Help us improve
Share bugs, ideas, or general feedback.
From erpaval
Runs multi-agent research: decomposes a question into parallel Opus agents that write findings to files, then synthesizes by theme. Useful for literature reviews, comparisons, or learning a domain.
npx claudepluginhub theagenticguy/erpaval --plugin erpavalHow this skill is triggered — by the user, by Claude, or both
Slash command
/erpaval:researchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
| Reference | When to load |
Executes multi-agent research pipeline on any topic with Scout, Investigators, Deep Diver, Verifier, Synthesizer, and Critic reviews to produce verified, sourced reports.
Conducts deep web research with parallel agents, multi-wave exploration for gaps, and structured synthesis. Activates for investigating topics, comparing options, best practices, or comprehensive web info.
Indexes deep research principle skills for methodology, source evaluation, hallucination prevention, and synthesis-reporting; provides /research command for orchestrated multi-agent web research with verification.
Share bugs, ideas, or general feedback.
| 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 |
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.
Read references/orchestrator.md and follow its phases. The short version:
research/{slug}/ and write a file per agent plus a synthesis file, each starting with Status: IN PROGRESS.Agent calls with model: "opus" and run_in_background: true.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.Agent reads every agent file and writes synthesis.md with themed findings, contradictions, confidence, gaps, next steps, and deduplicated sources.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.
[Source Name, 2026-04-15](https://url.com).Sources section at the end, newest-first.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.