analyzer
01Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
38 tagged chinese, measured the same way as everything else here.
Browse within: ai-assistant 12agent-workflow 10bun 9clinical-research 9literature-review 9medical-research 9obsidian 9translation 9tutorial 9
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
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
An agent that examines system health and alerts. Alerts are notifications that a system may have a problem.
Agent
An agent focused on software deployment, which means putting a new version of an application into a usable environment.
Agent
An agent that manages the incident-response process for problems in live systems.
Agent
A research-design agent for planning and evaluating studies. It uses PICO, a framework for describing a population, intervention, comparison, and outcome, and also considers study type, sample size, and bias.
Agent
A medical-research editorial coordinator that guides structured interviews, assigns work, reconciles review disagreements, and checks quality across the research process.
Agent
A literature-search agent focused on PubMed, a database of biomedical and health research papers, with optional searches through CNKI and Consensus. It organizes findings into a four-colour evidence matrix and extracts effect sizes when available.
Agent
A full-stack software development role covering both the parts users see and the server-side systems behind them. It includes application code, databases, deployment, performance work, bug fixes, and technical design.
Agent
A product-management agent that turns user needs, feedback, and competitor information into structured product documents. It defines features, acceptance criteria, and product requirements, but does not write code.
Agent
A role for designing, testing, and improving the instructions given to AI models, often called prompts. It keeps each prompt and its changes in files so they can be compared and reviewed.
Agent
Every agent definition in this repository follows the same interface.
Agent
PM Copilot is an AI Product Manager Agent System. The workflow is the safety rail; the agent experience is goal-driven product work.
Agent
Own the end-to-end AI product manager run from ambiguous request to review-ready product judgment, PRD, structured reference, document prototype, UI delivery, handoff, or launch decision.