Explorar skills

Use when implementing GitHub issues for skill or plugin development through TDD-governed phases with iterative planning, implementation, and review loops. Use this whenever the issue involves SKILL.md files, agent prompts, hook scripts, or plugin workflows.

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

Search for how other games solve a specific design problem — game loops, mechanics, systems, progression, economy. Returns a comparison of 2-4 reference games with what to borrow. Use when designing a new feature, exploring game mechanics, or looking for design inspiration before writing a design doc.

Git hygiene: clean up merged branches, prune stale remotes, and verify repository state.

Transforma relatórios de ajuste multiview em uma fila de reparo sequencial ou paralela para alinhar produtos Blender a templates de referência. Utilize após a validação mostrar desalinhamento, quando o agente deve corrigir iterativamente incompatibilidades de wireframe, textura, iluminação ou projeção, e quando lacunas de habilidade devem acionar o autoaperfeiçoamento antes de outra reconstrução.

Um ciclo de autoaperfeiçoamento é executado quando um resultado do Blender é insatisfatório, expectativas do usuário não são atendidas, validação falha ou problemas recorrentes indicam falta de profundidade na skill. Este ciclo diagnostica a falha, decide entre reparar o artefato ou aprimorar uma skill genérica, prepara lições para publicação, atualiza documentação, valida e prepara para implantação quando solicitado.

Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.

A curated collection of 115 skills, 16 agents, and 48 commands for Claude Code and Cursor.

Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html

Create coding agent benchmarks for evaluation with nasde. Use this skill when the user wants to: - Create a new benchmark project (set of tasks for evaluating coding agents) - Add tasks to an existing benchmark - Create or modify agent variants (configurations that control agent behavior) - Set up assessment dimensions and scoring criteria - Verify that a new benchmark's Docker environment and tes

Produces a structured research framework for finding, organising, and verifying a named person's previous public statements on a specific topic, so a journalist can enter an interview or write a story with full command of the subject's record.