analyzer
01Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
40 tagged desktop, measured the same way as everything else here.
Browse within: electron 22agent-orchestration 20android 5
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
Agent
AI team for Comet MVU framework development. Manages the src/Comet subproject.
Agent
Expert .NET MAUI DevFlow code reviewer. Multi-model review with adversarial consensus.
Agent
Review OpenCode releases and assess CodeWalk impact.
Agent
Agent "Chief Marketing Strategist" from muratgur/ordinus, covering role, capabilities, requested work, instructions and chief marketing strategist.
Agent
Agent "Marketing Report Builder" from muratgur/ordinus, covering role, capabilities, requested work, instructions and marketing report builder.
Agent
Agent "Product Intelligence Analyst" from muratgur/ordinus, covering role, capabilities, requested work, instructions and product intelligence analyst.
Agent Claude Code
Generates comprehensive Product Requirements Documents (PRDs) for new features. Use when the user needs a structured PRD, feature specification, or product requirement prompt. Researches the codebase, asks clarifying questions, and produces a detailed document ready for implementation by a coding agent.
Agent Claude Code
Extracts a Maven dependency's JAR (or sources JAR) into the project build dir so you can browse its classes and source. Use when you need to explore the API or internals of a library. Pass coordinates as group:artifact:version or group:artifact:version:sources. Omit version to have it looked up from…
Agent Claude Code
Runs Gradle commands with filtered output to keep the parent context window clean. Use for any ./gradlew or gradle invocation — compilation, tests, formatting checks.
Agent Codex
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Codex
Compare two outputs WITHOUT knowing which skill produced them.
Agent Codex
Evaluate expectations against an execution transcript and outputs.
Agent
Read these documents before you explore or change Codex Studio.
Agent
GitHub Issues and the linked GitHub Project hold live work state. Local Markdown files hold synchronized briefs, decisions, evidence, and handoffs.
Agent
GitHub Issues use one category label and one triage label. Local mirrors record the same values.
Agent Claude Code
Implements features with automatic review cycles. Use for new features or significant changes that benefit from review.
Agent Claude Code
Implements features and fixes based on requirements. Writes clean, working code.
Agent Claude Code
Reviews code changes for quality, bugs, and best practices. Provides actionable feedback.