Stats
Actions
Tags
From deep-research
Run deep multi-agent web research on a topic and produce a cited report with archived sources
How this command is triggered — by the user, by Claude, or both
Slash command
/deep-research:research <research question>This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Deep Research ## Pre-flight Research question: $ARGUMENTS Existing research directories in the current working directory: !`ls -d research-*/ 2>/dev/null || echo "None found"` ## Instructions ### Step 1: Validate Input If $ARGUMENTS is empty or contains fewer than 3 words, respond with: > Please provide a research question. Usage: `/research <your question>` > > Examples: > - `/research What are the current approaches to AI alignment and their tradeoffs?` > - `/research How does the EU AI Act compare to US AI regulation?` Do not proceed further. ### Step 2: Check for Existing Rese...
Research question: $ARGUMENTS
Existing research directories in the current working directory:
!ls -d research-*/ 2>/dev/null || echo "None found"
If $ARGUMENTS is empty or contains fewer than 3 words, respond with:
Please provide a research question. Usage:
/research <your question>Examples:
/research What are the current approaches to AI alignment and their tradeoffs?/research How does the EU AI Act compare to US AI regulation?
Do not proceed further.
Review the list of existing research directories above. If any appear to cover the same topic as the current question:
If no relevant existing research found, proceed immediately.
Follow the deep-research:deep-researching skill's 6-phase process exactly:
deep-research:research-worker agents in parallel via Task tooldeep-research:source-archiver in backgroundWhen the report is complete, present:
npx claudepluginhub jamesprial/prial-plugins --plugin deep-research/researchConducts interactive deep research on a topic: captures and refines scope, decomposes into subtopics, performs parallel web searches with source verification, synthesizes into a well-sourced markdown document.
/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_researchOrchestrates multi-agent deep research on a topic by analyzing complexity, generating sub-questions, spawning parallel research workers, and synthesizing cited reports.
/researchPerforms deep autonomous research on any topic, saving a structured brief to a timestamped file. Supports --depth and --sources flags.
/SKILLConducts deep parallel research on a topic using web searches and tools, producing cited markdown files in research/ directory with validated URLs and synthesis summary.
/sc-researchConducts deep web research with adaptive planning and multi-hop searches on a query, producing a markdown report with executive summary, citations, confidence levels, and sources.