LLM Research Skill
Quick Start
Run research from 3 models in parallel:
bash
python3 scripts/llm_research.py "Your research question here"
Or with a spec file:
bash
python3 scripts/llm_research.py --spec /path/to/research-spec.json
Workflow
- •Prepare prompt: Write a clear research question with expected output format
- •Run script: Launch all 3 models in parallel
- •Wait: Codex (xhigh reasoning) takes 2-5 minutes, others are faster
- •Collect: Results saved to
./llm-research/runs/<timestamp>/ - •Synthesize: Optionally combine insights into a summary
Output Structure
code
llm-research/runs/YYYYMMDD-topic/ ├── research-codex.md # Codex (gpt-5.2-codex, xhigh reasoning) ├── research-claude.md # Claude Opus ├── research-gemini.md # Gemini Pro Preview └── synthesis.md # Combined insights (optional)
Spec File Format
json
{
"topic": "Game Design Review",
"prompt": "Analyze the game mechanics and provide...",
"context_files": ["docs/design/GAME_DESIGN.md"],
"output_format": "## 1. Section\n## 2. Section\n...",
"synthesize": true
}
CLI Options
- •
--spec FILE- Use spec file instead of inline prompt - •
--output-dir DIR- Custom output directory - •
--no-codex- Skip Codex (faster, 2 models only) - •
--no-synthesis- Don't generate combined summary - •
--timeout MINUTES- Max wait time (default: 10)
Model Configuration
Uses ~/.config/llm-council/agents.json for model settings:
json
{
"planners": [
{ "name": "codex-1", "kind": "codex", "model": "gpt-5.2-codex", "reasoning_effort": "xhigh" },
{ "name": "claude-2", "kind": "claude", "model": "opus" },
{ "name": "gemini-3", "kind": "gemini", "model": "gemini-3-pro-preview" }
]
}
Example: Game Design Review
bash
cat > /tmp/review-spec.json << 'EOF'
{
"topic": "Investomania Cards Review",
"prompt": "You are an expert card game designer. Read docs/design/GAME_DESIGN.md and provide a structured review in Russian...",
"context_files": ["docs/design/GAME_DESIGN.md"],
"output_format": "## 1. Общая оценка\n## 2. Анализ механик\n## 3. Проблемы\n## 4. Улучшения\n## 5. Сравнение\n## 6. Плейтесты",
"synthesize": true
}
EOF
python3 scripts/llm_research.py --spec /tmp/review-spec.json
Key Differences from LLM Council
| Aspect | LLM Council | LLM Research |
|---|---|---|
| Output | Plans (how to do) | Answers (done) |
| Judge | Yes (scores plans) | Optional synthesis |
| Use case | Implementation planning | Analysis, reviews |
| Time | 5-30 min | 2-10 min |
Best Practices
- •Be specific: Give concrete output format, not vague instructions
- •Include context: Reference files the models should read
- •Set expectations: "Give numbers", "Be critical", "Minimum 5 points"
- •Russian output: Explicitly state language in prompt
Constraints
- •Models run independently (no shared context)
- •Codex with xhigh reasoning is slowest but most thorough
- •Total token budget ~50k per model
- •Don't expect identical outputs — diversity is the point