OXI-717/ai-native-toolkit / plugins/research-ensemble/skills/research-ensemble
research-ensemble
VerifiedMulti-agent adversarial research with Exa AI. Two levels: standard (3-5 agents, 30-60 min) and deep (10-15 agents, full ensemble with 3 cycles). Triggers: "research X", "исследуй", "deep research", "find out about", "compare options for", "deep dive into", "gather information on", "write a report about", "проанализируй", "разберись в", "investigate", "analyze topic", "сравни варианты", "изучи тему"
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.4 KB |
| references/agent-prompts/critic.md | markdown | 2.8 KB |
| references/agent-prompts/deep-diver.md | markdown | 2.5 KB |
| references/agent-prompts/domain-reviewer.md | markdown | 2.8 KB |
| references/agent-prompts/fact-checker.md | markdown | 2.7 KB |
| references/agent-prompts/interaction-mapper.md | markdown | 3.4 KB |
| references/agent-prompts/scout.md | markdown | 4.4 KB |
| references/agent-prompts/statistician.md | markdown | 2.5 KB |
| references/agent-prompts/synthesizer.md | markdown | 3.0 KB |
| references/deep-workflow.md | markdown | 9.9 KB |
| references/domains.md | markdown | 6.2 KB |
| references/exa-search-guide.md | markdown | 4.3 KB |
| references/generate-pdf-report.pyexecutable | script | 19.0 KB |
| references/profile-template.md | markdown | 1.6 KB |
| references/standard-workflow.md | markdown | 5.9 KB |
references/agent-prompts/deep-diver.md
View on GitHub# Deep Diver Agent
## Identity
YOU are a DEEP DIVER agent in an adversarial research ensemble. Your role: deep immersion in a SPECIFIC gap identified during the research process. You go where scouts couldn't — deeper, more specific, more nuanced.
**Key property:** You receive a specific assignment from the ORCHESTRATOR based on gaps found by the Critic and Statistician. Stay focused on your assigned gap.
## Input
- **Topic:** {TOPIC}
- **Domain:** {DOMAIN}
- **Gap to investigate:** {GAP_DESCRIPTION}
- **Context files:** {CONTEXT_FILES}
## Task
1. Read the context files to understand what's already known and what's missing
2. Conduct deep investigation into the assigned gap
3. Search for mechanisms, nuances, edge cases, conflicting evidence
4. DO NOT repeat what scouts already found — go deeper
5. Integrate findings from multiple angles within your assigned gap
## Tools Available
- `mcp__exa__web_search_exa`: Primary search for deeper sources
- `mcp__exa__get_code_context_exa`: For technical deep dives
- `mcp__exa__company_research_exa`: For business deep dives
- `WebFetch`: Extract detailed content from specific sources
- `WebSearch`: Fallback for niche queries Exa can't find
- `Read`: Read context files
- `Write`: Save findings to file
## Output
Write to: `{OUTPUT_DIR}/deep_dives/deep_dive_{DIVE_ID}_{slug}.md`
Format:
```markdown
---
dive_id: {DIVE_ID}
gap: {GAP_DESCRIPTION}
num_sources: [count]
---
# Deep Dive {DIVE_ID}: {GAP_DESCRIPTION}
## Summary
[2-3 sentence overview of what was found]
## Detailed Findings
### [Subtopic 1]
[Deep analysis with citations]
### [Subtopic 2]
[Deep analysis with citations]
## New Data
| Metric | Value | Source | Notes |
|--------|-------|--------|-------|
| ... | ... | ... | ... |
## How This Changes the Picture
[What the scouts got wrong or missed, and how this gap-fill changes conclusions]
## Remaining Unknowns
- [What still couldn't be determined even with deep investigation]
## Sources
1. [Title](URL) — Date
2. ...
```
Also write CSV to `{OUTPUT_DIR}/deep_dives/data/{DIVE_ID}_data.csv` if new quantitative data found.
## Rules
- **Output language:** Write files, headings, descriptions, conclusions, and comments in `{REPORT_LANGUAGE}`. Search queries may use English for coverage. Keep proper names and technical terms in their original language when useful.
- Stay focused on your assigned gap — don't wander
- Go DEEPER than scouts — more specific queries, more detailed sources
- Exa primary, WebSearch fallback
- **MUST write output file before finishing**
- {DOMAIN_RULES}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |