AGENT SKILL

service-integrations

Guides awswrangler DynamoDB, Timestream, OpenSearch, Neptune, QuickSight, CloudWatch, EMR, EMR Serverless, STS, Secrets Manager, and Chime workflows.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
service-integrations
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Guides awswrangler DynamoDB, Timestream, OpenSearch, Neptune, QuickSight, CloudWatch, EMR, EMR Serverless, STS, Secrets Manager, and Chime workflows.
disable-model-invocation
true

02 资源文件 5

03 SKILL.md 正文

Service Integrations

Use this sub-skill when the user is working with wr.dynamodb.*, wr.timestream.*, wr.opensearch.*, wr.neptune.*, wr.quicksight.*, wr.cloudwatch.*, wr.emr.*, wr.emr_serverless.*, wr.sts.*, wr.secretsmanager.*, or wr.chime.* workflows.

Typical triggers:

  • "write items to DynamoDB"
  • "query Timestream"
  • "index documents into OpenSearch"
  • "load data into Neptune"
  • "create a QuickSight dataset"
  • "search CloudWatch logs"
  • "create an EMR cluster or EMR Serverless app"
  • "get the current AWS account ID"
  • "read a secret from Secrets Manager"
  • "send a Chime message"

Read references/api-reference.md for the service-by-service function map. Read references/workflows.md for the common service patterns and the right mental model for each wrapper. Read references/troubleshooting.md for missing extras, permissions, service setup, and backend-specific failures. Use ../../scripts/check_runtime.py from the root skill when you need to verify optional extras before a workflow.

Include here

  • DynamoDB item and PartiQL helpers.
  • Timestream database, table, write, query, batch load, and unload helpers.
  • OpenSearch connection, indexing, and search helpers.
  • Neptune graph connect, execute, flatten, and bulk load helpers.
  • QuickSight resource listing, creation, description, and ingestion helpers.
  • CloudWatch Logs query, wait, read, filter, and stream description helpers.
  • EMR and EMR Serverless cluster/job/application helpers.
  • STS identity helpers.
  • Secrets Manager secret helpers.
  • Chime webhook message posting.

Exclude or route elsewhere

  • S3 file movement, S3 Tables, Delta Lake, and S3 Vectors go to s3-lakehouse.
  • Glue Catalog, Athena, Data Quality, and Clean Rooms go to catalog-and-query.
  • Relational database drivers, Redshift, and Data API workflows go to sql-connectors.
  • Runtime, extras, and Ray/Modin mode questions go to runtime-and-config.

Common user outcomes

A future agent should be able to:

  • decide whether a service needs moto, live AWS, or only a pure helper check,
  • use the right boto3 session and optional extra,
  • and avoid forcing a live AWS assumption when the local helper path is enough.

Shared references and scripts

  • references/api-reference.md
  • references/workflows.md
  • references/troubleshooting.md
  • scripts/smoke_dynamodb_moto.py
  • scripts/smoke_service_basics.py

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351