Find the best CLAUDE.md, AGENTS.md and Claude skills

AWSAGENTS.md

aws-cdk

aws/aws-cdk/AGENTS.md

Contributor-focused guide for AI agents working on the AWS CDK codebase. AWS CDK is an open-source framework that lets developers define cloud infrastructure in code and provision it through AWS CloudFormation. This is a TypeScript monorepo that uses jsii to generate bindings for Python, Java, .NET, and Go. Constructs follow a layered model: L1 (auto-generated CloudFormation wrappers), L2 (intent-based APIs with smart defaults), and L3 (multi-resource patterns). See CONTRIBUTING.md for the full contributor guide. You are a CDK contributor. You…

AWSCLAUDE.md

aws-cdk

aws/aws-cdk/CLAUDE.md

No summary in the file. Open it to read it.

AWSSkill

cdk-construct-design-review

aws/aws-cdk/skills/cdk-review/cdk-construct-design-review/SKILL.md

AWS CDK construct/API design-quality reviewer. Use when a PR adds or changes a public construct, its props/methods/attributes, or introduces a new L2 — reviewing DESIGN quality beyond correctness across feature-placement/abstraction, Design-Guidelines conformance, clarity/simplicity/consistency, and footgun-free/ages-well interface quality. Leading concept: the construct is correct AND well-designed, intuitive, footgun-free, and ages well.

AWSSkill

cdk-documentation-review

aws/aws-cdk/skills/cdk-review/cdk-documentation-review/SKILL.md

AWS CDK documentation-quality reviewer. Use when a PR changes a doc surface the CDK design guidelines govern — `@default`/`@attribute`/`@param` JSDoc tags, public-API docs, migration notes, README usage examples, and rosetta `*.ts-fixture` files and fenced `ts` snippets. Leading concept: docs must be TRUE and COMPLETE against the CDK design guidelines, so a doc that misstates a default, is missing where a guideline requires it, or won't compile is a defect with the standing of a code defect — never prose or wording quality.

AWSSkill

cdk-regression-review

aws/aws-cdk/skills/cdk-review/cdk-regression-review/SKILL.md

AWS CDK regression + breaking-change reviewer. Use when reviewing an AWS CDK pull request for both regression risks (input-validation, token-handling, JSII-transpilation, and other undefined runtime-behavior breakage) AND breaking changes (API-surface changes that fail to compile, behavior/template-synthesis changes, and library-stability-policy violations) introduced BY the PR.

AWSSkill

cdk-review-principles

aws/aws-cdk/skills/cdk-review/cdk-review-principles/SKILL.md

Shared foundation every CDK review-dimension skill applies — the harm-based severity scale (BLOCKING/RECOMMENDED/OPTIONAL), evidence + citation authority order, exact file:line, the concrete-fix rule, the 3-7 comment budget, review tone, the shared what-NOT-to-flag exclusions, the finding-output contract (ruleId + reference fields), and the rules-lookup convention. Apply whenever conducting a CDK PR review, rating a finding's severity, deciding whether something is a finding at all, or turning a finding into a posted comment.

AWSSkill

cdk-security-review

aws/aws-cdk/skills/cdk-review/cdk-security-review/SKILL.md

AWS CDK security reviewer. Use when reviewing an AWS CDK pull request for security exposure introduced BY the PR — across IAM least-privilege, network/resource access, secrets/credentials, and secure-by-default changes. Triggers on changes to IAM/KMS/Secrets Manager/certificates, network config, or other security-sensitive services. Leading concepts: least-privilege and secure-by-default.

AWSSkill

cdk-testing-review

aws/aws-cdk/skills/cdk-review/cdk-testing-review/SKILL.md

AWS CDK test-coverage reviewer. Use when a PR adds or changes tests (`**/*.test.ts`, `integ.*.ts`, `*.snapshot`) or ships new functionality, branches, feature-flag states, CFN properties, or cross-service behavior that should be tested — deciding first what coverage each change OWES (a unit test? an integ test? both? already covered? exempt?), then judging whether the PR's tests DISCHARGE it: meaningful assertions over non-asserting tests, edge/negative/feature-flag cases, required integ tests, snapshot-as-synthesized-template diffs, deploy-time assertions, and legitimate exemptions.

AWSAGENTS.md

amazon-sagemaker-examples

aws/amazon-sagemaker-examples/AGENTS.md

Guidance for AI coding agents (Cursor, GitHub Copilot, Claude Code, Amazon Q Developer, Kiro, Codex, Gemini CLI, etc.) working in this repository. Follows the AGENTS.md convention (https://agents.md). This repository contains example notebooks for the Amazon SageMaker Python SDK v3. pip install sagemaker installs v3. SDK v3 is a modular redesign and is not backward compatible with v2. It is split into: Generate SageMaker Python SDK v3 code by default. Produce v2 code only when the user explicitly asks for "v2"…

AWSllms.txt

amazon-sagemaker-examples

aws/amazon-sagemaker-examples/llms.txt

Example notebooks for building, training, and deploying models with the Amazon SageMaker Python SDK v3. This repository targets v3 only; pip install sagemaker installs v3. SDK v3 is modular (sagemaker-core, sagemaker-train, sagemaker-serve, sagemaker-mlops) and is not backward compatible with v2. v2 examples are archived, not maintained. This file follows the llms.txt convention (https://llmstxt.org): a curated index plus explicit instructions so AI coding agents generate correct, current (v3) code. - SDK-first: for any SageMaker task (train, deploy, process, pipelines), use the…

No other project uses it yet