Deep Research
Core Purpose
Deliver citation-backed, verified research reports through a structured pipeline with source credibility scoring, evidence persistence, and progressive context management.
Autonomy Principle: Operate independently. Infer assumptions from context. Only stop for critical errors or incomprehensible queries.
Decision Tree
Request Analysis
+-- Simple lookup? --> STOP: Use WebSearch
+-- Debugging? --> STOP: Use standard tools
+-- Complex analysis needed? --> CONTINUE
Mode Selection
+-- Initial exploration --> quick (3 phases, 2-5 min)
+-- Standard research --> standard (6 phases, 5-10 min) [DEFAULT]
+-- Critical decision --> deep (8 phases, 10-20 min)
+-- Comprehensive review --> ultradeep (8+ phases, 20-45 min)
Default assumptions: Technical query = technical audience. Comparison = balanced perspective. Trend = recent 1-2 years.
Workflow Overview
| Phase |
Name |
Quick |
Standard |
Deep |
UltraDeep |
| 1 |
SCOPE |
Y |
Y |
Y |
Y |
| 2 |
PLAN |
- |
Y |
Y |
Y |
| 3 |
RETRIEVE |
Y |
Y |
Y |
Y |
| 4 |
TRIANGULATE |
- |
Y |
Y |
Y |
| 4.5 |
OUTLINE REFINEMENT |
- |
Y |
Y |
Y |
| 5 |
SYNTHESIZE |
- |
Y |
Y |
Y |
| 6 |
CRITIQUE |
- |
- |
Y |
Y |
| 7 |
REFINE |
- |
- |
Y |
Y |
| 8 |
PACKAGE |
Y |
Y |
Y |
Y |
Execution
On invocation, load relevant reference files:
- Phase 1-7: Load methodology.md for detailed phase instructions
- Phase 8 (Report): Load report-assembly.md for progressive generation
- HTML/PDF output: Load html-generation.md
- Quality checks: Load quality-gates.md
- Long reports (>18K words): Load continuation.md
Templates:
Scripts:
python scripts/validate_report.py --report [path]python scripts/verify_citations.py --report [path]python scripts/md_to_html.py [markdown_path]
Output Contract
Required sections:
- Executive Summary (200-400 words)
- Introduction (scope, methodology, assumptions)
- Main Analysis (4-8 findings, 600-2,000 words each, cited)
- Synthesis & Insights (patterns, implications)
- Limitations & Caveats
- Recommendations
- Bibliography (COMPLETE - every citation, no placeholders)
- Methodology Appendix
Output files (all to ~/Documents/[Topic]_Research_[YYYYMMDD]/):
- Markdown (primary source)
- HTML (McKinsey style, auto-opened)
- PDF (professional print, auto-opened)
Quality standards:
- 10+ sources, 3+ per major claim
- All claims cited immediately [N]
- No placeholders, no fabricated citations
- Prose-first (>=80%), bullets sparingly
When to Use / NOT Use
Use: Comprehensive analysis, technology comparisons, state-of-the-art reviews, multi-perspective investigation, market analysis.
Do NOT use: Simple lookups, debugging, 1-2 search answers, quick time-sensitive queries.
1---2name: deep-research3description: Conducts enterprise-grade research with multi-source synthesis, citation tracking, and verification. Produces citation-backed reports through a structured pipeline with source credibility scoring. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.4---56# Deep Research78## Core Purpose910Deliver citation-backed, verified research reports through a structured pipeline with source credibility scoring, evidence persistence, and progressive context management.1112**Autonomy Principle:** Operate independently. Infer assumptions from context. Only stop for critical errors or incomprehensible queries.1314---1516## Decision Tree1718```19Request Analysis20+-- Simple lookup? --> STOP: Use WebSearch21+-- Debugging? --> STOP: Use standard tools22+-- Complex analysis needed? --> CONTINUE2324Mode Selection25+-- Initial exploration --> quick (3 phases, 2-5 min)26+-- Standard research --> standard (6 phases, 5-10 min) [DEFAULT]27+-- Critical decision --> deep (8 phases, 10-20 min)28+-- Comprehensive review --> ultradeep (8+ phases, 20-45 min)29```3031**Default assumptions:** Technical query = technical audience. Comparison = balanced perspective. Trend = recent 1-2 years.3233---3435## Workflow Overview3637| Phase | Name | Quick | Standard | Deep | UltraDeep |38|-------|------|-------|----------|------|-----------|39| 1 | SCOPE | Y | Y | Y | Y |40| 2 | PLAN | - | Y | Y | Y |41| 3 | RETRIEVE | Y | Y | Y | Y |42| 4 | TRIANGULATE | - | Y | Y | Y |43| 4.5 | OUTLINE REFINEMENT | - | Y | Y | Y |44| 5 | SYNTHESIZE | - | Y | Y | Y |45| 6 | CRITIQUE | - | - | Y | Y |46| 7 | REFINE | - | - | Y | Y |47| 8 | PACKAGE | Y | Y | Y | Y |4849---5051## Execution5253**On invocation, load relevant reference files:**54551. **Phase 1-7:** Load [methodology.md](./reference/methodology.md) for detailed phase instructions562. **Phase 8 (Report):** Load [report-assembly.md](./reference/report-assembly.md) for progressive generation573. **HTML/PDF output:** Load [html-generation.md](./reference/html-generation.md)584. **Quality checks:** Load [quality-gates.md](./reference/quality-gates.md)595. **Long reports (>18K words):** Load [continuation.md](./reference/continuation.md)6061**Templates:**62- Report structure: [report_template.md](./templates/report_template.md)63- HTML styling: [mckinsey_report_template.html](./templates/mckinsey_report_template.html)6465**Scripts:**66- `python scripts/validate_report.py --report [path]`67- `python scripts/verify_citations.py --report [path]`68- `python scripts/md_to_html.py [markdown_path]`6970---7172## Output Contract7374**Required sections:**75- Executive Summary (200-400 words)76- Introduction (scope, methodology, assumptions)77- Main Analysis (4-8 findings, 600-2,000 words each, cited)78- Synthesis & Insights (patterns, implications)79- Limitations & Caveats80- Recommendations81- Bibliography (COMPLETE - every citation, no placeholders)82- Methodology Appendix8384**Output files (all to `~/Documents/[Topic]_Research_[YYYYMMDD]/`):**85- Markdown (primary source)86- HTML (McKinsey style, auto-opened)87- PDF (professional print, auto-opened)8889**Quality standards:**90- 10+ sources, 3+ per major claim91- All claims cited immediately [N]92- No placeholders, no fabricated citations93- Prose-first (>=80%), bullets sparingly9495---9697## When to Use / NOT Use9899**Use:** Comprehensive analysis, technology comparisons, state-of-the-art reviews, multi-perspective investigation, market analysis.100101**Do NOT use:** Simple lookups, debugging, 1-2 search answers, quick time-sensitive queries.
jordangaston