Skills

Think of Claude Code as a brilliant colleague who can code anything, but needs you to explain the goal clearly. The better you describe what you want, the better the result. Whether you speak or type, the approach is the same — just say what you need.

For your AI agents data to show up in the Sentry [AI Agents Insights](https://sentry.io/orgredirect/organizations/:orgslug/insights/ai/agents/), at least one of the AI spans needs to be created and have well-defined names and data attributes. If the required data (marked with MUST or required) is missing, the data will not show up in the Agents dashbboard.

This guide shows how to take a Python app built with the OpenAI Agents SDK and add the TraceCore evaluation loop without rebuilding the app from scratch.

**Created**: 2025-12-09 **Last Updated**: 2026-02-12 **Category**: Architecture

AI coding agent instructions for project conventions and guidelines.

An AI agent is a system that uses a language model as its reasoning engine to decide what actions to take, execute those actions, observe the results, and iterate until a task is complete. While a standard LLM call is a single input-output exchange, an agent operates in a **loop** — thinking, acting, and adapting.

At a recent event in London, I was excited to learn how [RedwoodSDK](https://rwsdk.com/) makes it easy to run React Server Components (RSC) on Cloudflare. I decided to learn more about this by building multi-user AI chat. Code on [GitHub](https://github.com/jldec/agents-chat). Deployed at https://agents-chat.jldec.me/.

**Load this reference when:** creating or editing skills, before deployment, to verify they work under pressure and resist rationalization.

Cursor IDE rules and conventions for AI-assisted development.

Agents: https://docs.langchain.com/oss/python/langchain/agents Models: https://docs.langchain.com/oss/python/langchain/models Messages: https://docs.langchain.com/oss/python/langchain/messages Tools: https://docs.langchain.com/oss/python/langchain/tools

1. Generate verification codes using `src/utils/auth/verification-codes.ts` 2. Validate codes against hashes

Previous, simpler attempts to resolve this issue have failed. Standard procedures are now suspended. You will initiate a **deep diagnostic protocol.** Your approach must be systematic, evidence-based, and relentlessly focused on identifying and fixing the **absolute root cause.** Patching symptoms is a critical failure.

Uniform is a modern, headless, component-based Content Management System (CMS). Its primary purpose is to allow non-technical authors (marketers, etc) to create and maintain websites and other similar experiences in a visual editor.

1. **Check for Open Tickets**: Look for the next highest priority ticket in the project management system. 2. **Provide Ticket Details**: If a ticket is found, provide the user with: 3. **No Tickets Available**: If there are no open tickets, inform the user that there are no tasks available at the moment.

Use `bun test` to run tests. import { test, expect } from "bun:test"; test("hello world", () => {

event_store: EventStore, // NATS JetStream persistence write_model: GraphAggregate, // Command processing read_model: GraphReadModel, // Query optimization bevy_bridge: AsyncSyncBridge, // Real-time updates

These rules define how to transform TypeScript types into JSON Schema dynamically. They will be used by cursor to generate JSON Schema from provided TypeScript code.

Cursor IDE rules and conventions for AI-assisted development.

Use `bun test` to run tests. import { test, expect } from "bun:test"; test("hello world", () => {

**This app is built on the Lovelace platform.** The Query Server is the primary data source — use it first for any data needs (entities, news, filings, sentiment, relationships, events). Do NOT call external APIs

SRP: **A class, function, or module should have only one reason to change.** That is, each component is responsible for only **one task**.

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.