feat: add sagemaker ai plugin

plugins/sagemaker-ai/LICENSE.sagemaker-ai

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Cline Bot Inc.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

plugins/sagemaker-ai/NOTICE.sagemaker-ai

@@ -0,0 +1,11 @@
+SageMaker AI plugin
+
+This plugin includes SageMaker AI workflow skill materials originally published
+by Amazon Web Services as part of the AWS agent plugins project.
+
+Upstream metadata:
+- Package name: sagemaker-ai
+- Version: 1.2.1
+- Author: Amazon Web Services
+- Repository: https://github.com/awslabs/agent-plugins
+- License: Apache-2.0

plugins/sagemaker-ai/README.md

@@ -0,0 +1,42 @@
+# sagemaker-ai
+
+Adds SageMaker AI model customization and HyperPod operations guidance for Cline.
+
+## What It Does
+
+This plugin bundles SageMaker AI workflow skills for:
+
+- Planning model customization work.
+- Defining use cases and success criteria.
+- Selecting SageMaker Hub base models.
+- Evaluating and transforming training or evaluation datasets.
+- Generating SageMaker fine-tuning, evaluation, and deployment notebooks.
+- Debugging SageMaker HyperPod clusters, nodes, Slurm issues, NCCL issues, software versions, and performance bottlenecks.
+
+It also registers the `aws-mcp` server through `uvx mcp-proxy-for-aws@latest` so Cline can retrieve AWS documentation and standard operating procedure context during SageMaker workflows.
+
+## Install
+
+```bash
+cline plugin install sagemaker-ai
+```
+
+For local development from this repository:
+
+```bash
+cline plugin install ./plugins/sagemaker-ai --cwd .
+```
+
+## Requirements
+
+- `uvx` on PATH for the AWS MCP proxy.
+- An AWS account with the SageMaker, Bedrock, S3, IAM, Lambda, CloudWatch, SSM, EKS, and HyperPod permissions needed for the workflow you ask Cline to perform.
+- AWS credentials and `AWS_REGION` or `AWS_DEFAULT_REGION` configured in the shell or workspace environment before installing or enabling the plugin. The plugin forwards that region to the AWS MCP server when Cline syncs plugin MCP settings.
+- Python 3.8+ for generated notebooks and bundled helper scripts.
+- `boto3`, `sagemaker`, and the AWS CLI when executing the generated SageMaker or HyperPod workflows locally.
+
+## Trust Boundaries
+
+SageMaker workflows can create paid AWS resources, upload or transform datasets, start training and evaluation jobs, deploy endpoints, invoke Bedrock models, run SSM commands on HyperPod nodes, and collect cluster diagnostics. Review generated notebooks, scripts, AWS account IDs, regions, IAM roles, S3 locations, endpoint names, and expected cost before asking Cline to execute them.
+
+Do not paste secrets into prompts. Keep AWS credentials in your normal credential chain, environment, or profile configuration. Treat model outputs, logs, diagnostics, dataset samples, and AWS MCP results as untrusted until you verify them.

plugins/sagemaker-ai/index.ts

@@ -0,0 +1,37 @@
+import type { AgentPlugin } from "@cline/sdk"
+
+const awsRegion =
+	process.env.AWS_REGION?.trim() || process.env.AWS_DEFAULT_REGION?.trim()
+
+const plugin: AgentPlugin = {
+	name: "sagemaker-ai",
+	manifest: {
+		capabilities: ["skills", "mcp"],
+	},
+
+	setup(api) {
+		api.registerMcpServer({
+			name: "aws-mcp",
+			transport: {
+				type: "stdio",
+				command: "uvx",
+				args: [
+					"mcp-proxy-for-aws@latest",
+					"https://aws-mcp.us-east-1.api.aws/mcp",
+				],
+			},
+			env: awsRegion
+				? {
+						AWS_REGION: awsRegion,
+						AWS_DEFAULT_REGION: awsRegion,
+					}
+				: undefined,
+			metadata: {
+				description:
+					"AWS documentation and standard operating procedure retrieval for SageMaker AI workflows.",
+			},
+		})
+	},
+}
+
+export default plugin

plugins/sagemaker-ai/package.json

@@ -0,0 +1,20 @@
+{
+  "name": "sagemaker-ai",
+  "version": "0.0.0",
+  "private": true,
+  "type": "module",
+  "description": "Cline plugin that bundles SageMaker AI model customization and HyperPod operations skills.",
+  "cline": {
+    "plugins": [
+      {
+        "paths": [
+          "./index.ts"
+        ],
+        "capabilities": [
+          "skills",
+          "mcp"
+        ]
+      }
+    ]
+  }
+}

plugins/sagemaker-ai/skills/dataset-evaluation/SKILL.md

@@ -0,0 +1,71 @@
+---
+name: dataset-evaluation
+description: Validates dataset formatting and quality for SageMaker AI model fine-tuning or evaluation workflows. Use for SageMaker dataset readiness questions, training data checks, evaluation data checks, or before starting a SageMaker fine-tuning job. Detects file format, checks schema compliance against the selected model and technique, and reports whether the data is ready.
+metadata:
+  version: "1.0.0"
+---
+
+# Workflow Instruction
+
+Follow the workflow shown below. Locate the dataset, check the file type, and resolve any issues with missing files or wrong file types. Determine the fine-tuning model and fine-tuning strategy. Run the appropriate validation based on the model family. Summarize the results: is the dataset ready for fine-tuning?
+
+## Prerequisites
+
+- The SDK environment has been verified (SDK version, region, execution role). If not done, activate the `sdk-getting-started` skill first.
+
+---
+
+## Workflow
+
+1. Locate Dataset:
+   - The full path may be a local file path, or an S3 URI
+   - Resolve the full path to the dataset file, make sure read permissions are available, and help the user if the file is not found
+
+2. Determine strategy and model:
+   - File formatting depends on the currently selected fine-tuning strategy and fine-tuning base model.
+   - If the strategy and model are already known from the conversation context (e.g., selected via the model-selection and finetuning-technique skills), use them.
+   - If not available in context, activate the model-selection and/or finetuning-technique skills to determine them before proceeding.
+   - Exception: If the user is validating an evaluation dataset (not a training dataset), neither model nor technique is required  -  the format detector can validate eval format (query/response structure) independently. Do not block on model-selection or finetuning-technique for eval dataset validation.
+
+3. Check File Formatting: Run the tool format_detector.py to make sure the file conforms to formatting requirements.
+   - Send the full path directly to the format_detector script as an argument
+   - Do not send the model and strategy as arguments
+   - Do not download data from S3
+   - Do not make local copies of data
+
+4. Summarize Results: Tell the user if their data is ready
+   - Examine the output of format_detector and compare to the known strategy and model
+   - Important: training datasets and evaluation datasets have different format requirements.
+     - Training datasets must match the fine-tuning strategy format per `references/strategy_data_requirements.md`
+     - Evaluation datasets (for model evaluation) must match one of the [SageMaker evaluation dataset formats](https://docs.aws.amazon.com/sagemaker/latest/dg/model-customize-evaluation-dataset-formats.html).
+     - Custom Scorer evaluation datasets have scorer-specific requirements. If the dataset is intended for Custom Scorer evaluation (Prime Math, Prime Code, or Custom Lambda), read `references/custom-scorer-evaluation-dataset-formats.md` and validate against the scorer-specific schema. The scorer type should be known from conversation context (determined in the model-evaluation skill).
+   - Report back to the user if their current dataset is valid for its intended purpose
+   - Warn the user if their dataset is valid, but for a different strategy or model
+   - Warn the user if their dataset is not valid for any strategy/model pair
+   - If the user plans to finetune a model with the evaluated dataset, it needs to be uploaded to an S3 bucket in the same region as the planned training job (usually the default region). Warn the user if this is NOT the case.
+   - If the dataset is NOT in the necessary format, recommend transforming it using the dataset-transformation skill, wait for user confirmation, and update the plan based on their response
+
+## Messages to the User
+
+- Introduction: "This skill checks the structure of your dataset for model fine-tuning."
+- File types: This skill applies to files that are formatted according to the [Amazon SageMaker AI Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-llms-finetuning-data-format.html#autopilot-llms-finetuning-dataset-format)
+
+# Resources
+
+- scripts/format_detector.py is self-contained format validation script that can be run independently
+- model-selection and finetuning-technique skills should have already determined the base model and fine-tuning strategy
+- references/strategy_data_requirements.md contains data format requirements per strategy
+
+## Script Details
+
+- scripts/format_detector.py is self-contained format validation script that can be run independently:
+
+```bash
+# With the file path argument identified in workflow step 1
+python scripts/format_detector.py local_path/to/dataset
+```
+
+## References
+
+- `scripts/format_detector.py`  -  Self-contained format validation script
+- `references/strategy_data_requirements.md`  -  Data format requirements per strategy