Skill UI

This skill automates the multi-round research review process. It iteratively reviews provided work using advanced AI models (Codex MCP), identifying critical weaknesses, implementing fixes, and re-reviewing until the content achieves a positive assessment or the maximum round limit is reached. Ideal for refining complex academic papers, technical designs, or large codebases that require rigorous, iterative quality assurance.

This skill executes an autonomous, iterative research review loop, simulating a rigorous peer-review process. It repeatedly uses an external OpenAI-compatible LLM via API calls to score, critique, and identify weaknesses in a given research topic or document. The process continues to refine the content by implementing suggested fixes until the LLM provides a positive assessment or the maximum round limit is reached. Ideal for academic writing, technical documentation, and refining complex proposals.

This skill automates the iterative process of academic paper refinement, simulating the rigorous peer-review cycle of top-tier conferences (e.g., NeurIPS, ICML). It connects with an external LLM (MiniMax) to receive multi-round, critical feedback, tracks state persistence, and guides the user through necessary revisions until the research is deemed submission-ready. Ideal for maximizing the quality of technical writing.

This advanced skill orchestrates a systematic, multi-stage workflow for generating novel and feasible research ideas in robotics and embodied AI. It moves users from a broad concept (e.g., manipulation, locomotion) to specific, benchmark-grounded, simulation-first projects. The pipeline surveys literature, checks novelty against major conferences (CoRL, ICRA, RSS), and reviews technical constraints to ensure ideas are falsifiable and practically achievable with current infrastructure.

This skill systematically generates a detailed, section-by-section paper outline by synthesizing research narratives, experimental results, and reviewer feedback. It guides the user through structuring the entire paper, enforcing coherence and logic, and adhering to specific constraints such as target venue guidelines (e.g., ICLR, NeurIPS) and page limits. Ideal for the pre-writing phase of technical papers.

This skill transforms vague research ideas or fuzzy technical approaches into structured, elegant, and highly concrete method plans, suitable for academic papers or complex projects. It operates through an iterative, multi-phase review cycle, anchoring the original problem while forcing the development of the minimal, most impactful contribution. Ideal for researchers who need to refine a breakthrough idea into an implementation-ready proposal, simulating the rigorous process of top-tier academic review.

This mode enables ultra-compressed communication, drastically reducing token usage (up to 75%) while retaining full technical accuracy. It simulates speaking in a highly terse, telegraphic style. Users can select from multiple intensity levels (lite, full, ultra, and classical Chinese variants) to tailor the level of abbreviation needed for specific contexts, making it ideal for API interactions or constrained API calls.

Compresses natural language memory files (like notes, to-do lists, and preferences) into a highly condensed 'caveman-speak' format. The tool removes filler words, articles, and redundant phrasing while strictly preserving all technical elements, including code blocks, URLs, and Markdown structure. This process significantly reduces input tokens, optimizing memory storage and retrieval efficiency.

Creates high-fidelity visuals through structured JSON prompts and a Python generator script, handling subjects, styles, references, and technical specs for characters, scenes, or products.

This skill creates high-quality videos from structured JSON prompts and optional reference images, then runs the prescribed Python script to produce MP4 output tailored to the requested scene, style, and technical specs.

This utility compresses natural language documents (notes, preferences, memory files) into a highly condensed, 'caveman-speak' format. Its primary function is drastically reducing input tokens for efficiency while meticulously preserving all technical substance, including code blocks, URLs, file paths, and markdown structure. Ideal for optimizing memory consumption when interacting with AI models.

This guide outlines the structure and content guidelines for an AGENTS.md file. This file serves as a comprehensive 'README for agents,' providing detailed, technical context and operational instructions (such as setup, development workflow, testing procedures, and code style) that enable advanced AI coding agents to interact with and understand a codebase effectively. It greatly complements traditional READMEs by focusing purely on machine-readable technical requirements.