From research-council
Launches multi-agent deep research on a topic using Claude and Codex with cross-pollination refinement, producing a structured synthesis report.
npx claudepluginhub hamelsmu/research-council --plugin research-council[--test] <research topic>Run the setup script to validate prerequisites and create the research workspace: If setup fails (non-zero exit code), help the user fix the issue (install missing CLIs, set API keys, etc.) and DO NOT proceed further. If setup succeeds (exit code 0), read the state file to get the research details: Extract the research_id, models, and workspace path (`research/<research_id>/`) from the state file. Tell the user: 1. The research council is now active with 2 AI agents (Claude, Codex) 2. They can monitor progress with: `tail -f research/<research_id>/progress.log` 3. When all agents fi...
/researchExecutes deep multi-AI research workflow, synthesizing multi-source analysis via orchestrated LLM agents with configurable breadth and intensity.
/research-deepLaunches Gemini Deep Research Agent for autonomous web-grounded research on a topic, after interview-driven brief refinement and prior context loading from knowledge base.
/researchExecutes multi-agent research pipeline on given topic with Scout, Investigators, Deep Diver, Verifier, Synthesizer, and iterative Critic review to produce verified synthesized insights.
/deep-researchConducts autonomous multi-agent deep research on topics, producing executive summaries, full reports (20-50+ pages), bibliographies with quality ratings. Supports resume, status, query via arguments or interactive menu.
/researchPerforms adaptive deep web research on a query with configurable --depth and --strategy options. Outputs markdown report with executive summary, analysis, confidence scores, and cited sources.
/deep_researchOrchestrates multi-agent deep research on a topic by analyzing complexity, generating sub-questions, spawning parallel research workers, and synthesizing cited reports.
Share bugs, ideas, or general feedback.
Run the setup script to validate prerequisites and create the research workspace:
set -o noglob; bash "${CLAUDE_PLUGIN_ROOT}/scripts/setup-research.sh" $ARGUMENTS; _rc=$?; set +o noglob; (exit $_rc)
If setup fails (non-zero exit code), help the user fix the issue (install missing CLIs, set API keys, etc.) and DO NOT proceed further.
If setup succeeds (exit code 0), read the state file to get the research details:
cat .claude/deep-research.local.md
Extract the research_id, models, and workspace path (research/<research_id>/) from the state file. Tell the user:
tail -f research/<research_id>/progress.logThen finish your response — the Stop hook will automatically launch all research agents. You do not need to run any additional commands.
When you are given the synthesis prompt (after the research agents complete), read ALL refined reports carefully and write a comprehensive synthesis to the specified path. Structure it as: