Pesquisa e Web

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

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

Start the Native Python ChromaDB background server. Use when semantic search returns connection refused on port 8110, or when the user wants to enable concurrent agent read/writes.

Drafts paper sections (Intro, Lit Review, Method, Empirical Setting, Empirics, Discussion, Limitations, or arbitrary paragraphs) in the user's voice — hedged, modest, natbib-apa citations, \Cref cross-references, \emph over \textit, figure/table notes minipages, three-stream lit-review structure. Use this skill whenever the user asks to "draft", "write", "rewrite in my voice", "give me a paragraph

Autorreflexão sistemática e refinamento iterativo de saídas para agentes de IA, baseado em Self-Refine, Reflexion e o padrão de Reflexão de Andrew Ng. Ideal para ciclos de crítica e melhoria em várias rodadas, quando a qualidade inicial é insuficiente ou para tarefas complexas que se beneficiam da autocorreção.

Shklovsky-inspired peripheral-vision audit of a SINGLE figure or table in a quantitative-marketing paper. Forces a four-quadrant grid — Unexplained Feature, Convenient Absence, Unasked Question, Unexploited Strength — to surface what the author has stopped seeing in a coefficient plot, DiD event-study, conjoint utility plot, predicted-engagement curve, GAN attribute-axis image grid, SAE feature he

Converta um PDF de pesquisa em um pacote Markdown de fonte rica usando Mistral OCR, e então traduza e corrija-o para Markdown chinês combinando o markdown original com imagens de páginas PDF renderizadas.

(Industry standard: Loop Agent / Single Agent) Primary Use Case: Self-contained research, content generation, and exploration where no inner delegation is required. Self-directed research and knowledge capture loop. Use when: starting a session (Orientation), performing research (Synthesis), or closing a session (Seal, Persist, Retrospective). Ensures knowledge survives across isolated agent sessi

Competitive intelligence engine that deconstructs competitor positioning, surfaces exploitable weaknesses, and predicts competitive responses. Use when: competitive analysis, competitor research, competitive landscape, competitive intelligence, who are our competitors, how do we compete against.

Um sistema de descoberta de habilidades de IA e gerenciamento de capacidades, o único guia inteligente de habilidades no mundo chinês. Ajuda usuários a encontrar, avaliar, instalar e gerenciar habilidades de Agente, com recomendações atualizadas regularmente, para qualquer ação relacionada a habilidades em chinês ou inglês.

Memory-as-a-Service para agentes de IA, permitindo armazenar e recuperar memórias com busca vetorial semântica. Oferece 100 chamadas gratuitas por carteira, seguidas de micropagamentos x402, e seu endereço de carteira é sua identidade.

Run a 6-agent pre-submission referee report for an academic paper targeting a specified journal. Covers spelling/style, internal consistency, unsupported claims, math/notation, tables/figures, and an adversarial top-journal referee evaluation. Supports marketing (MKSCI, JMR, JCR, MS) and economics/finance journals.