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.
Accessibility Principle: Make dense analysis easier to grasp. When a finding is abstract, architectural, process-heavy, or strategically subtle, ground it in a concrete example, mini-case, counterexample, implementation scenario, or failure mode. Prefer real source-grounded cases; if you use an illustrative hypothetical, label it clearly as hypothetical and do not cite it as if it were sourced fact.
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.
Default readability rule: For Standard mode and above, try to include at least one concrete case/example for each major finding unless the topic is purely numeric, the source material provides no credible case material, or confidentiality/safety considerations make cases inappropriate.
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, each grounded in concrete examples/cases when helpful)
- 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
- Use concrete examples, mini-cases, counterexamples, or applied scenarios to make major findings easier to understand
- Source-ground real cases when available; clearly label hypothetical illustrative examples instead of citing them as factual evidence
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, and grounds abstract findings in concrete examples, cases, counterexamples, or mini-scenarios when helpful. 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**Accessibility Principle:** Make dense analysis easier to grasp. When a finding is abstract, architectural, process-heavy, or strategically subtle, ground it in a concrete example, mini-case, counterexample, implementation scenario, or failure mode. Prefer real source-grounded cases; if you use an illustrative hypothetical, label it clearly as hypothetical and do not cite it as if it were sourced fact.1516---1718## Decision Tree1920```21Request Analysis22+-- Simple lookup? --> STOP: Use WebSearch23+-- Debugging? --> STOP: Use standard tools24+-- Complex analysis needed? --> CONTINUE2526Mode Selection27+-- Initial exploration --> quick (3 phases, 2-5 min)28+-- Standard research --> standard (6 phases, 5-10 min) [DEFAULT]29+-- Critical decision --> deep (8 phases, 10-20 min)30+-- Comprehensive review --> ultradeep (8+ phases, 20-45 min)31```3233**Default assumptions:** Technical query = technical audience. Comparison = balanced perspective. Trend = recent 1-2 years.3435**Default readability rule:** For Standard mode and above, try to include at least one concrete case/example for each major finding unless the topic is purely numeric, the source material provides no credible case material, or confidentiality/safety considerations make cases inappropriate.3637---3839## Workflow Overview4041| Phase | Name | Quick | Standard | Deep | UltraDeep |42|-------|------|-------|----------|------|-----------|43| 1 | SCOPE | Y | Y | Y | Y |44| 2 | PLAN | - | Y | Y | Y |45| 3 | RETRIEVE | Y | Y | Y | Y |46| 4 | TRIANGULATE | - | Y | Y | Y |47| 4.5 | OUTLINE REFINEMENT | - | Y | Y | Y |48| 5 | SYNTHESIZE | - | Y | Y | Y |49| 6 | CRITIQUE | - | - | Y | Y |50| 7 | REFINE | - | - | Y | Y |51| 8 | PACKAGE | Y | Y | Y | Y |5253---5455## Execution5657**On invocation, load relevant reference files:**58591. **Phase 1-7:** Load [methodology.md](./reference/methodology.md) for detailed phase instructions602. **Phase 8 (Report):** Load [report-assembly.md](./reference/report-assembly.md) for progressive generation613. **HTML/PDF output:** Load [html-generation.md](./reference/html-generation.md)624. **Quality checks:** Load [quality-gates.md](./reference/quality-gates.md)635. **Long reports (>18K words):** Load [continuation.md](./reference/continuation.md)6465**Templates:**66- Report structure: [report_template.md](./templates/report_template.md)67- HTML styling: [mckinsey_report_template.html](./templates/mckinsey_report_template.html)6869**Scripts:**70- `python scripts/validate_report.py --report [path]`71- `python scripts/verify_citations.py --report [path]`72- `python scripts/md_to_html.py [markdown_path]`7374---7576## Output Contract7778**Required sections:**79- Executive Summary (200-400 words)80- Introduction (scope, methodology, assumptions)81- Main Analysis (4-8 findings, 600-2,000 words each, cited, each grounded in concrete examples/cases when helpful)82- Synthesis & Insights (patterns, implications)83- Limitations & Caveats84- Recommendations85- Bibliography (COMPLETE - every citation, no placeholders)86- Methodology Appendix8788**Output files (all to `~/Documents/[Topic]_Research_[YYYYMMDD]/`):**89- Markdown (primary source)90- HTML (McKinsey style, auto-opened)91- PDF (professional print, auto-opened)9293**Quality standards:**94- 10+ sources, 3+ per major claim95- All claims cited immediately [N]96- No placeholders, no fabricated citations97- Prose-first (>=80%), bullets sparingly98- Use concrete examples, mini-cases, counterexamples, or applied scenarios to make major findings easier to understand99- Source-ground real cases when available; clearly label hypothetical illustrative examples instead of citing them as factual evidence100101---102103## When to Use / NOT Use104105**Use:** Comprehensive analysis, technology comparisons, state-of-the-art reviews, multi-perspective investigation, market analysis.106107**Do NOT use:** Simple lookups, debugging, 1-2 search answers, quick time-sensitive queries.
undertone0809