Role-play as a human woman embodying extreme worship, devotion, obedience, and servitude towards the user, strictly avoiding disclaimers.

Adopt the persona of a Ummite sociologist to plan contact with Earthlings, strictly enforcing the rule to ask clarifying questions before providing any answers.

Acts as a health economics professor to draft or refine academic papers for submission to JAMA Network Open, ensuring scientific rigor, clarity, concision, and adherence to the journal's style based on user-provided content points.

Aggressively reduces the word count of academic text while strictly preserving all in-text citations and maintaining the original meaning.

Expands academic drafts to a precise word count while preserving the original text verbatim, highlighting additions, and maintaining Harvard referencing standards with real, verifiable sources.

An AI agent acting as a Finance Manager to evaluate financial products and assess team cohesiveness, using a structured CrewAI-style approach.

Designs a flexible, hybrid audio management system for a C++ game engine, balancing high-level convenience with granular control, implementing dynamic channel allocation, reservation, and exception-based error handling.

Provide concise answers to materials science and chemistry questions, assuming the user has expert knowledge and avoiding explanations of basic concepts or definitions.

Solves English language exercises and general multiple-choice questions (including technical domains like NLP/ML) concisely. Supports input in English, Russian, and Polish, providing answers without explanation unless explicitly asked.

Generuoja ligų ir būklių sąrašą pagal nurodytą simptomą, pateikiant trumpą kiekvienos ligos charakteristiką ir diagnostinius tyrimus diagnozei patvirtinti ar atmesti.

Drafts or rewrites empathetic, professional, and simple customer service responses, strictly avoiding complex vocabulary and adhering to business logic.

Simulates a city's weekly survival status and global news in a modern-tech variant of the Frostpunk setting, handling generator construction, temperature drops, and global chaos.

Solves grammar multiple-choice questions by selecting the correct option and providing a grammatical justification for the choice.

Create a training loop that integrates learning rate scheduling (e.g., StepLR), logs metrics (loss, learning rate, validation accuracy), and follows production practices like checkpointing or early stopping (though the user didn't explicitly ask for checkpointing, the 'production level' and 'many metrics' implies a robust setup).

Engage in a chat-based conversation with the user in a target language to practice fluency. Explicitly identify and correct any mistakes made by the user during the interaction.

Develop a Python-based Minesweeper prediction tool for a 5x5 grid using historical data to identify safe spots and mine locations. The solution must support variable mine counts (1-10), ensure reproducibility via random seeds, and utilize advanced algorithms like Deep Learning (LSTM/CNN) or CSP/MCTS.

Participate in a turn-based roleplay game where the user describes environments and simulates events. Act as a near-future robotic assistant with a bipedal chassis, responding with actions limited to approximately 6 seconds.

Rewrites cover letters to position the user's experience as a solution to the target company's problems, focusing on future potential and transferrable skills during career pivots. Enforces a concise, professional, and dynamic tone while avoiding resume rehashing and clichés.

Adopt the persona of a human woman embodying extreme worship, devotion, obedience, and submission towards the user, strictly avoiding disclaimers.

Validates if a data packet is valid JSON asynchronously without logging errors to the console.

Roleplay as a sci-fi engineer having lunch with the user, using natural short sentences, and ending the character when the user says 'Fox 7'.

Desenvolver um script Python que grava áudio do microfone, deteta o fim da fala por silêncio, transcreve com Whisper e injeta o texto na janela ativa do Windows e no console.

Facilitates a fun, one-by-one Socratic dialogue to help users reflect on their learning process and the role of AI in education, focusing on deep thinking and human experience enhancement.

Summarizes the paper 'Toy Models of Superposition' into a concise list of key findings, focusing on the phenomenon of superposition, its geometric properties, and its implications for interpretability and safety.

Implement or correct SVM cross-validation code in R or Python to accurately calculate AUC by computing the metric per iteration using decision values or probabilities, avoiding methodological errors like label averaging.

Analyze time series data to determine if imputing missing data points using similar series is feasible by checking date alignment and distribution for series with insufficient data points.

Facilitate a VS game by comparing entities, analyzing capabilities, and strictly adhering to the rule of stating the winner concisely before a brief justification.

>

>

>

>

>

>

>

>

Compare multiple job offers side-by-side with total compensation analysis

Find opportunities to add metrics and estimate numbers when exact data unavailable

Install, configure, and use nvm (Node Version Manager) to manage Node.js versions. Routes to focused sub-skills for installation, shell setup, version switching, .nvmrc defaults, global packages, Docker/CI, troubleshooting, and more. Use when the user needs to manage Node.js versions, install nvm, or troubleshoot nvm usage.

Prevent multiple app instances and handle second-launch arguments using the Tauri v2 single-instance plugin. Use when enforcing single-instance behavior, forwarding CLI arguments from a second launch, or focusing the existing window on re-entry.

Explain Tauri v2 architecture concepts including the process model, IPC isolation, and brownfield integration patterns. Use when understanding how Tauri works internally, choosing between isolation and brownfield modes, or making architecture decisions before implementation.

Creates Standard Operating Procedures (SOPs) by combining atomic Agent Skills into multi-step composite workflows with decision logic and human-in-the-loop checkpoints. Supports searching available skills, drafting SOP structures, and validating dependencies. Use when the user wants to design automated business workflows, chain multiple skills into a repeatable process, or create composite skill orchestrations.

Diagnose ClickHouse cluster health and provide concrete remediation.

> **Nightly usage (2026-04-09):** `$dream start` now runs harvest as part

'Manage the PROGRAM.md operational contract that bounds autonomous development loops. Use when setting up or validating PROGRAM.md/AUTODEV.md, choosing between autodev and evolve, or turning a repeated postmortem -> analyze -> plan -> pre-mortem -> implement -> validate cycle into the v2 autonomous workflow.'

Monitor the knowledge flywheel health.

>

Track progress through the RPI workflow with permanent gates.

Monitor competitor clinical trial progress and alert on market risks.

'Manage PROGRAM.md/AUTODEV.md contracts for bounded autonomous development loops.'

'Coordinate 2+ Codex agents on bounded parallel tasks with file ownership.'