⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

aws-agentcore

inceptionstack@inceptionstack⭐ 0 stars· last commit 6mo ago· 0 open issues

Build, test, and deploy AI agents using AWS Bedrock AgentCore with local development workflow. Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating effective agents.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 0 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

loki-skills

Skills library for AI agents — works with OpenClaw, Roundhouse, and any agent that supports the skill format.

Synced from Kiro Powers with custom additions. Each skill provides structured guidance (steering docs, reference material, and constraints) that help AI agents perform specialized tasks effectively.

Usage

OpenClaw: Clone into the workspace — skills are auto-discovered:

cd ~/.openclaw/workspace
git clone https://github.com/inceptionstack/loki-skills.git skills

Roundhouse / Pi: Clone and copy to pi agent skills:

git clone https://github.com/inceptionstack/loki-skills.git /tmp/loki-skills
for d in /tmp/loki-skills/*/; do
  [ -d "$d" ] && cp -r "$d" ~/.pi/agent/skills/
done

Skills

From Kiro Powers (upstream synced)

SkillDescription
arm-soc-migrationMigration between Arm SoC platforms
aws-agentcoreBuild agents with Amazon Bedrock AgentCore
aws-amplifyFull-stack apps with AWS Amplify Gen 2
aws-devops-agentAWS DevOps automation and CI/CD
aws-graviton-migrationCode compatibility with Graviton/Arm64
aws-healthomicsGenomics workflows in AWS HealthOmics
aws-infrastructure-as-codeCDK + CloudFormation best practices
aws-mcpMulti-step AWS tasks with MCP server
aws-observabilityCloudWatch, X-Ray, Application Signals
aws-samServerless Application Model
aws-step-functionsAWS Step Functions workflows
aws-transformAWS application modernization/transformation
checkoutCheckout.com payments API
cloud-architectAWS infrastructure (Well-Architected)
cloudwatch-application-signalsCloudWatch Application Signals
datadogDatadog observability
dynatraceDynatrace observability via DQL
gcp-aws-migrateGCP to AWS migration
neonServerless Postgres with Neon
postmanAPI testing with Postman
power-builderBuild new Kiro powers
saas-builderMulti-tenant SaaS apps
spark-troubleshooting-agentSpark on EMR/Glue troubleshooting
stackgenStackGen infrastructure generation
strandsAI agents with Strands SDK
stripeStripe payment integrations
terraformInfrastructure as Code with Terraform

Custom (loki-only)

SkillDescription
claude-agent-sdkBuild AI agents using Claude Agent SDK
cross-agent-testZero-context cross-agent testing of CLI tools
lambda-durableAWS Lambda durable functions

Sync with upstream

git clone --depth 1 https://github.com/kirodotdev/powers.git /tmp/powers
# Copy new/updated skills, preserve custom ones

Last synced: 2026-05-07

License

Skills derived from Kiro Powers retain the licensing terms of their original sources. Custom skills are provided as-is.

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • aws-agentcore/SKILL.md4.7 KBupstream ↗
    ---
    name: "aws-agentcore"
    displayName: "Build an agent with Amazon Bedrock AgentCore"
    description: "Build, test, and deploy AI agents using AWS Bedrock AgentCore with local development workflow. Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating effective agents."
    keywords: ["agentcore", "bedrock", "aws", "agents", "ai", "development", "agent"]
    author: "AWS"
    ---
    
    # AWS Bedrock AgentCore
    
    ## Overview
    
    Build and deploy AI agents using AWS Bedrock AgentCore with a complete local development workflow. This power provides access to AgentCore documentation, runtime management, memory operations, and gateway configuration through MCP tools, plus comprehensive guidance for the create-dev-test-deploy cycle.
    
    AgentCore supports multiple agent SDKs (Strands, Claude, OpenAI) and model providers (Bedrock, OpenAI), with infrastructure deployment via CDK or Terraform.
    
    ## When to Use This Power
    
    - Building a new agent from scratch with `agentcore create`
    - Getting started with agent development and need guidance on the workflow
    - Deploying an existing agent to AgentCore runtime
    - Integrating AgentCore primitives (Memory, Gateway) into an existing agent
    - Starting local development servers with hot reloading
    - Testing agents locally before cloud deployment
    - Searching AgentCore documentation
    - Managing agent runtime, memory, and gateway configurations
    - Deploying agents to AWS
    - Working with Strands agents framework
    
    ## Available MCP Tools
    
    This power provides the agentcore-mcp-server:
    - `search_agentcore_docs` - Search AgentCore documentation
    - `fetch_agentcore_doc` - Retrieve specific documentation pages
    - `manage_agentcore_runtime` - Manage agent runtime configuration
    - `manage_agentcore_memory` - Handle agent memory operations
    - `manage_agentcore_gateway` - Configure agent gateway settings
    
    ## Getting Started
    
    **For new users or building a new agent:** Use the getting-started steering file for complete step-by-step guidance on prerequisites, project creation, development workflow, and deployment. Access it with `readPowerSteering("agentcore", "getting-started.md")`.
    
    **For deploying existing agents:** Use the `manage_agentcore_runtime` MCP tool to get complete deployment requirements and instructions for wrapping and deploying existing agents to AgentCore runtime.
    
    ## Integration Guides
    
    **AgentCore Gateway:** 
    - For creating and managing Gateway resources, use the `manage_agentcore_gateway` MCP tool for framework-agnostic CLI commands
    - For fully integrating Gateway with a Strands agent, use `readPowerSteering("agentcore", "agentcore-gateway-integration.md")`
    
    **AgentCore Memory:** 
    - For creating and managing Memory resources, use the `manage_agentcore_memory` MCP tool for framework-agnostic CLI commands
    - For fully integrating Memory with a Strands agent, use `readPowerSteering("agentcore", "agentcore-memory-integration.md")`
    
    ## Using MCP Tools
    
    ### Search Documentation
    
    To search AgentCore docs:
    ```
    usePower("agentcore", "agentcore-mcp-server", "search_agentcore_docs", {
      "query": "deployment configuration"
    })
    ```
    
    ### Fetch Specific Documentation
    
    ```
    usePower("agentcore", "agentcore-mcp-server", "fetch_agentcore_doc", {
      "doc_id": "getting-started"
    })
    ```
    
    ### Manage AgentCore Runtime
    
    Get deployment requirements and runtime configuration:
    ```
    usePower("agentcore", "agentcore-mcp-server", "manage_agentcore_runtime", {})
    ```
    
    ### Manage AgentCore Memory
    
    Get memory resource creation and CLI commands:
    ```
    usePower("agentcore", "agentcore-mcp-server", "manage_agentcore_memory", {})
    ```
    
    ### Manage AgentCore Gateway
    
    Get gateway configuration and deployment instructions:
    ```
    usePower("agentcore", "agentcore-mcp-server", "manage_agentcore_gateway", {})
    ```
    
    ## Troubleshooting
    
    ### Dev Server Won't Start
    
    **Error:** `Could not find entrypoint module`
    **Solution:** Ensure `.bedrock_agentcore.yaml` exists or specify entrypoint manually
    
    **Error:** `Port 8080 already in use`
    **Solution:** The CLI will automatically try the next available port
    
    ### Local Invoke Fails
    
    **Error:** `Connection refused`
    **Solution:** Ensure dev server is running with `agentcore dev`
    
    **Error:** `Invalid JSON payload`
    **Solution:** Use proper JSON format or plain text (which gets auto-wrapped)
    
    ### Deployment Issues
    
    **Error:** `AWS authentication failed`
    **Solution:** Run `aws login` to authenticate
    
    **Error:** `Model access denied`
    **Solution:** Verify you have permissions for the Bedrock model in AWS console
    
    ## Additional Resources
    
    For detailed development workflow guidance, see the steering file which covers:
    - Complete project creation options
    - Development server configuration
    - Testing strategies
    - Deployment best practices
    
    Use `readPowerSteering("agentcore", "getting-started")` for the full guide.
    
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/inceptionstack-loki-skills-aws-agentcore.md

// REPO STATS

0 stars
0 open issues
Last commit: 6mo ago