autonomous-cloud-orchestration — Claude Code skill
autonomous-cloud-orchestration walks your agent through AWS Bedrock AgentCore: picking the right service and wiring the deployment with the AWS CLI.
LicenseRef-Proprietary 131 installs ★ 50 updated 2026-01-05
npx skills add qodex-ai/ai-agent-skills --skill autonomous-cloud-orchestration -a claude-codeWhat autonomous-cloud-orchestration does
Seven AgentCore services sit behind this skill: Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability. The SKILL.md holds a service table that points at per-service READMEs under services/, so the agent opens the doc it actually needs.
Workflows come as ordered steps. A Gateway target means uploading the OpenAPI schema to S3, creating a credential provider when the API uses key auth, linking schema and credentials to the target, then checking status and connectivity. Lambda targets lean on IAM roles, MCP servers on OAuth. Everything runs through AWS CLI commands.
Fresh AWS answers depend on AWS MCP tools being there. Without them the skill sends you to set up AWS MCP: the full server when uvx and AWS credentials exist, or the documentation-only MCP server with no auth otherwise.
What it helps with
- turn a REST API into MCP tools with Gateway
- give an agent memory that survives between sessions
- keep API keys in an Identity credential provider and attach them to a target
- trace agent runs and set CloudWatch alarms
- run agent code inside the Code Interpreter sandbox
Example prompts for the agent
- Walk me through deploying our OpenAPI schema as a Gateway target and testing connectivity.
- Add conversation memory to this agent — which Memory setup and which
bedrock-agentcore-controlcommands do I need? - Enable Observability for the agent and tell me which metrics belong on the CloudWatch dashboard.
How to install autonomous-cloud-orchestration
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill autonomous-cloud-orchestration -a claude-code2Manually: put the files in place
~/.claude/skills/autonomous-cloud-orchestration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/autonomous-cloud-orchestration/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill autonomous-cloud-orchestration -a codex2Manually: put the files in place
.agents/skills/autonomous-cloud-orchestration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill autonomous-cloud-orchestration -a cursor2Manually: put the files in place
.cursor/skills/autonomous-cloud-orchestration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install qodex-ai/ai-agent-skills skills/autonomous-cloud-orchestration2Manually: put the files in place
.github/skills/autonomous-cloud-orchestration/SKILL.md1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill autonomous-cloud-orchestration -a gemini-cli2Platform CLI
gemini skills install https://github.com/qodex-ai/ai-agent-skills --path skills/autonomous-cloud-orchestrationManually: put the files in place
.devin/skills/autonomous-cloud-orchestration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill autonomous-cloud-orchestration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about autonomous-cloud-orchestration
How to install autonomous-cloud-orchestration in Claude Code?
Run npx skills add qodex-ai/ai-agent-skills --skill autonomous-cloud-orchestration -a claude-code. The skill file lands at ~/.claude/skills/autonomous-cloud-orchestration/SKILL.md.
What does autonomous-cloud-orchestration do?
It maps AWS Bedrock AgentCore service by service and hands the agent concrete deployment steps: Gateway targets, Runtime hosting, memory, credentials, sandboxes, browser access, monitoring.
What do I need for the skill to work?
AWS MCP tools, so the agent can verify current AWS documentation. The full AWS MCP Server needs uvx plus AWS credentials; without them you fall back to AWS Documentation MCP, which takes no auth.