Agent skill
research
Use when the user asks to research, investigate, compare approaches, or explore a topic in depth. Supports configurable depth and multi-source synthesis.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/research-cmtkdot-arc
SKILL.md
Research
Deep research with multi-source synthesis. Uses multi-ai skill for provider routing when available.
Workflow
Step 1: Determine Depth
Use AskUserQuestion if depth is not specified:
- Quick: Fast overview of key concepts (2-3 sources)
- Standard: Comprehensive analysis with examples (5-8 sources)
- Deep: Thorough research with citations and evidence (10+ sources)
If the user provides --depth, skip the question.
Step 2: Provider Routing
- If
ARC_MULTI_AI=trueand providers are available, use multi-provider research viamulti-aiskill. - Otherwise run Claude-only research with the same structure.
Step 3: Multi-Source Synthesis
Launch the persona-research-synthesizer agent with gathered context:
subagent_type: "arc:persona-research-synthesizer"
run_in_background: true
prompt: "Research topic: <topic>\nDepth: <depth>\nProviders: <available providers>"
Output a status message and end your turn. The system wakes you when the agent finishes.
Step 4: Report Results
## Research Complete
**Topic**: <topic>
**Depth**: <quick|standard|deep>
**Sources Consulted**: <count>
### Key Findings
[Structured findings with evidence]
### Comparative Analysis
[Pros/cons of different approaches]
### Recommendations
[Actionable recommendations with rationale]
### Next Steps
- `/arc:core:plan` to plan implementation based on findings
- `/arc:specialized:prd` to write a PRD incorporating research
Error Handling
| Scenario | Action |
|---|---|
| Topic too broad | Ask user to narrow scope |
| No external providers | Continue with Claude-only research |
| Low confidence findings | Flag uncertainty, recommend deeper research |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?