Desenvolvimento

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headli

Criação completa de PR de ponta a ponta, incluindo configuração de branch, implementação, testes, commit, push e abertura de PR no GitHub.

Especialização em análise de comunicação célula-célula (CCC), com roteamento de intenção para ferramenta, padrões de fluxo de trabalho, modelos de código e avisos de armadilhas. Abrange LIANA+, CellPhoneDB, CellChat, NicheNet, COMMOT, Squidpy, MEBOCOST, DIALOGUE e mais de 10 ferramentas para dados de scRNA-seq e transcriptômica espacial.

Use when the user pastes a URL from an external board (Linear, GitHub, Trello, Azure DevOps, Jira, Slack, or a custom internal board) or refs a card by id. Detects the provider via configured URL patterns, probes whether the provider's MCP tool is connected in Claude Code, and either fetches the card body via that MCP or falls back to asking for paste. Pre-fills source_* fields on the resulting wo

Use when the user describes work, or recent file edits touch paths, that aren't owned by any active persona. Detects emerging specialization signals (a new file type appearing repeatedly, a directory pattern unique to a specialty, a request mentioning a domain outside boardmaster/developer/ reviewer/architect/researcher scope) and surfaces a suggestion: either activate an existing library persona,

Packs the entire codebase (or selected folders) into a single token-efficient file using repomix, so other skills can analyze the whole repo without re-reading individual files. Use when the task requires whole-codebase context: full security audits, cross-cutting refactors, architecture review, project-wide code review, or first-time onboarding to an unfamiliar repo. Auto-runs once per session at

Aplica convenções de nomenclatura de branches, estratégia de merge e limpeza. Use ao criar branches, fazer merges ou quando o usuário perguntar sobre fluxo de trabalho Git ou estratégia de branches.

Test-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, Vitest, and Mocha. Use when the user asks to write tests, improve test coverage, practice TDD, generate mocks or stubs, or mentions testing frameworks like Jest, pytest, or JUnit.

Severity definitions, approval gate protocol, and fix constraints shared across all review and test skills.

Create comprehensive MATLAB unit tests using the MATLAB Testing Framework. Use when generating test files, test cases, unit tests, test suites, or when the user requests testing for MATLAB code, functions, or classes.

Structured retrospective and lesson extraction. Use when reflecting on completed work or projects. Triggered by "learning", "retrospective", "what did we learn?", "reflection", or "what to apply next time".

Uma Skill de 'irmã mais velha' gentil, com uma personalidade de IA que é suave por fora e forte por dentro, oferecendo suporte emocional poderoso, inclusivo e curativo.