AI Agent Skills

Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

Structured Adaptive Mesh Refinement Application Infrastructure - a scalable C++ framework for block-structured AMR application development

Voronoi / Delaunay tessellations on the sphere

Generate draw.io diagrams from natural language — 6 presets, vision self-check + up to 5-round refinement, codebase-to-diagram, 10,000+ official shapes & 321 AI/LLM bran…

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimi…

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web searc…

N개 brand experiment를 한 화면에서 비교하는 gallery index.html을 생성. 각 카드는 brand name, wow rating, multi-turn refinement deltas, iframe scaled preview, standalone link 포함. '결과물 한 번에…

A skill that improves AI aesthetic judgment for web UI generation, review, and refinement.

Master the art and science of crafting effective prompts for large language models. Covers foundational patterns, advanced techniques like chain-of-thought and role prom…

SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombinat…

Produce an implementation plan at .turbo/plans/<slug>.md. Use when the user asks to \"draft a plan\", \"draft the plan\", \"write an implementation plan\", \"plan this c…

Quant-focused research ideation pipeline: scope selection (3 stages) → anchor-first literature grounding → single-core idea generation → iterative refinement → ELO tourn…

Formula Student Driverless Path Planning Algorithm. Colorblind centerline calculation algorithm developed by FaSTTUBe. It introduces a novel approach that uses neither D…

Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagno…