branch47- `create_pr_for_working_branch` - Create a PR for the current working branch4849**Typical flow:**50511. `get_session_workspace_and_branch` — check if a workspace/branch is already set522. If not set: `list_workspaces` → pick a workspace → `set_session_workspace_and_branch`533. For development work: `create_workspace_branch` (session switches to the new branch automatically)5455### Discovery5657- `list_entities` - List all entities in the model (names, keys, descriptions)58- `get_entity` - Get detailed info for a specific entity (attributes, metrics, datasets, relations, YAML)59- `get_field` - Get detailed info for a specific field (attribute or metric) within an entity60- `list_domains` - List all domains with their names, descriptions, and entities61- `get_domain` - Get detailed info for a specific domain (entities, filters, parameters, YAML)62- `search_model` - Search across all model objects (entities, attributes, metrics, datasets, dynamic datasets, domains, parameters). Requires `query` and `search_mode`:63 - `OR` — splits by whitespace, returns objects matching any word64 - `AND` — splits by whitespace, returns only objects matching all words65 - `EXACT` — uses the full string as-is, matches name or display name exactly66 - Use `entity.field` syntax to scope to fields within an entity (e.g. `customers.balance` finds `balance` on entities matching `customers`; `customers.` returns all fields of matching entities)6768### Agents & Context6970Honeydew has two layers: the **semantic layer** (entities, metrics, attributes, relations, domains — the data model and business logic such as metric calculations) and the **context layer** (agents and their associated context items — instructions, skills, knowledge, and memory — that shape how the AI analyst behaves).7172- `list_agents` — List all agents with their names, descriptions, domains, and context references73- `get_agent` — Get detailed info for a specific agent (domain, context items, welcome message, sample questions)74- `list_context_items` — List all context items with their types, names, titles, and subtypes75- `get_context_item` — Get detailed info for a specific context item7677### Warehouse Discovery7879- `list_databases` - List all databases in the connected data warehouse80- `list_schemas` - List schemas in a specific database81- `list_tables` - List tables in the connected data warehouse (requires `database` and `schema` parameters)82- `get_table_info` - Get column-level details for a specific warehouse table8384### Query Execution8586- `get_data_from_fields` - Execute a query from field parameters and return data (supports `limit` and `offset` for pagination)87- `get_sql_from_fields` - Generate SQL from field parameters without executing8889## Example Usage9091### Structured Query Execution9293Use `get_data_from_fields` to run structured queries in the context of model exploration — e.g. spot-check field values, verify counts, check a metric's computed value, or sample rows after discovering fields.9495Call `get_data_from_fields` with:9697- `attributes`: `["order_header.order_year_month"]`98- `metrics`: `["order_header.total_revenue"]`99- `filters`: `["order_header.order_year_month LIKE '2021%'"]`100- `order_by`: `["\"order_header.order_year_month\" ASC"]` — field references must be wrapped in double quotes, like SQL identifiers101- `domain`: `"my_domain"` (optional)102- `limit`: max rows to return (default: 100)103- `offset`: rows to skip (for pagination)104105### get_sql_from_fields (SQL Preview)106107Same field parameters as `get_data_from_fields`, but returns the generated SQL without executing it — useful for investigating how Honeydew resolves a specific query.108109### Analysis Questions110111For natural language questions, trends, "why", or multi-step investigation — use the **query** skill (`initiate_analysis` + `monitor_analysis`).112113---114115### Discovery Examples116117- Use `list_entities` to list all entities118- Use `get_entity` with an entity name to see its attributes, metrics, datasets, and relations119- Use `get_field` with entity name and field name to get detailed info about a specific field120- Use `list_domains` to list all domains121- Use `get_domain` with a domain name to see its entities, filters, parameters, and YAML definition122- Use `search_model` with a query string and `search_mode` (`OR`, `AND`, or `EXACT`) to find any model object by name. Use `EXACT` when you know the precise name; use `OR` or `AND` for broad discovery123124## Documentation Lookup125126Use the `honeydew-docs` MCP tools to search the Honeydew documentation when:127128- The user asks conceptual questions ("what is an entity?", "how do metrics work?", "what is a semantic layer?")129- You need to explain Honeydew concepts, architecture, or terminology130- The user is new to Honeydew and needs orientation on capabilities131- You need to understand how a feature works beyond what the MCP tool descriptions provide132- The user asks about advanced modeling concepts or patterns133- The user asks about integrations, setup, or configuration134135Search for topics like: "entities", "metrics", "attributes", "domains", "relations", "semantic layer", "governance", or any Honeydew-specific concept.136137---138139## Best Practices1401411. Use `get_entity` to explore fields on a specific entity1422. Reference fields using `entity.field_name` syntax1433. Use discovery tools before any creation tasks1444. For creating entities, metrics, attributes, or relations - use the specialized skills listed above