Pesquisa e Web

Building professional CLIs with Typer and Rich - type-safe argument parsing, progress bars, model visualization, Hydra integration, RichHandler logging, and multi-process handling for ML workflows

Interactive sprint worker. Reads status/ready + owner/ai items from GitHub Issues (or local backlog), presents them with context, groups into proposed PRs, and waits for your approval before building. Dispatches parallel sub-agents with self-review and full testing. Reads CONTEXT.md for domain terminology and .pm/out-of-scope/ for negative constraints. Trigger: "let's build", "work the backlog", "

Define a UX research plan including methods, participants, goals, and timeline. Use this skill when a team needs to structure a research effort before executing it.

Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.

Onboard Product Pulse to a new project. Interviews you about your product, competitors, target audiences, and strategic priorities, then scaffolds the research directory, pulse-config.yaml, research context, research sources, and deep-dives directory. Run this once when you first install the plugin. Use when you say "setup product pulse", "onboard", "configure pulse", "initialize research", or inv

Market research and validation agent. Analyzes competitors, identifies target users, and validates product-market fit before any code is written. Triggers on: market research, competitor analysis, validate idea, target audience.

Forneça aos agentes do Council Room um navegador real para navegar em páginas, extrair conteúdo, preencher formulários e raspar sites que bloqueiam buscas simples. Construído nativamente no Playwright, é ideal para monitorar concorrentes, pesquisar ou encontrar contatos.

Extracts individual entities from a large source document and creates separate .md files for each one. Use when a source contains multiple distinct entities that should each have their own file, or when user says "extract", "pull out entities", "split this file", or "create files from this source". Does NOT compile scattered info about one entity — use /compiling-entities for that.

Trigger on "pursue client", "pitch email", "follow up proposal", "call script proposal", "consult pursue", "cos pursue", "/cos-pursue {client} for {topic}". Post-pack pursuit: cover email, 30-min call script, objection stubs. Cold-start mode when only client + topic given — synthesizes pack from public research. Uses timeln-shipped and timeln-quickly. NOT packaging (consult-package), NOT frame (co

Cross-document and cross-code coherency analysis — finds contradictions, conflicting values, and inconsistencies across multiple files, then researches official sources to resolve factual errors and asks the user only about preference decisions. MUST use this skill whenever the user asks to compare, cross-check, cross-reference, or verify consistency between 2+ files of any type — docs, configs, c

Scans worldbuilding files for unexamined assumptions — descriptions, vocabulary, and social structures that were imported rather than derived from the civilization's biology, cognition, and environment. Applies to ALL civilizations: alien species get checked for anthropomorphism; human civilizations in novel contexts get checked for assumptions imported from familiar Earth cultures. Use after writ

Automação e extração universal de navegador para agentes de IA em sites, aplicativos web, dashboards e consoles de administração. Permite que agentes inspecionem páginas, naveguem por fluxos multi-etapas, pesquisem, extraiam dados estruturados, preencham formulários, gerenciem arquivos, lidem com paginação e trabalhem em sessões autenticadas, automatizando fluxos de trabalho web repetidos.