OffchainLabs/arbitrum-docs / .agents/skills/research
research
VerifiedStandalone domain research using researcher. Use for exploring similar solutions, patterns, constraints, and failure lessons without running the full PRD workflow. Triggers on "research this", "find similar solutions", "what patterns exist", "explore options".
Standalone Research
Delegates to researcher for focused domain research outside of PRD workflow.
When working on Arbitrum projects, use @arbitrum-best-practices for domain-specific patterns.
When to Use
- Exploring a problem space before committing to a solution
- Finding similar implementations in the Arbitrum ecosystem
- Understanding technical constraints before requirements gathering
- Learning from failures in similar projects
Process
1. ArbitrumDocs Research (Primary)
- Search official Arbitrum documentation first
- Query for existing patterns, constraints, and gotchas
- Find canonical implementations and examples
2. Similar Solutions Analysis
- Identify 3-5 comparable implementations
- Document strengths, weaknesses, architecture
- Extract key learnings
3. Pattern & Anti-Pattern Discovery
- Catalog proven patterns for the domain
- Document known anti-patterns to avoid
- Learn from project failures
4. Constraint Mapping
- Performance, compatibility, scalability limits
- Technology options with trade-offs
- Arbitrum-specific considerations
Output Format
# Research: [Topic]
## Similar Solutions
| Solution | Strengths | Weaknesses | Key Learning |
|----------|-----------|------------|--------------|
## Patterns
- [Pattern]: [When to use] - [Benefit]
## Anti-Patterns
- [Anti-pattern]: [What goes wrong] - [Alternative]
## Constraints
- [Constraint]: [Impact] - [Mitigation]
## Arbitrum-Specific Considerations
- [Finding from ArbitrumDocs]
## Recommendation
[1-2 paragraph summary with suggested approach]
Example Usage
/research token bridge architectures for custom ERC20s
/research Orbit chain gas token configurations
/research retryable ticket failure handling patterns
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 114k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 114k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 114k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 114k | Updated | Claude CodeCodex | Verified | Install |