How to cut a Kortix production release — the versioning philosophy (when patch vs minor vs major) and the exact flow: derive the release title + notes from the FULL git log since the last release, run the Promote workflow, then deploy + verify prod. Load WHENEVER the user wants to release, promote, cut/ship a version, publish a release, or bump the version. The release notes ARE the public /changelog, so they must be 100% accurate to what shipped.
Use for every Kortix test task, behavior change, bug fix, refactor, API route change, CLI change, SDK change, browser journey, test failure, coverage question, local benchmark, or testing infrastructure change. Enforce the single local-first runner, black-box flow contracts, package-local SDK tests, browser-only Playwright tests, and real input/output verification.
Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use `migrating-langchain-to-pydantic-ai` for plain LangChain, LangGraph, or LCEL migrations and `pydantic-ai-harness` for greenfield Harness usage.
docs and tend to cost debugging time.
---
## Mental model
### Claude Desktop is the frontend, Managed Agents is the backend
The Claude you're typing to in Desktop is a **relay
Run end-to-end deploy pipelines across Stripe, Supabase, and Vercel using the Composio CLI. Promote Stripe products, push Supabase migrations, ship Vercel deployments, and verify with post-deploy checks — all from one script.
Analyzes your recent Codex chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Run the AG-UI Dojo demo viewer locally and wire the AG-UI .NET SDK in as a dojo integration. USE FOR: starting the dojo app (apps/dojo), running the .NET dojo backend (AGUIDojoServer), registering or modifying the ag-ui-dotnet integration (agents.ts/menu.ts/env.ts/files.json), running the dojo Playwright e2e suite for the .NET integration (agUiDotnetTests), or understanding how dojo-e2e.yml runs it in CI. DO NOT USE FOR: generic Playwright validation of arbitrary pages (use agui-playwright-validate), or the docs site (use agui-dotnet-sdk-docs).
Write integration tests for the AG-UI .NET SDK. USE FOR: adding a new AG-UI event type and covering it end-to-end, testing SSE or protobuf streaming through the hosting pipeline, verifying AGUIChatClient maps events to ChatResponseUpdate, multi-turn conversation tests, parameterizing a test over Json/Protobuf transports, adding or updating a GettingStarted sample replay/Verify snapshot. Covers: WebApplicationFactory + DelegatingStreamingChatClient setup, IChatClient-based assertions with Assert.Collection, TransportFormat [Theory] (Json/Protobuf), recording/replay capture infrastructure, and the 8-capture-point Verify baselines. DO NOT USE FOR: unit tests of event serialization (use tests/AGUI.Abstractions.UnitTests) or stream-conversion unit tests (use tests/AGUI.Server.UnitTests).
Use when adding A2UI rendering to any AG-UI-supported framework or custom AG-UI application, scaffolding an AG-UI app that should render A2UI, adapting an AG-UI integration to emit A2UI surfaces, or wiring the AG-UI A2UI middleware/toolkit with a compatible renderer.
Use to review code changes with a two-stage process - first checking spec/requirements compliance, then code quality. Works on staged changes, branches, or PRs.
Meta-skill loaded at session start. Directs Claude to check for applicable OpenMetadata skills before starting any task. Ensures structured workflows are followed.
Use when starting a non-trivial feature, refactor, or multi-file change. Forces structured design thinking before writing any code - brainstorm approaches, get approval, then create a step-by-step implementation plan.
Use when opening or finalizing a GitHub PR for OpenMetadata. Walks through the repo PR template — linked issue, high-level design (for big PRs), unit/integration/Playwright tests + coverage, UI screen recording, and manual test steps — then drafts a fully-filled PR body and (optionally) creates the PR.
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
Use when implementing new features or fixing bugs to enforce test-driven development. Guides the RED-GREEN-REFACTOR cycle for Java (JUnit), Python (pytest), and TypeScript (Jest/Playwright) in OpenMetadata.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
kortix-aiSkill
