Desenvolvimento

Step through a simulation agent replay to find where and why it failed — timeout, invalid move, crash, or strategic collapse. Use when the user says "debug the agent", "why did it lose", "find the failing turn", "analyze the replay", or after a regression in local eval.

Orquestre um fluxo de trabalho Git abrangente, desde a revisão de código até a criação de PRs, utilizando agentes especializados para garantia de qualidade, testes e prontidão para implantação. Este fluxo de trabalho implementa g moderno.

Cria automaticamente changelogs para usuários a partir de commits Git, analisando o histórico de commits, categorizando mudanças e transformando commits técnicos em notas de lançamento claras e amigáveis ao cliente. Transforma horas de escrita manual de changelogs em minutos de geração automatizada.

MaxQuant + Perseus proteomics pipeline: run MaxQuant for LFQ and SILAC; parse proteinGroups.txt in Python; filter contaminants/decoys; log2 + median-normalize; impute MNAR; t-test with FDR; volcano plot; GO/pathway enrichment. Use Proteome Discoverer for Thermo-native processing; FragPipe/MSFragger for GPU-accelerated DB search.

Diagnose machine learning training failures including loss divergence, mode collapse, gradient issues, architecture problems, and optimization failures. This skill spawns a specialist ML debugging ...

Adversarial pressure-test of a decision, plan, or piece of work. Articulates the case FOR the current approach, then spawns a subagent to steel-man the best alternative, returns a synthesis with mandatory verdict. Invoke ONLY via /adversary — do NOT trigger on 'what do you think' or 'any concerns'.

Python testing framework for writing simple, scalable, and powerful tests

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

Extract, filter, annotate, and export differential expression results from DESeq2 or edgeR. Use for identifying significant genes, applying multiple testing corrections, adding gene annotations, and preparing results for downstream analysis. Use when filtering and exporting DE analysis results.

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

Validates that code actually works through sandbox testing, execution verification, and systematic debugging. Use this skill after code generation or modification to ensure functionality is genuine rather than assumed. The skill creates isolated test environments, executes code with realistic inputs, identifies bugs through systematic analysis, and applies best practices to fix issues without brea

This skill should be used when the user asks to "track work across sessions", "create an epic", "manage issue waves", "post a checkpoint", "claim an issue", "recover from compaction", "coordinate multiple agents", "update memory bank", "store large documents", or mentions GitHub Issues as persistent memory, multi-session work, context survival, agent collaboration, SERENA MCP memory, or project-le