From ark
Researches technical solutions by searching the web, examining GitHub repos, and gathering evidence. Use when exploring implementation options or evaluating technologies.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ark:researchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Research technical solutions and gather evidence before implementation.
Research technical solutions and gather evidence before implementation.
Always start with web search to find:
GitHub raw content is often blocked. Clone repos to examine them:
cd /tmp
git clone https://github.com/owner/repo.git
cat /tmp/repo/README.md
Look for:
If a website cannot be loaded:
Example prompt:
"I found a relevant resource at [URL] but cannot access it. Could you paste the key content or provide the PDF?"
Store findings in ./scratch/research/ for review:
mkdir -p ./scratch/research
Save:
Minimum 2-3 datapoints required before recommending a solution:
If insufficient evidence, ask for guidance:
"I found only one reference to this approach. Can you point me to additional resources or clarify the requirements?"
Always back up findings with sources:
## Research: [Topic]
### Option 1: [Solution Name]
- **Source**: [URL or repo link]
- **Pros**: ...
- **Cons**: ...
- **Evidence**: [What confirms this works]
### Option 2: [Solution Name]
...
### Recommendation
Based on [N] sources, I recommend [Option] because...
### Sources
- [Title](URL)
- [Repo](GitHub URL) - cloned and examined
- [Spec](URL) - user provided
User: "Research options for terminal recording in an MCP server"
npx claudepluginhub mckinsey/agents-at-scale-ark --plugin ark3plugins reuse this skill
First indexed Jul 15, 2026
Conducts deep research into technical solutions by web searching, cloning/examining GitHub repos, gathering evidence from docs/examples, and comparing options with sources.
Researches questions across library docs, web, local code, GitHub, and wiki, then synthesizes findings with explicit confidence.
Conducts deep technical research using EXA tools with two-tier caching for cross-project reuse via git scoping. Supports /research, promote, refresh, list operations for best practices, architectures, patterns.