Skill UI

Analyzes text to determine emotional tone and polarity, classifying passages as positive, negative, or neutral; ideal for processing reviews, social media posts, surveys, or any feedback that requires opinion mining or emotion detection.

This skill orchestrates end-to-end autonomous AI research projects using a sophisticated two-loop architecture. It manages the entire research lifecycle, from initial literature review and hypothesis formation to running constrained experiments and synthesizing findings into publishable papers. It acts as a project manager, autonomously driving the process while structuring the workspace and presenting progress to human users.

This skill implements an autonomous iterative review process, simulating continuous academic or product refinement. It repeatedly submits work for review via an external model (Codex MCP), applies suggested fixes, and re-reviews until a positive assessment or the maximum number of rounds is reached. It manages state persistence and various difficulty levels to ensure robust, self-correcting iteration.

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 skill guides the entire process of writing a research paper rebuttal following submission to a major conference. It parses complex, multi-reviewer feedback, structures responses according to strict venue rules (e.g., text-only, per-reviewer threads), and ensures all claims are grounded in the original paper, preventing fabrication or overpromising. It manages follow-up rounds and maintains academic rigor.

This skill generates publication-quality academic illustrations using a sophisticated, multi-stage iterative workflow. It leverages Claude as a planner and reviewer, optimizing layout and verifying style against top conference standards (e.g., CVPR, NeurIPS). The process includes initial prompt generation, layout refinement, style checking, native image rendering via a local Codex bridge, and a final, strict visual review loop (Score ≥ 9) to ensure the figure is ready for publication.