Desenvolvimento

End-to-end eDNA metabarcoding from raw amplicons to community ecology. Covers QC, primer removal (mandatory before DADA2 filterAndTrim), denoising with OBITools3 v3 (obi stats plural; DMS-based) or DADA2 ASVs (Callahan 2017), decontam combined method as screening-not-classifier (Davis 2018), tag-jumping with NovaSeq 10x MiSeq caveat (Schnell 2015), Hill-number effective species counts with coverag

xUnit testing patterns and data-driven test guidance. Use when writing or reviewing .NET unit tests.

"setup" = install testing infra only. "check" = audit gaps and report, don't write tests. "full" or omitted = setup + audit + write + run + verify.

Builds and refactors code safely; prefers small diffs, clear validation steps, and testable outcomes.

Red-green-refactor development methodology requiring verified test coverage. Use for feature implementation, bugfixes, refactoring, or any behavior changes where tests must prove correctness.

Diagnóstico e correção de travamentos no FastAPI, causados pelo desligamento bloqueante do ThreadPoolExecutor na rota de stream de notícias, com a inclusão de captura py-spy e um padrão de executor não bloqueante.

Context handoff for fresh sessions. Saves unsaved session knowledge to notebook, then produces a short orientation block to paste into a new chat. Use when user says '/memento', 'hand off context', 'prepare for fresh chat', 'save and brief', or before clearing context. NOT for: recovering context (use /notebook recover) or saving a single note.

URL (YouTube, article, X/Twitter thread, podcast) or file path to extract from

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

Implements multiplicity control for confirmatory clinical trials using graphical procedures (Bretz-Maurer-Hommel), gatekeeping (parallel, serial, mixed), Hochberg/Hommel/Holm with PRDS, and the closed-testing principle (Marcus-Peritz-Gabriel; Goeman 2021 admissibility). Covers FDA Multiple Endpoints Final Guidance (October 2022), graphical procedures via R gMCP, primary + key-secondary + subgroup

Geração de prompts para simulação de agentes e GEO para auditoria de visibilidade de IA. Utilize para criar tarefas de simulação via TPC CLI, gerar prompts GEO sem marca para testar recomendações de produtos por IA, ou executar simulações de agentes.

Upgrade superskills to the latest version. Pulls from GitHub, re-runs setup, and shows the version change. Use when asked to "upgrade superskills", "update superskills", or "get the latest version of superskills".