Receber por email
← Voltar para o catálogo

research

The research topic or question.

25estrelas
Atualizado há 5 meses

Ver no GitHub ↗ Licença: MIT

Como adicionar

/plugin marketplace add theagenticguy/erpaval

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/research-theagenticguy/svg)](https://www.skillteca.com.br/skills/research-theagenticguy)

Skills relacionadas

Ver todas de Pesquisa e Web →

Alerta por categoria

Receba novas skills de Pesquisa e Web toda segunda

1 email curto, só com as skills novas de Pesquisa e Web. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

Contents

| Reference | When to load | | --------------------------------- | --------------------------------------------------- | | references/orchestrator.md | Running /research <topic> — the full 5-phase flow | | references/write-protocol.md | Copy verbatim into every agent prompt | | references/search-strategies.md | Tool inventory, priority order, query patterns | | templates/agent-skeleton.md | Per-agent Markdown file skeleton | | templates/synthesis-skeleton.md | Synthesis output skeleton |

Research

A single-mode research orchestrator. Runs inside a forked subagent so the main conversation stays clean. Decomposes the question, launches 2–4 Opus 4.7 agents in parallel with a file-first write protocol, monitors progress by reading their files, recovers stuck agents, and then runs one synthesis pass to produce the final brief.

How it works

Read references/orchestrator.md and follow its phases. The short version:

  1. Plan — decompose into 2–4 workstreams with non-overlapping scopes and 3–6 sections each. Present plan. Wait for approval.
  2. Skeletons — create research/{slug}/ and write a file per agent plus a synthesis file, each starting with Status: IN PROGRESS.
  3. Launch — fire all research agents in one message as parallel Agent calls with model: "opus" and run_in_background: true.
  4. Monitor — escalating check-ins (30s → 2m → 5m). wc -l per file to track progress. If an agent's line count stalls across two checks, launch a fresh Agent with the existing file state and a "skip these sections" prompt.
  5. Synthesize — one foreground Agent reads every agent file and writes synthesis.md with themed findings, contradictions, confidence, gaps, next steps, and deduplicated sources.

Write discipline

Every agent prompt carries the write protocol verbatim from references/write-protocol.md: one search or fetch → edit the file with findings → next search. This keeps partial progress on disk where it survives timeouts and 403 errors.

Citation conventions

  • Inline Markdown links with publication date when available: Source Name, 2026-04-15.
  • Citations for the same point are ordered newest-first.
  • Primary focus on the last 6 months. Reach further back only for canonical sources or when recent literature is thin.
  • Synthesis builds a deduplicated Sources section at the end, newest-first.

Cost note

All research and synthesis agents run as Opus 4.7 in parallel. Expect significant token usage on a full run — 2–4 parallel Opus agents plus one synthesis pass. Worth it for the quality, but know what you're ordering.

Compartilhar X LinkedIn