Menu
SkillsMP has collected 11 skills from aws-samples/sample-amazon-bedrock-agentcore-coding-agents. Open a skill to review its source and details.
Showing 11 of 11 collected skills.
Build a well-structured backend service for ANY task: an API, a tool server, a data endpoint, or an MCP server that exposes a module's capabilities over the wire. Use when implementing the server side of a build. Principles the agent applies to whatever it is…
Configure a second Claude Code agent as the VALIDATOR in our AgentCore harness: it reads the task and the builders' work, authors a self-contained executable check, the engine runs that check, and its real exit code is the gate. Use when the user says "set up…
Configure the Kiro agent as the VALIDATOR in our AgentCore harness: Kiro reads the task and the builders' work, AUTHORS a self-contained executable check, the engine runs that check, and its real exit code is the gate. Use when the user says "set up Kiro",…
Configure the Claude Code agent as the BACKEND builder in the 3-agent AgentCore coding harness: the agent that implements whatever backend the task's contract names and exposes it through the AgentCore Gateway. Use this when the user says "set up Claude…
Decision guide for adding a 4th+ role to OUR 3-agent AgentCore coding-agent harness (Claude Code = BACKEND / implements the backend deliverable, Kiro = VALIDATOR / authors the acceptance check whose exit code decides, opencode = FRONTEND BUILDER). Use when…
Ship the opencode-built chatbot UI (the FRONTEND BUILDER's artifact in our 3-agent harness) to Vercel and wire it to the AgentCore Gateway MCP endpoint. Use when the user says "deploy the frontend", "deploy to Vercel", "ship the chatbot UI", "publish the UI",…
Configure opencode as the frontend builder in the three-agent AgentCore harness. Use for deploying the opencode Runtime, staging AGENTS.md and .config/opencode/opencode.json, or verifying that the generated interface resolves its service address at runtime…
Umbrella entrypoint for standing up the 3-agent AgentCore coding-agent harness end to end. Use when the user says "set up the harness", "configure the agents", "first time setup", "deploy the coding agents", "bootstrap the harness", "get the agents running",…
Build clean, accessible, professional web UI for ANY task. Use when creating or changing a frontend: pages, components, forms, dashboards, or a chat/console UI. Principles the agent applies to whatever it is asked to build, not a fixed file list. Covers…
Configure Codex as the frontend builder in the three-agent AgentCore harness. Use for deploying the Codex Runtime, staging AGENTS.md and .codex/config.toml, or verifying that the generated interface resolves its service address at runtime and delegates work…
Configure Claude Code as the BACKEND builder: implement the service the request asks for and expose it as a remote MCP server behind the AgentCore Gateway. Use when the user says "set up Claude Code", "configure the backend agent", or "build the backend MCP…