querying-data-lake

Name: querying-data-lake
Author: aws

2.4kinstalls190forks

How to install querying-data-lake?

aws/agent-toolkit-for-aws/querying-data-lake

$npx -y skills add aws/agent-toolkit-for-aws --skill querying-data-lake

Installs into the current project.

Summary

Execute and manage Athena SQL queries across default and federated catalogs (Glue, S3 Tables, Redshift). Triggers on phrases like: query data, run SQL, athena query, analyze table, SQL query, workgroup status, profile table, query Redshift catalog, query S3 Tables. Do NOT use for

Files · 1

View on GitHub

SKILL.md

1	# Query Data Lake
2
3	Execute SQL queries on Amazon Athena across default and federated catalogs (Glue, S3 Tables, Redshift) with workgroup selection, statement classification, and error recovery.
4
5	## Overview
6
7	Executes and manages Athena SQL queries across default and federated catalogs. Selects a workgroup, resolves target assets (delegating fuzzy references to `finding-data-lake-assets`), classifies statements for safety, and reports cost and data scanned. Use the AWS MCP server for sandboxed execution and audit logging; the same AWS CLI commands work directly when the MCP server is not available.
8
9	Constraints for parameter acquisition:
10
11	- You MUST accept a single optional argument: SQL text, a named-query name, a workgroup name, a catalog name, or `profile TABLE_NAME`
12	- You MUST accept the argument as direct text or a pointer to a file containing SQL
13	- You MUST ask the user for the target AWS region if not already set
14	- You MUST confirm the output S3 location before executing any non-trivial query
15	- You MUST respect the user's decision to abort at any step
16
17	## Common Tasks
18
19	### 1. Verify Dependencies
20
21	Check for required tools and AWS access before running queries.
22
23	Constraints:
24
25	- You MUST verify AWS MCP server tools are available (`aws___call_aws`) and run queries through them when present; fall back to AWS CLI only if the MCP server is unavailable
26	- You MUST NOT fall back to shell or Bash for query execution — results must be captured via the MCP tool or `aws athena` CLI so output location and cost are tracked
27	- You MUST confirm credentials with `aws sts get-caller-identity` and inform the user about any missing tools
28
29	### 2. Resolve Workgroup
30
31	Check caller identity, list workgroups, auto-select the best one (see [workgroup-selection.md](references/workgroup-selection.md)).
32
33	Constraints:
34
35	- You MUST select a workgroup before submitting any query (prevents output-location errors)
36	- You MUST present the selected workgroup and its output location to the user
37	- You MUST NOT auto-escalate to a different workgroup on failure without user confirmation
38
39	### 3. Resolve the Target Asset
40
41	If the user refers to a table by name, by business concept ("our quarterly report", "the sales data"), by S3 path, or by catalog without specifying the table, delegate to `finding-data-lake-assets` to return the concrete `database.table` (and catalog if non-default).
42
43	Constraints:
44
45	- You MUST NOT attempt to resolve fuzzy asset references with `athena list-data-catalogs` or by iterating `get-tables` — those miss federated catalogs and waste tokens
46	- You SHOULD skip this step only when the user provides a fully-qualified reference (exact `database.table`) or raw SQL they want executed as-is
47	- You MUST state the resolved asset explicitly before building the query: "Found [table] in [catalog]. Using this for the query."
48	- You SHOULD default to the default Glue catalog unless the user mentions "federated", "Redshift", "S3 Tables", or `finding-data-lake-assets` returns a different catalog
49
50	### 4. Discover Schema
51
52	For analytical queries, You SHOULD profile the target table before building the final query. You MUST show sample rows (`SELECT ... LIMIT 5`) as part of profiling.
53
54	### 5. Build Query
55
56	Table addressing depends on catalog type:
57
58	- Default Glue catalog: `database.table` (omit the catalog prefix for single-catalog queries). In cross-catalog queries, qualify default-catalog tables with `"awsdatacatalog".database.table`.
59	- Registered data source: `datasource.database.table`
60	- Unregistered Glue catalog: `"catalog/subcatalog".database.table`
61
62	### 6. Classify and Execute
63
64	Classify the SQL statement before executing:
65
66	\| Statement \| Behavior \|
67	\|---\|---\|
68	\| `SELECT`, `SHOW`, `DESCRIBE`, `EXPLAIN` \| Safe — execute \|
69	\| `INSERT`, `UPDATE`, `DELETE`, `DROP`, `ALTER`, `CREATE`, `TRUNCATE`, `MERGE` \| Destructive — warn the user and require explicit confirmation \|
70	\| Unsure \| Treat as destructive; confirm \|
71
72	Example tool call (via AWS MCP server):
73
74	```
75	aws___call_aws(command="aws athena start-query-execution --work-group <WORKGROUP_NAME> --query-string '<sql>' --query-execution-context Database=<db>")
76	```
77
78	For federated or S3 Tables catalogs, also set `Catalog=<CATALOG_PATH>` in the execution context (e.g. `Catalog=s3tablescatalog/<BUCKET_NAME>`).
79
80	Constraints:
81
82	- You MUST warn the user before executing when the target is Redshift-federat

People who liked this also viewed

6 picks

Type

querying-data-lake

2.4kinstalls190forks

View on GitHub

How to install querying-data-lake?

aws/agent-toolkit-for-aws/querying-data-lake

$npx -y skills add aws/agent-toolkit-for-aws --skill querying-data-lake

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Query Data Lake
2
3	Execute SQL queries on Amazon Athena across default and federated catalogs (Glue, S3 Tables, Redshift) with workgroup selection, statement classification, and error recovery.
4
5	## Overview
6
7	Executes and manages Athena SQL queries across default and federated catalogs. Selects a workgroup, resolves target assets (delegating fuzzy references to `finding-data-lake-assets`), classifies statements for safety, and reports cost and data scanned. Use the AWS MCP server for sandboxed execution and audit logging; the same AWS CLI commands work directly when the MCP server is not available.
8
9	Constraints for parameter acquisition:
10
11	- You MUST accept a single optional argument: SQL text, a named-query name, a workgroup name, a catalog name, or `profile TABLE_NAME`
12	- You MUST accept the argument as direct text or a pointer to a file containing SQL
13	- You MUST ask the user for the target AWS region if not already set
14	- You MUST confirm the output S3 location before executing any non-trivial query
15	- You MUST respect the user's decision to abort at any step
16
17	## Common Tasks
18
19	### 1. Verify Dependencies
20
21	Check for required tools and AWS access before running queries.
22
23	Constraints:
24
25	- You MUST verify AWS MCP server tools are available (`aws___call_aws`) and run queries through them when present; fall back to AWS CLI only if the MCP server is unavailable
26	- You MUST NOT fall back to shell or Bash for query execution — results must be captured via the MCP tool or `aws athena` CLI so output location and cost are tracked
27	- You MUST confirm credentials with `aws sts get-caller-identity` and inform the user about any missing tools
28
29	### 2. Resolve Workgroup
30
31	Check caller identity, list workgroups, auto-select the best one (see [workgroup-selection.md](references/workgroup-selection.md)).
32
33	Constraints:
34
35	- You MUST select a workgroup before submitting any query (prevents output-location errors)
36	- You MUST present the selected workgroup and its output location to the user
37	- You MUST NOT auto-escalate to a different workgroup on failure without user confirmation
38
39	### 3. Resolve the Target Asset
40
41	If the user refers to a table by name, by business concept ("our quarterly report", "the sales data"), by S3 path, or by catalog without specifying the table, delegate to `finding-data-lake-assets` to return the concrete `database.table` (and catalog if non-default).
42
43	Constraints:
44
45	- You MUST NOT attempt to resolve fuzzy asset references with `athena list-data-catalogs` or by iterating `get-tables` — those miss federated catalogs and waste tokens
46	- You SHOULD skip this step only when the user provides a fully-qualified reference (exact `database.table`) or raw SQL they want executed as-is
47	- You MUST state the resolved asset explicitly before building the query: "Found [table] in [catalog]. Using this for the query."
48	- You SHOULD default to the default Glue catalog unless the user mentions "federated", "Redshift", "S3 Tables", or `finding-data-lake-assets` returns a different catalog
49
50	### 4. Discover Schema
51
52	For analytical queries, You SHOULD profile the target table before building the final query. You MUST show sample rows (`SELECT ... LIMIT 5`) as part of profiling.
53
54	### 5. Build Query
55
56	Table addressing depends on catalog type:
57
58	- Default Glue catalog: `database.table` (omit the catalog prefix for single-catalog queries). In cross-catalog queries, qualify default-catalog tables with `"awsdatacatalog".database.table`.
59	- Registered data source: `datasource.database.table`
60	- Unregistered Glue catalog: `"catalog/subcatalog".database.table`
61
62	### 6. Classify and Execute
63
64	Classify the SQL statement before executing:
65
66	\| Statement \| Behavior \|
67	\|---\|---\|
68	\| `SELECT`, `SHOW`, `DESCRIBE`, `EXPLAIN` \| Safe — execute \|
69	\| `INSERT`, `UPDATE`, `DELETE`, `DROP`, `ALTER`, `CREATE`, `TRUNCATE`, `MERGE` \| Destructive — warn the user and require explicit confirmation \|
70	\| Unsure \| Treat as destructive; confirm \|
71
72	Example tool call (via AWS MCP server):
73
74	```
75	aws___call_aws(command="aws athena start-query-execution --work-group <WORKGROUP_NAME> --query-string '<sql>' --query-execution-context Database=<db>")
76	```
77
78	For federated or S3 Tables catalogs, also set `Catalog=<CATALOG_PATH>` in the execution context (e.g. `Catalog=s3tablescatalog/<BUCKET_NAME>`).
79
80	Constraints:
81
82	- You MUST warn the user before executing when the target is Redshift-federat

People who liked this also viewed

6 picks

Type