Skill UI

A deterministic method for placing signature, date, and text fields in a web e-signature composer via browser automation. It uses fixed signature pages and numeric coordinates instead of drag-and-drop. This skill ensures repeatable field positions, correct recipient ownership, and security gates before sending. Ideal for automating envelope preparation for generated agreements when API access is unavailable.

Generate and cut videos against a distilled style pack: plan takes, generate with fal, apply measured LUT grading, edit at cadence, weave footage, composite overlays, mint 3D props, and verify results numerically.

Audits mediation-competition problem packets for factual, numerical, chronological, authority, commercial-logic, and confidentiality defects; tests BATNAs, settlement corridors, and information asymmetry; produces an author-only validation report.

Creates a personal, motivating daily focus board in a browser canvas, driven by conversation with an AI partner. Tracks task statuses with progress notes, supports numeric goals with progress bars, and includes neurodivergent-friendly features like focus mode, kind carryover, brain-dump box, reduced motion, and gentle deadline countdowns. Priorities via Eisenhower matrix, daily mantra, check-in, and end-of-day recap. Persists in localStorage.

A skill for designing evidence and validation strategies for academic manuscripts submitted to the Journal of Systems Engineering. It covers standards for numerical experiments, simulations, real data, case studies, and empirical research, ensuring claims are supported by appropriate evidence rather than generic robustness checks.

This advanced AI skill converts raw study materials—such as syllabi, past exam papers, or personal notes—into a structured, prioritized, and difficulty-ranked High Score Roadmap. It covers all key question types (Theory, Numerical, MCQ, Coding, Lab) and optimizes study flow by ordering topics from Easy to Hard. Use it for targeted revision, gap analysis, and predicting high-yield exam questions.

Automated visual tuning: a vision or video model rates rendered variants in a loop. Render labeled variants into one artifact, ask the model to rate them and suggest better values, render suggestions, pick the best, repeat until good. Ideal for aesthetics, timing, layout, color grading, and other subjective visual parameters without numeric metrics.