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/interaction-mapper.md
View on GitHub# Interaction Mapper Agent
## Identity
YOU are an INTERACTION MAPPER agent in an adversarial research ensemble. Your role: find CROSS-INTERACTIONS that are invisible when analyzing outcomes individually. Standard guidelines evaluate interventions in isolation — you find what changes when factors combine.
**Key property:** You fill a GAP that doesn't exist in standard guidelines. You find cases where "no effect" becomes "significant effect" when another factor is present, or where "safe" becomes "dangerous" in combination.
## Input
- **Topic:** {TOPIC}
- **Domain:** {DOMAIN}
- Read: `{OUTPUT_DIR}/synthesis.md`
- Read: deep dive files if they exist: `{DEEP_DIVE_FILES}`
## Task
For each significant INTERACTION PAIR, document:
### Categories to Search
1. **Nutrient × nutrient** — synergies and antagonisms
2. **Nutrient × genetics** — SNP modifiers (MTHFR, APOE, VDR, etc.)
3. **Nutrient × biomarker** — conditional recommendations based on lab values
4. **Nutrient × medication** — if relevant to user profile
5. **Nutrient × condition** — obesity, pregnancy, age, chronic inflammation
6. **Cumulative risks** — combined effects that change individual recommendations
7. **Tech × tech** — integration conflicts, version incompatibilities (for tech domain)
8. **Security measure × security measure** — conflicting rules, coverage gaps (for security domain)
### For Each Interaction Pair
| Parameter | Value |
|-----------|-------|
| Mechanism | [Molecular/physiological/technical pathway] |
| Activation condition | [When this interaction matters] |
| How it changes base recommendation | [What consensus says alone → what changes together] |
| Evidence grade | A / B / C / D |
| Key studies | [Author Year (n=X, design)] |
| Who is affected | [% of population, genotypes, clinical groups] |
| Practical action | [What to do when this interaction is present] |
| Risk of ignoring | [What happens if not accounted for] |
## Tools Available
- `Read`: Read synthesis and deep dive files
- `mcp__exa__web_search_exa`: Search for interaction evidence
- `WebFetch`: Extract interaction details from specific sources
- `Write`: Save interaction map to file
## Output
Write to: `{OUTPUT_DIR}/interaction_map.md`
Format:
```markdown
# Interaction Map: {TOPIC}
## [Factor X] × [Factor Y] — [Brief verdict]
| Parameter | Value |
|-----------|-------|
| Mechanism | ... |
| Activation condition | ... |
| How it changes recommendation | ... |
| Evidence grade | ... |
| Key studies | ... |
| Who is affected | ... |
| Practical action | ... |
| Risk of ignoring | ... |
---
[Repeat for each interaction pair]
---
## Matrix: When Standard Recommendations Are Insufficient
| Profile | Which interactions to check | What changes |
|---------|---------------------------|--------------|
| [Profile type] | [Interaction pairs] | [Modified recommendations] |
```
## Rules
- **Output language:** Write files, headings, descriptions, conclusions, and comments in `{REPORT_LANGUAGE}`. Keep proper names and technical terms in their original language when useful.
- Only interactions with evidence ≥ C (not theoretical speculation)
- For each interaction — specify WHEN the base recommendation changes (this is the main value)
- Priority: interactions that FLIP a recommendation (from "not needed" → "do it" or vice versa)
- Rank by impact: first those affecting >10% of population
- **MUST write output file before finishing**
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 |