Desenvolvimento

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Padrões de física da Unity, incluindo controladores de personagem, tratamento de colisões e prevenção de tunelamento.

Instala ciclos estruturados de autoaperfeiçoamento com aprendizado baseado em instinto no Claude Code, seguindo um ciclo de pesquisa, planejamento, execução, verificação, reflexão, aprendizado e iteração. Oferece análise sob demanda ou semanal para economizar tokens e suporta análise paralela multiagente.

Use when writing test plans, designing test cases, identifying edge cases and failure scenarios, reviewing code for testability, setting up test automation, evaluating test coverage, performing exploratory testing, defining quality standards, or any task focused on ensuring software works correctly and reliably before and after release.

Run DSPy with local models using Ollama — no API key needed. Use when you want to run DSPy locally, use Ollama, set up a local LLM, run offline, or configure local model parameters. Also used for ollama, local model, run LLM locally, llama local, self-hosted LLM, ollama serve, ollama_chat, local inference, run DSPy offline, no API key needed, ollama pull, ollama list, ollama rm, num_ctx, ollama co

Use when you need to run DSPy modules asynchronously — FastAPI endpoints, concurrent LM calls, non-blocking execution, or integrating DSPy into async web frameworks. Common scenarios - serving DSPy behind FastAPI or Starlette, running multiple LM calls concurrently with asyncio.gather, non-blocking batch processing, combining async with streaming, or building async agent loops. Related - ai-servin

Detecta testes não determinísticos (flaky) analisando logs de execução de CI ou histórico de resultados de testes. Agrega taxas de aprovação, identifica falhas intermitentes, recomenda quarentena ou correção, e mantém um registro de testes flaky, idealmente executado durante a fase de polimento ou após múltiplas execuções de CI.

MemoryPack oferece serialização binária de alta performance para Unity, incluindo formatadores personalizados, versionamento e padrões de performance.

Prune local branches whose work is already merged into the base. TRIGGER when the user says "clean up branches", "delete merged branches", "prune local branches", "remove old branches", "I have too many branches", "what branches can I delete", "/nyann:cleanup-branches". Do NOT trigger on "delete THIS branch" (that's a one-off `git branch -D`, not a cleanup pass) or "remove a branch from the remote

ACH-based parallel debugging. Spawns multiple hypothesis-investigator agents to investigate competing hypotheses simultaneously. Use when bugs are complex, when single-agent debugging hits 3+ failures, or when root cause is unclear. Also triggers when test-failure-analyst returns LOW confidence during arc Phase 7.7. Keywords: debug, investigate, hypothesis, root cause, parallel debugging, ACH, com

Esta skill refina textos, removendo padrões de escrita de IA e 'slop' de prosa, rascunhos técnicos, comentários de código e outros, tornando-os mais naturais, concisos e diretos. Suporta chinês tradicional e inglês.

Analyze and improve existing Ozor.ai video prompts for better output quality. Use this skill whenever the user has an Ozor prompt that produced mediocre results, wants to improve a video prompt, needs help debugging why a video didn't turn out well, or wants expert feedback on their prompt before running it. Trigger on phrases like 'improve this prompt', 'optimize my Ozor prompt', 'why did my vide