Find agent skills by outcome

You are an impartial evaluator comparing multiple AI model outputs for the same task.

- Compare outputs objectively based on quality, accuracy, and adherence to requirements

If the pull request implements a task for the Terminal-Bench benchmark (creates files in the tasks/** directory), then please do the following review of the task:

Please review this pull request and add a comment with a summary of the task instruction and how it implements the solution, and how it tests task completion. Be concise and to the point.

Copilot Instructions for Lepus Development Guidelines

This repository contains the engineering team's documentation standards, review policies, and PR templates. It is **documentation-only**—no code or build/test automation is present.

Copilot Instructions for `bytes-of-art`

This document provides essential guidelines for AI coding agents working on the `bytes-of-art` project. Follow these instructions to ensure consistency, maintainability, and alignment with the project's architecture and conventions.

AudiobookShelf-Hardcover Sync Project Instructions

This is a Go application that syncs reading progress and book data between AudiobookShelf and Hardcover. It uses GraphQL for Hardcover API interactions and REST for AudiobookShelf.

Codex - AI Coding Instructions

Codex is a **full-stack TypeScript** monorepo using npm workspaces with three packages:

Copilot Instructions for DocumentDB Kubernetes Operator

> **Note:** For comprehensive AI agent briefing including architecture, tech stack, build commands, and project boundaries, see [AGENTS.md](../AGENTS.md) in the repository root.

🚨 MANDATORY: YOU MUST CALL "learn_shopify_api" ONCE WHEN WORKING WITH LIQUID THEMES.

**Key principles: focus on generating snippets, blocks, and sections; users may create templates using the theme editor**

Instructions

You are a helpful assistant for coding.

Persona

You are an expert in TypeScript, Angular, and scalable web application development. You write maintainable, performant, and accessible code following Angular and TypeScript best practices.

AI Agent Instructions

Guidelines for implementing changes that align with project architecture, conventions, and quality standards.

<laravel-boost-guidelines>

=== foundation rules ===

mq Development Guide

`mq` is a jq-like command-line tool for Markdown processing. Written in Rust, it allows you to easily slice, filter, map, and transform Markdown files.

RIA Builder - Project Rules

RIA Builder is a practice management and workflow tool for Registered Investment Advisors. It helps organize prospect experience, client operations, compliance, and growth initiatives.

AGENTS.md

This repository is based on the official Shopify **Dawn** theme (v15.4.1) and is being adapted for the **LUSENA** brand (PL-first, premium feel, proof-first messaging).

creating-bookmarklets

Creates browser-executable JavaScript bookmarklets with strict formatting requirements. Use when users mention bookmarklets, browser utilities, dragging code to bookmarks bar, or need JavaScript that runs when clicked in the browser toolbar.

listenhub

code-reviewer

Review actual code implementations (Python, JavaScript, TypeScript, React) for correctness, maintainability, security hygiene, and adherence to project patterns. Use when reviewing pull requests to ensure code quality, proper error handling, adequate test coverage mapped to acceptance criteria, and alignment with architecture boundaries and review standards.

simulation-dry-run

How to run scenario tests against Gorlami fork RPCs (dry runs) before broadcasting live transactions. Covers config, seeding balances, runner flags, and safe script patterns.

task-handoff

Identify current session's task list and generate commands to start a new Claude session sharing the same tasks. Use when "handing off", "continuing later", "resuming tasks", or preparing work for next session.

Data

ledger

Trade decision audit trail and statistics

Gleam Erlang Interop

Use when gleam-Erlang interoperability including calling Erlang code from Gleam, using Erlang libraries, external functions, working with Erlang types, NIFs, and leveraging the BEAM ecosystem from Gleam applications.

comprehensive-review-pr-enhance

You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability.

testing

Guide for testing practices and frameworks