复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
Supercharge Claude Code with AWS cloud engineering skills across 18 core AWS services.
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
来源文件:README.md
Supercharge Claude Code with AWS cloud engineering skills across 18 core AWS services.
Developing AWS solutions is complex spanning IAM, compute, storage, security, serverless, networking, and more.
AWS Agent Skills equips Claude Code (and Codex) with deep expertise across 18 AWS domains, enabling automated cloud engineering support from IaC templates to debugging guidance and security best practices.
Automatically checks AWS documentation for updates on a weekly basis to ensure skills stay current with AWS service changes.
AWS MCP is great for live docs and API calls, but AWS Agent Skills is designed for reasoning first. It gives AI Agents a curated, LLM-optimized AWS knowledge base with real-world patterns, edge cases, and best practices, without streaming large docs or schemas. Because the skills are local and pre compressed, it is far more token efficient, keeps the context window small and predictable, and avoids MCP infrastructure, latency, and expanded credential exposure.
# Add the marketplace
/plugin marketplace add itsmostafa/aws-agent-skills
# Install the plugin
/plugin install aws-agent-skills
/plugin install https://github.com/itsmostafa/aws-agent-skills
/plugin install ./path/to/aws-agent-skills
$skill-installer install https://github.com/itsmostafa/aws-agent-skills/<skill-name>
For example, to install the rlhf skill:
$skill-installer install https://github.com/itsmostafa/aws-agent-skills/rlhf
| Skill | Description |
|---|---|
| iam | Identity and Access Management - users, roles, policies, permissions |
| lambda | Serverless functions - deployment, triggers, debugging |
| dynamodb | NoSQL database - table design, queries, indexes |
| s3 | Object storage - buckets, objects, security, lifecycle |
| api-gateway | REST and HTTP APIs - integrations, authorization |
| ec2 | Virtual machines - instances, AMIs, networking |
| ecs | Container orchestration - clusters, services, tasks |
| eks | Kubernetes - clusters, node groups, IRSA |
| cloudformation | Infrastructure as Code - templates, stacks, drift |
| cloudwatch | Monitoring - logs, metrics, alarms, dashboards |
| rds | Relational databases - instances, backups, replication |
| sqs | Message queues - standard, FIFO, dead-letter queues |
| sns | Notifications - topics, subscriptions, filtering |
| cognito | User authentication - user pools, identity pools, OAuth |
| step-functions | Workflow orchestration - state machines, error handling |
| secrets-manager | Secret storage - rotation, versioning, RDS integration |
| eventbridge | Event bus - rules, patterns, cross-account events |
| bedrock | Foundation models - inference, RAG, custom models |
Ask Claude to help with IAM:
Each skill contains:
SKILL.md - Core concepts, patterns, CLI reference, best practices, troubleshootingSkills include metadata showing when content was last updated, so you always know how current the information is.
---
name: service-name
description: Service description. Use when <trigger phrases>.
---
# AWS Service Name
## Overview
## Core Concepts
## Common Patterns
## CLI Reference
## Best Practices
## Troubleshooting
## References
MIT License - see LICENSE for details.
name: s3
description: AWS S3 object storage for bucket management, object operations, and access control. Use when creating buckets, uploading files, configuring lifecycle policies, setting up static websites, managing permissions, or implementing cross-region replication.
last_updated: "2026-01-07"
doc_source: https://docs.aws.amazon.com/AmazonS3/latest/userguide/Amazon Simple Storage Service (S3) provides scalable object storage with industry-leading durability (99.999999999%). S3 is fundamental to AWS—used for data lakes, backups, static websites, and as storage for many other AWS services.
Containers for objects. Bucket names are globally unique across all AWS accounts.
Files stored in S3, consisting of data, metadata, and a unique key (path). Maximum size: 5 TB.
| Class | Use Case | Durability | Availability |
|---|---|---|---|
| Standard | Frequently accessed | 99.999999999% | 99.99% |
| Intelligent-Tiering | Unknown access patterns | 99.999999999% | 99.9% |
| Standard-IA | Infrequent access | 99.999999999% | 99.9% |
| Glacier Instant | Archive with instant retrieval | 99.999999999% | 99.9% |
| Glacier Flexible | Archive (minutes to hours) | 99.999999999% | 99.99% |
| Glacier Deep Archive | Long-term archive | 99.999999999% | 99.99% |
Keeps multiple versions of an object. Essential for data protection and recovery.
AWS CLI:
# Create bucket (us-east-1 doesn't need LocationConstraint)
aws s3api create-bucket \
--bucket my-secure-bucket-12345 \
--region us-west-2 \
--create-bucket-configuration LocationConstraint=us-west-2
# Enable versioning
aws s3api put-bucket-versioning \
--bucket my-secure-bucket-12345 \
--versioning-configuration Status=Enabled
# Block public access
aws s3api put-public-access-block \
--bucket my-secure-bucket-12345 \
--public-access-block-configuration \
BlockPublicAcls=true,IgnorePublicAcls=true,BlockPublicPolicy=true,RestrictPublicBuckets=true
# Enable encryption
aws s3api put-bucket-encryption \
--bucket my-secure-bucket-12345 \
--server-side-encryption-configuration '{
"Rules": [{"ApplyServerSideEncryptionByDefault": {"SSEAlgorithm": "AES256"}}]
}'
boto3:
import boto3
s3 = boto3.client('s3', region_name='us-west-2')
# Create bucket
s3.create_bucket(
Bucket='my-secure-bucket-12345',
CreateBucketConfiguration={'LocationConstraint': 'us-west-2'}
)
# Enable versioning
s3.put_bucket_versioning(
Bucket='my-secure-bucket-12345',
VersioningConfiguration={'Status': 'Enabled'}
)
# Block public access
s3.put_public_access_block(
Bucket='my-secure-bucket-12345',
PublicAccessBlockConfiguration={
'BlockPublicAcls': True,
'IgnorePublicAcls': True,
'BlockPublicPolicy': True,
'RestrictPublicBuckets': True
}
)
# Upload a single file
aws s3 cp myfile.txt s3://my-bucket/path/myfile.txt
# Upload with metadata
aws s3 cp myfile.txt s3://my-bucket/path/myfile.txt \
--metadata "environment=production,version=1.0"
# Download a file
aws s3 cp s3://my-bucket/path/myfile.txt ./myfile.txt
# Sync a directory
aws s3 sync ./local-folder s3://my-bucket/prefix/ --delete
# Copy between buckets
aws s3 cp s3://source-bucket/file.txt s3://dest-bucket/file.txt
import boto3
from botocore.config import Config
s3 = boto3.client('s3', config=Config(signature_version='s3v4'))
# Generate presigned URL for download (GET)
url = s3.generate_presigned_url(
'get_object',
Params={'Bucket': 'my-bucket', 'Key': 'path/to/file.txt'},
ExpiresIn=3600 # URL valid for 1 hour
)
# Generate presigned URL for upload (PUT)
upload_url = s3.generate_presigned_url(
'put_object',
Params={
'Bucket': 'my-bucket',
'Key': 'uploads/newfile.txt',
'ContentType': 'text/plain'
},
ExpiresIn=3600
)
cat > lifecycle.json << 'EOF'
{
"Rules": [
{
"ID": "MoveToGlacierAfter90Days",
"Status": "Enabled",
"Filter": {"Prefix": "logs/"},
"Transitions": [
{"Days": 90, "StorageClass": "GLACIER"}
],
"Expiration": {"Days": 365}
},
{
"ID": "DeleteOldVersions",
"Status": "Enabled",
"Filter": {},
"NoncurrentVersionExpiration": {"NoncurrentDays": 30}
}
]
}
EOF
aws s3api put-bucket-lifecycle-configuration \
--bucket my-bucket \
--lifecycle-configuration file://lifecycle.json
aws s3api put-bucket-notification-configuration \
--bucket my-bucket \
--notification-configuration '{
"LambdaFunctionConfigurations": [
{
"LambdaFunctionArn": "arn:aws:lambda:us-east-1:123456789012:function:ProcessS3Upload",
"Events": ["s3:ObjectCreated:*"],
"Filter": {
"Key": {
"FilterRules": [
{"Name": "prefix", "Value": "uploads/"},
{"Name": "suffix", "Value": ".jpg"}
]
}
}
}
]
}'
| Command | Description |
|---|---|
aws s3 ls | List buckets or objects |
aws s3 cp | Copy files |
aws s3 mv | Move files |
aws s3 rm | Delete files |
aws s3 sync | Sync directories |
aws s3 mb | Make bucket |
aws s3 rb | Remove bucket |
| Command | Description |
|---|---|
aws s3api create-bucket | Create bucket with options |
aws s3api put-object | Upload with full control |
aws s3api get-object | Download with options |
aws s3api delete-object | Delete single object |
aws s3api put-bucket-policy | Set bucket policy |
aws s3api put-bucket-versioning | Enable versioning |
aws s3api list-object-versions | List all versions |
--recursive: Process all objects in prefix--exclude/--include: Filter objects--dryrun: Preview changes--storage-class: Set storage class--acl: Set access control (prefer policies instead){
"Rules": [{
"ID": "AbortIncompleteMultipartUpload",
"Status": "Enabled",
"Filter": {},
"AbortIncompleteMultipartUpload": {"DaysAfterInitiation": 7}
}]
}
Causes:
Debug steps:
# Check your identity
aws sts get-caller-identity
# Check bucket policy
aws s3api get-bucket-policy --bucket my-bucket
# Check public access block
aws s3api get-public-access-block --bucket my-bucket
# Check object ownership
aws s3api get-object-attributes \
--bucket my-bucket \
--key myfile.txt \
--object-attributes ObjectOwner
Symptom: Browser blocks cross-origin request
Fix:
aws s3api put-bucket-cors --bucket my-bucket --cors-configuration '{
"CORSRules": [{
"AllowedOrigins": ["https://myapp.com"],
"AllowedMethods": ["GET", "PUT", "POST"],
"AllowedHeaders": ["*"],
"ExposeHeaders": ["ETag"],
"MaxAgeSeconds": 3600
}]
}'
Solutions:
aws s3 cp with --expected-size for large filesCauses:
Fix: Ensure signer has permissions and use correct region.
评论 (0)
暂无评论,成为第一个评论者吧!