Pesquisa e Web

Esta skill implementa um planejamento baseado em arquivos estilo Manus para organizar e acompanhar tarefas complexas, criando task_plan.md, findings.md e progress.md. É ideal para projetos multifásicos ou pesquisas que exigem mais de cinco chamadas de ferramenta, e suporta recuperação automática de sessão.

6-model R&D Council debate — multi-round argument, cross-examination, consensus memo. Triggers: "/debate", "council", "R&D meeting", "model debate", "6 models discuss". NOT FOR: simple questions (just ask), code review (use review), brainstorming. Produces: executive memo with consensus position from 6 AI models.

Compresses verbose text into the shortest precise phrasing that preserves every constraint and leaves zero ambiguity. Use whenever the user wants to shorten, compress, tighten, distill, or cut down any text — CLAUDE.md sections, README files, AGENTS.md personas, CONTRIBUTING.md, commit messages, error messages, package descriptions, or any prose that says too much with too many words. Also use whe

Strategic reality check for any project. Researches whether the solution already exists, whether there are better approaches, and whether the codebase follows current best practices — using live documentation, not stale training data. Use this skill when the user says 'perspective', 'am I on the right track?', 'is there a better way?', 'has someone already built this?', 'reality check', or any req

Debug common ML training issues (NaN loss, OOM, slow training, convergence problems) and provide solutions. Use when training fails, metrics don't improve, or encountering errors like NaN loss, CUDA OOM, or slow convergence.

Conduct technical research using Gemini CLI, producing comparison reports with recommendations and code examples. Use when evaluating technologies, comparing libraries, or running /research.

Orchestrate hierarchical multi-agent research with lead agents, sub-agents, critical review, and synthesis. Use for deep investigation tasks, research projects, complex analysis, or when exploring unfamiliar topics thoroughly.

Find visual design references for a new project. Use when the user wants to find real-world design inspiration, establish a visual design direction, or create a design brief based on existing apps or sites.

Entry point for the Signal Prospecting Kit. Deep onboarding: researches the user's company from their domain, captures ICP, stack, and voice. Routes to /profile for market research. Triggers: /start, first run, "help me set up". Reads: ./gtm/ (all files). Writes: ./gtm/company.md, ./gtm/icp.md, ./gtm/voice.md. Standalone: yes.

Full-spectrum web application VAPT skill for Claude Code, OpenCode, Codex CLI & Gemini CLI — from reconnaissance to exploitation to remediation reporting

Audits any website for SEO, AEO (Answer Engine Optimization), GEO (Generative Engine Optimization), and Structured Data. Crawls with Playwright, runs Lighthouse, checks Perplexity citations, applies research-backed rules, scores deterministically, and produces a prioritised fix list with letter grades. Use this skill whenever the user mentions a domain or URL and wants to know what's wrong with it

Execute training runs with proper monitoring, checkpointing, and experiment tracking. Use when starting training, resuming training, debugging training issues, or setting up multi-GPU/distributed training with PyTorch Lightning and Hydra.