Explorar skills

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Use when implementation, review, security, scalability, or incident work reveals that an upstream .forge/ artifact is wrong, when a contract is missing an operation, when an ADR is being contradicted by a current need, when security recommends architecture changes, or when the user says "we discovered the spec is wrong".

Integração com BioPython Seq/SeqRecord/SeqIO, API Entrez do NCBI, consultas UniProt e conversão de formatos biológicos.

Redija PII de documentos antes de compartilhar, usando IA sensível ao contexto para detectar 14 tipos como nomes e cartões de crédito. Aplica redação com barra preta em PDFs, imagens e textos, com um nível gratuito de 2.000 páginas/mês.

Receitas de análise de FASTA/FASTQ/CSV, padrões de E/S de arquivo por streaming e armadilhas específicas de formato para arquivos de dados de bioinformática.

Use when the user wants to "solve a model", "run the algorithm", "compute the solution", "find the optimal", "prove this theorem", "implement the solver", "solve this problem", "what algorithm should I use", "optimize this", "find the answer", or needs to execute a mathematical solution with computational rigor. This is the solving engine for models produced by /uber-model.

On-demand sales battlecards for live competitive deals - positioning matrix, top objections with responses, trap questions, proof points, and a "do not say" list. Use when: competitor surfaced in deal, sales battlecard, competitive enablement, deal-specific battlecard, objection handling, competitive trap questions, why we win against, why we lose to, displacement playbook.

Activate when the user wants to add APM governance, lockfile/audit readiness, or multi-runtime package management to an existing Claude/Copilot/agent plugin, or explicitly convert a plugin into an APM-native package.

Iteradores personalizados para bioinformática, incluindo iteração de códons, geração de k-mers, streaming FASTA/FASTQ e padrões de processamento lazy de sequências.

Environment health check and auto-remediation for vibe-* projects. Checks node_modules vs package.json drift, nested .git directories, Tailwind and shadcn version mismatches, dotenv load order, Vite HMR WebSocket config, husky hook permissions, ESLint config validity, TypeScript path resolution, and missing dependencies in generated code. Auto-remediates where safe. Flags where human action is nee

Verifies that os-architect actually causes evolution — not just words. Dispatches os-architect in single-shot simulation mode for a given test scenario, then checks for real artifact presence (new files, HANDOFF_BLOCK, plan files). Reports PASS / FAIL with grep evidence. Accumulates results into a test report. Use after any changes to os-architect, os-evolution-planner, or improvement-intake-agent

A standard Spec-Kitty workflow routine.