Skill UI

This skill provides advanced secondary workflows for Ideogram, enabling comprehensive image manipulation beyond simple text-to-image generation. Key functions include Magic Fill (inpainting/editing), Remix (style transfer), Upscaling, describing image content (image-to-text), and re-framing. Ideal for professional image refinement, style transfer, and content enhancement.

Guides how to craft detailed prompts for Google Stitch so it generates high-quality web and mobile UI designs, covering specificity, visual style, multi-screen structure, platform targeting, and iterative refinement.

This skill guides users through a comprehensive, multi-stage process for creating high-quality documentation. It systematically moves through Context Gathering (understanding the background and audience), Refinement & Structure (iteratively building and editing sections), and Reader Testing (simulating external review to catch blind spots). Ideal for drafting complex specifications, proposals, or design documents that need to be robust and clear for a wide audience.

This skill transforms flawed writing — whether pasted text or uploaded documents — into publication-ready prose. It eliminates grammatical, spelling, punctuation, clarity, and tone issues while strictly preserving the author’s original intent and unique voice. Use it for professional document refinement, academic paper polishing, or general text review, ensuring the corrected version maintains your authentic style.

Master the Zod library for defining robust, type-safe schemas in TypeScript. This expert covers advanced validation techniques, including primitives, objects, unions, and discriminated unions. It specializes in type inference (`z.infer`), data coercion, complex refinements, and seamless integration with modern frameworks like React Hook Form, Next.js, and tRPC, ensuring consistency across your application state and API inputs.

This skill manages and schedules recurring, autonomous experiments. It allows users to set an experiment to run continuously at predefined intervals (e.g., every 10 minutes, daily, or weekly) using cron scheduling logic. It handles the full lifecycle, including execution, result review, strategy refinement, and state persistence.

This skill implements an autonomous, multi-round research review loop, simulating the rigorous peer-review process of top-tier conferences. It iteratively reviews, identifies weaknesses, suggests fixes, and re-reviews a research document using the MiniMax API. The system manages state persistence across multiple rounds, ensuring continuous improvement until a 'ready' assessment is achieved or the maximum round limit is reached. Ideal for academic writing, thesis refinement, or comprehensive project documentation.

This skill simulates security incidents using discussion-based tabletop exercises for Security Operations Center (SOC) teams. It is designed to test incident response procedures, evaluate cross-functional communication workflows (e.g., Legal, PR, Executive), and assess decision-making capabilities under pressure, all without touching production environments. Ideal for compliance validation, playbook refinement, and comprehensive team training.

Transform vague research directions into concrete, problem-anchored, elegant, and implementation-ready method plans through iterative AI review. Ideal for refining research proposals, decomposing complex problems, and creating paper-worthy research methods that stay focused and current in the foundation-model era.

This skill executes an end-to-end workflow combining research refinement and experiment planning. It transforms vague research directions into a focused final proposal and detailed experiment roadmap. It chains research-refine and experiment-plan to generate method theses, review histories, and validation plans. Ideal for academic research where both methodology and experimental validation are needed simultaneously.

The Santa Method is a multi-agent adversarial verification framework designed to improve output quality by requiring two independent reviewers (Agent B and Agent C) to pass the content before publication. It eliminates single-agent bias and systematically improves outputs through iterative refinement loops until convergence or manual escalation.

This skill refines vague raw ideas into actionable concepts using structured divergent and convergent thinking. It helps stress-test assumptions, expand options, and define MVP scope before committing to a plan. Ideal for early-stage product development where clarity is needed.