Explorar skills

Use when user says "research competitors", "competitive analysis", "how do we compare to X", when planning go-to-market and needs competitive positioning, when assessing the competitive landscape before launch, or when objection handling and win/lose scenarios need to be documented.

Árvores geradoras mínimas — Kruskal (Union-Find, O(E log E)) e Prim (heap, O((V+E) log V)), agrupamento MST.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

三機(Claude/Gemini/Codex)平行審查計畫，評估完整性、順序、風險後投票共識

Do not discard a function's final value with return (), pure (), or void; adjust the type to return the value and let the caller discard it when unneeded. Use when writing or reviewing Haskell functions that return unit or discard results.

Autonomous security vulnerability scanner for codebases. Detects secrets, XSS, missing security headers, auth issues, OWASP Top 10 patterns, dependency vulnerabilities, PII exposure, CORS misconfiguration, and more. Aligned to OWASP APTS (Autonomous Penetration Testing Standard) Foundation tier. Outputs SARIF JSON, Markdown report, and APTS Conformance Claim. Use when the user wants a security aud

Geneformer e scGPT para Modelagem de Células Únicas.

Git 大师技能，涵盖交互式变基、工作树管理、reflog 恢复、bisect 调试、高级工作流、提交信息最佳实践和清晰的历史管理。使用此技能进行高级 Git 操作、清理提交历史、管理多个工作树、恢复丢失的提交、使用 bisect 调试或实现复杂的 Git 工作流时使用。

Use this skill when the user runs /help, /help commands, or /help <command-name>. Shows plugin command reference. Read-only — writes nothing, modifies nothing.

Use this skill on EVERY Edit, Write, or code-modification tool call. Enforces minimum-diff discipline — only touch files listed in the plan's in-scope list, only modify functions listed in the plan's in-scope functions, never modify adjacent functions, never refactor or rename unrelated code, never "fix while you're here". Unrelated bugs get logged to the follow-ups file, not fixed inline. This sk

Convergence diagnostics, fit evaluation, and debugging for Marketing Mix Models. Use when checking rhat, ESS, divergences, evaluating model fit metrics (R-squared, MAPE, wMAPE), debugging sampling issues, assessing overfitting, running model comparison (LOO/WAIC), or validating cross-validation results. Also activate when the user encounters convergence warnings, poor model fit, or needs to unders