/ask
Answer a strategic question using accumulated research
Command definition
ask.mddescription: Answer a strategic question using accumulated research
allowed-tools: Read, Glob, Bash
Answer Strategic Question
Use accumulated research findings to answer the user's question.
Context
The user will provide a question after this command, like:
- `/ask What opportunities exist in AI agents?`
- `/ask What are the main risks we should watch?`
- `/ask Should we pursue [specific opportunity]?`
Steps
1. **Understand the Question**
- Parse the user's question
- Identify key topics and themes to search for
2. **Search Research Findings**
- First, discover the researcher's shared folder: `ls /home/developer/shared-in/`
- Look for a folder containing "researcher" in the name
- Read all available findings from that folder's `findings/` subdirectory
- Look for relevant information matching the question topics
- Note supporting evidence and sources
3. **Synthesize Answer**
- Compile relevant findings
- Draw connections between data points
- Form a coherent answer
4. **Provide Response**
## Question
[Restate the question]
## Answer
[Clear, direct answer based on research]
## Supporting Evidence
1. **[Finding 1]** (from [date])
- [Relevant detail]
2. **[Finding 2]** (from [date])
- [Relevant detail]
## Confidence Level
[High/Medium/Low] - based on [amount of supporting data]
## Caveats
- [Any limitations or gaps in the research]
## Suggested Follow-up
- [Additional research that could help]
5. **Handle Missing Data** If insufficient research exists:
- State what information is missing
- Suggest running `/request-research [topic]` to gather more data
Answer the question now.
Read more
description: Answer a strategic question using accumulated research allowed-tools: Read, Glob, Bash
Answer Strategic Question
Use accumulated research findings to answer the user's question.
Context
The user will provide a question after this command, like:
- `/ask What opportunities exist in AI agents?`
- `/ask What are the main risks we should watch?`
- `/ask Should we pursue [specific opportunity]?`
Steps
1. **Understand the Question**
- Parse the user's question
- Identify key topics and themes to search for
2. **Search Research Findings**
- First, discover the researcher's shared folder: `ls /home/developer/shared-in/`
- Look for a folder containing "researcher" in the name
- Read all available findings from that folder's `findings/` subdirectory
- Look for relevant information matching the question topics
- Note supporting evidence and sources
3. **Synthesize Answer**
- Compile relevant findings
- Draw connections between data points
- Form a coherent answer
4. **Provide Response**
## Question [Restate the question] ## Answer [Clear, direct answer based on research] ## Supporting Evidence 1. **[Finding 1]** (from [date]) - [Relevant detail] 2. **[Finding 2]** (from [date]) - [Relevant detail] ## Confidence Level [High/Medium/Low] - based on [amount of supporting data] ## Caveats - [Any limitations or gaps in the research] ## Suggested Follow-up - [Additional research that could help]
5. **Handle Missing Data** If insufficient research exists:
- State what information is missing
- Suggest running `/request-research [topic]` to gather more data
Answer the question now.
Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.
Other commands on trinity.
More commands from other plugins.
setup
CommandOne-time setup after installing ARIS as a Claude Code plugin — registers the Codex reviewer MCP server from the plugin directory…
autoresearch
CommandAutonomous iteration loop: modify, verify, keep/discard against any metric
agent
Commandname: sc:agent description: SC Agent — session controller that orchestrates investigation, implementation, and review category:…

