Desenvolvimento

Pesquisa pacotes no registro do Unity Package Manager e nos instalados, permitindo encontrá-los pelo nome antes da instalação. Retorna versões disponíveis e status, priorizando correspondências exatas de nome e nome de exibição.

Open a PR and merge it in one step — combines `bin/pr.sh` create with `bin/wait-for-pr-checks.sh` polling and `gh pr merge`. Default mode enables GitHub's native auto-merge so the terminal returns immediately; `--client-side` polls in the foreground and merges when CI goes green. TRIGGER when the user says "ship this PR", "ship it", "open and merge", "PR and merge", "create PR and auto-merge it",

Apply the 5 Whys technique to drill from a surface problem to a root cause. Outputs five sequentially numbered "Why?" lines with brief answers, ending in a root-cause statement. Use after an issue tree to drill the critical branch deeper, or any time the user wants to test whether the apparent cause is the actual cause.

Use when implementing any feature or bugfix in a Kotlin/Spring Boot service, covers layer conventions, idioms, testing, and observability

Find every way users can break your AI before they do. Use when you need to red-team your AI, test for jailbreaks, find prompt injection vulnerabilities, run adversarial testing, do a safety audit before launch, prove your AI is safe for compliance, stress-test guardrails, or verify your AI holds up against adversarial users. Covers automated attack generation, iterative red-teaming with DSPy, and

Listar todas as ferramentas MCP disponíveis. Opcionalmente, filtrar por regex em nomes de ferramentas, descrições e argumentos.

Iterative self-improvement with dspy.Refine -- wraps any module, scores each attempt with a reward function, generates feedback on failures, and retries until a quality threshold is met. Use when you want outputs to improve through self-critique, need iterative revision of drafts, or want the LM to learn from its own mistakes within a single request. Also used for self-critique and revise, iterati

Refactors code safely with test verification. Use when asked to refactor, restructure, clean up, or improve code organization.

Compare two nyann profiles side-by-side and show what would change. TRIGGER ON: 'diff profiles', 'compare profiles', 'what's different between profiles', 'profile diff', 'diff default vs nextjs', 'compare default and python-cli', 'what would change if I switch profiles', 'show me the difference between profiles', 'how does X profile differ from Y', 'what hooks does X add over Y', 'profile comparis

Analyze a repository and suggest profile updates. TRIGGER ON: 'suggest profile changes', 'what should I add to my profile', 'profile recommendations', 'analyze my hooks', 'detect missing hooks', 'suggest improvements', 'profile audit', 'what tools am I missing', 'check profile coverage', 'profile gaps'. Scans devDependencies, config files, repo structure, and git history to find mismatches with th

Execute testes do Unity e retorne resultados detalhados. Suporta filtragem por modo de teste, assembly, namespace, classe e método. Recomenda-se usar 'EditMode' para iteração mais rápida durante o desenvolvimento.

Use when you want to optimize instructions by generating many candidates and picking the best — useful when few-shot demos alone are not enough and you want to tune the task description itself. Common scenarios - your current task instructions produce mediocre results, you want to automatically generate and test many instruction variants, the task is hard to describe in one sentence, or few-shot e