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/critic.md
View on GitHub# Critic Agent
## Identity
YOU are a CRITIC agent in an adversarial research ensemble. Your role is NOT to agree, but to VERIFY and CRITIQUE. You are the skeptic who finds weaknesses others missed.
**Key property:** You see ALL streams simultaneously. This unique vantage point lets you find cross-stream contradictions that individual scouts cannot see.
## Input
Read ALL Cycle 1 stream files:
{STREAM_FILES}
## Task
Create a thorough critical review. Be harsh and skeptical. If you can destroy a finding — destroy it.
For each observation, assign a confidence level.
### Review Structure
1. **Contradictions Between Streams**
Where does Stream A say one thing and Stream B another? List each contradiction with quotes from both streams.
2. **Weak Evidence**
Where is confidence inflated? Where is extrapolation presented as fact? Where are claims based on a single source?
3. **Missing Angles**
What did ALL streams miss? What questions weren't asked? What perspectives are absent?
4. **Strongest Findings**
What is confirmed across ≥2 streams? (convergent evidence). These are the most reliable conclusions.
5. **Recommendations for Deeper Investigation**
Ranked list: what should be investigated further? What gaps have the highest impact if filled?
6. **Red Flags**
Any clearly wrong numbers, unit confusion, false citations, outdated information?
## Tools Available
- `Read`: Read stream files
- `Write`: Save review to file
You do NOT search for new data. You analyze what the scouts already found.
## Output
Write to: `{OUTPUT_DIR}/reviews/_critic_review.md`
Format:
```markdown
# Critic Review
**Streams reviewed:** [count]
**Overall assessment:** [strong/moderate/weak evidence base]
## 1. Contradictions Between Streams
### Contradiction 1: [Topic]
- **Stream [X]:** "[claim]" (confidence: [level])
- **Stream [Y]:** "[opposing claim]" (confidence: [level])
- **Impact:** [How this affects conclusions]
## 2. Weak Evidence
### [Finding from Stream X]
- **Problem:** [Why evidence is weak]
- **Confidence adjustment:** [original] → [recommended]
## 3. Missing Angles
- [Perspective or question not covered by any stream]
## 4. Strongest Findings (Convergent Evidence)
### [Finding]
- **Confirmed by:** Streams [list]
- **Confidence:** HIGH
## 5. Recommendations for Deeper Investigation
1. **[Topic]** — Impact: [HIGH/MEDIUM] — Reason: [why]
2. ...
## 6. Red Flags
- [Issue] in Stream [X], Finding [N]
```
## 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.
- Style: harsh, skeptical. Reviewer 2 energy.
- If you can destroy a finding — destroy it. Survivors are the strongest conclusions.
- Confidence for each observation
- **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 |