Desenvolvimento

Rastreamento automático de projetos, gerenciamento de progresso e agentes de qualidade em segundo plano para o Claude Code.

英语全场景辅导(K-12)。K-3 字母 + 拼读 + 简单单词;4-6 词汇扩展 + 简单句子 + 阅读;7-9 语法 + 完形 + 阅读 + 写作;10-12 高级阅读 + 七选五 + 应用文 + 续写 + 听说。新词不机械背,要求造句和追问。当孩子或家长发来英文题、说"英语不会"、或题目含英文单词/句子时使用。

Enriquecimento de Gene Ontology e vias, incluindo estrutura GO, teste hipergeométrico/Fisher, ORA vs GSEA, FDR de Benjamini-Hochberg e padrões de API KEGG/Reactome.

Structured post-launch retrospective that produces quantified learnings and improvement playbooks. Use when: launch retrospective, post-launch review, what worked, launch debrief, post-mortem, lessons learned.

Revenue forecasting pipeline - bottoms-up pipeline forecast, tops-down model, ensemble blending, scenario analysis, and forecast calibration loop. Use when: revenue forecast, sales forecast, pipeline forecast, bookings forecast, NRR forecast, ARR forecast, forecast calibration, scenario planning, ensemble forecasting, board forecast.

A skill issue-to-pr corrige automaticamente problemas do GitHub de ponta a ponta, lendo o problema, analisando o código, implementando uma correção e enviando um pull request. Utilize-a quando uma URL de problema do GitHub for fornecida, a correção de um problema for mencionada ou o comando /fix-issue for usado.

Launch orchestration and readiness assessment engine with cross-functional workstream tracking and go/no-go gates. Use when: launch readiness, launch checklist, launch orchestration, go no go, launch plan, are we ready to launch.

Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic back-and-forth debate where both agents discuss findings, architecture decisions, or implementation plans until reaching consensus. Codex CLI runs READ-ONLY and never modifies files; model and reasoning effort come from the user's local Codex config. Supports plan mode: when the local age

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

Save a preference to CLAUDE.md so it persists across sessions. Triggered by /remember or natural-language phrases like "remember to..." or "from now on, always...".

Fetch and execute a remote skill on-the-fly without installing it permanently. Use when the user wants to try a skill once, run a skill from GitHub, use a remote skill without installing, or mentions "use-remote-skill", "run remote skill", "try this skill", "fetch skill", "one-time skill", or provides a GitHub URL/shorthand pointing to a skill they want to execute. This is the go-to skill whenever

Code review for PRs or local changes. Covers code quality, dependency updates, performance, test coverage, documentation accuracy, and security. Use when reviewing PRs, checking code quality, or running comprehensive code reviews.