Explorar skills

Use when preparing a sales demo, an investor demo, a partner walkthrough, or any scripted product flow with talking points. Use 48-72 hours before the live demo so there's time for dry-run, seed data verification, and fallback rehearsal.

Use when validating whether a biblical passage constitutes a coherent discourse unit. Use when user asks to check passage boundaries, evaluate if a text range is a natural pericope, or needs to know if their selected passage should be extended or contracted.

Run the execution + quality polish + delivery stages of review-loop against one of three entry modes: resume an approved session (`--session`), execute a user-supplied plan (`--plan`), or run a pure-CR pass on the current working tree (`--review-only`). Supports batched runs via `--stop-after <stage>`. Use when you already have a plan, or only want CR on existing code.

Referência completa da API DeepRead, cobrindo todos os endpoints, autenticação, formatos de requisição/resposta, blueprints, webhooks, tratamento de erros e exemplos de código para OCR, extração estruturada, preenchimento de formulários e redação de PII.

Variáveis e tipos de dados Python para bioinformática, abordando nomeação, mutabilidade, referências e tipos numéricos e de string.

Identificação de metabólitos a partir de espectros MS/MS: correspondência espectral, previsão de fórmula molecular e busca em bancos de dados (HMDB, KEGG). Use ao anotar metabólitos desconhecidos.

Multi-model agent implementation workflow for software development. Orchestrates research, evaluation, design baseline, implementation, RCA, structured decomposition, constraint discovery, model selection, and agent-driven Stage 3 codemap exploration across external AI models (GPT, GLM, Claude). Use when implementing features through a structured multi-phase pipeline with planspace/codespace separ

Use this skill whenever a task requires integrating with an external or internal API — HTTP clients, SDK calls, gRPC stubs, webhooks, or any network boundary. Verifies that an API spec (OpenAPI/Swagger, GraphQL schema, Protobuf, AsyncAPI, or equivalent) is configured and referenced in the plan or design artifact, then probes the endpoint to confirm reachability in the current environment. If the s

MAGI System - 三機平行共識決策系統，參考新世紀福音戰士的 MAGI 超級電腦。三機（Claude Opus、Codex-CLI、Gemini）同時平行分析同一任務，各自提出觀點後進行投票共識。支援 brainstorming、架構審查、plan、review、security、test 等任務類型。

Cross-check every numeric claim in a manuscript against the actual R / Python outputs that produced it, and report PASS / FAIL per claim against numeric tolerances. Use when the user says "audit reproducibility", "check my numbers", "verify the tables match the code", "reproducibility audit", "do the paper numbers match", or before submitting / resubmitting a paper or releasing a replication packa

Operações de string em Python para sequências biológicas: complemento reverso, extração de códons, varredura de motivos, parsing FASTA. Padrões e armadilhas bio-específicos.

Análise de sequenciamento de bissulfito: processamento WGBS/RRBS, identificação de DMRs e estimativa do relógio epigenético.