Skip to content
Get packs

New AI Agent Project Setup

Scaffold an AI agent wired to Olakai monitoring, with KPI design and validation steps.

Source Download skill
Repository
andrewyng/context-hub
Stars
13,984
Licence
MIT
Files
1 file

What it does

When installed, the agent walks you through creating a new AI agent that reports to the Olakai monitoring platform. It guides you to design business KPIs before coding, create a workflow and agent using the Olakai CLI, define custom data fields that feed KPI formulas, and integrate the Olakai SDK. The file is a set of written instructions, so the agent follows them step by step rather than running a fixed program.

Great for

  • Developers starting a new AI agent that needs Olakai analytics and KPI tracking
  • Teams setting up governance and monitoring for agentic or chatbot-style AI workflows
  • Engineers who want a checklist for defining KPIs and customData fields before writing SDK code

Skip it if

  • Projects not using the Olakai platform, since every step depends on its CLI and API keys
  • Anyone who would paste generated agent API keys (sk_agent_...) into shared code or chats, because the guide treats them as secrets to embed in the SDK

Try asking

  • “Create a new Olakai-monitored agent for my document summarizer, including KPIs and workflow setup”
  • “Help me design KPIs and customData fields for a ticket classification agent before I write SDK code”
  • “Walk me through creating a workflow and agent with the Olakai CLI and validating the integration end to end”
Step-by-step guide: how to use New AI Agent Project SetupInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    new-project.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip new-project.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip new-project.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Design your 2-4 KPIs and customData fields before writing any SDK code, as the guide insists, and register each field as a CustomDataConfig.
  • Store the generated agent API key in an environment variable or secret manager rather than hard-coding it in source files.
  • Check the full Olakai documentation for the SDK steps, since this excerpt ends before the SDK integration and validation sections.

What's inside

  • SKILL.md

Redistributed unmodified from andrewyng/context-hub under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.