thematic-investment-research
Skill10 starsChanged 7 months agoMITView on GitHub
Comprehensive framework for conducting institutional-quality thematic investment research. Use when the user asks to: (1) Identify and validate investment themes, (2) Analyze thematic market opportunities and value chains, (3) Build a thematic stock universe and screen candidates, (4) Conduct company deep dives with thematic focus, (5) Value companies using theme-appropriate methodologies, (6) Assess theme-level and company-level risks, (7) Write thematic research reports, (8) Design portfolio implementation and monitoring frameworks. Triggers on phrases like thematic research, investment theme, secular trend analysis, theme validation, thematic universe, value chain mapping, or requests for structured investment research methodology.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- HHFinAi/Institutional-Growth-Equity-Skillsedited, first seen Apr 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- HHFinAi/Institutional-Growth-Equity-Skills★ 399% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Alternative: Search trends, VC flows, job postings, satellite data
- Distinctive: line 92
Document: current framework, pending legislation, subsidies/incentives, geographic variance, political durability
- Distinctive: line 229
Must be: Specific & measurable, Observable, Pre-committed, Action-triggering
- Distinctive: line 252
All claims sourced or derived from explicit assumptions
- Very specific: line 304
Use checklists in assets/ for standardized execution:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Thematic Investment Research Framework
Overview
Thematic investing identifies structural, long-duration trends reshaping economies and captures value across industries united by common secular drivers. This skill provides an eight-phase methodology from theme identification through portfolio implementation.
Research Workflow
Execute phases sequentially, with gate reviews between major phases:
Phase I: Theme Identification & Validation
Phase II: Structural Analysis (TAM, Value Chain, Competition)
Phase III: Universe Construction & Screening
Phase IV: Company Deep Dives
Phase V: Valuation Architecture
Phase VI: Risk Assessment
Phase VII: Report Construction
Phase VIII: Implementation & MonitoringPhase I: Theme Identification & Validation
Theme Discovery Sources
Monitor systematically:
- Primary: Academic journals, patent databases, regulatory filings, conference proceedings, expert networks
- Secondary: Institutional research, consultancy reports, multilateral publications
- Alternative: Search trends, VC flows, job postings, satellite data
DRIVER Validation Framework
Validate every theme against six criteria before proceeding:
| Criterion | Question |
| Durability | Is this structural (demographics, physics, regulation) or temporary? |
| Relevance | Does it drive revenue growth, margin expansion, or re-rating? |
| Investability | Are there listed equities with genuine, liquid exposure? |
| Verifiability | Can thesis elements be empirically tested with leading indicators? |
| Expansion | Is TAM growing through new use cases or geographies? |
| Rationality | Is opportunity not fully discounted in current valuations? |
Theme Statement Construction
Structure: [DRIVER] is causing [STRUCTURAL CHANGE], benefiting [BENEFICIARIES] over [TIME HORIZON], measured by [KEY METRICS].
Deliverable: Initial Scoping Document (2-3 pages)
- Theme statement and thesis points
- DRIVER validation assessment
- Hype cycle positioning
- Initial value chain sketch
- Key research questions and data sources
- Preliminary risks and thesis killers
Gate Review: Obtain approval before committing to full research.
→ For detailed validation frameworks: See references/theme-validation.md
Phase II: Structural Analysis
Market Sizing
Apply both approaches and triangulate:
Top-Down: Macro data → penetration rates → growth assumptions → industry forecasts Bottom-Up: Customer segments → adoption curves → company validation → reconciliation
Value Chain Mapping
For each layer (Upstream → Midstream → Downstream → Adjacent), analyze:
- Gross margin profile
- Competitive intensity
- Bargaining power
- Scale economics
- Capital intensity
- Technology risk
Competitive Dynamics (Porter's Five Forces)
- Industry rivalry: concentration, differentiation, growth vs. capacity
- New entrants: capital, technology, regulatory barriers
- Supplier power: concentration, substitutes, forward integration threat
- Buyer power: concentration, price sensitivity, alternatives
- Substitutes: alternative technologies, price-performance, switching costs
Regulatory Landscape
Document: current framework, pending legislation, subsidies/incentives, geographic variance, political durability
→ For detailed frameworks: See references/structural-analysis.md
Phase III: Universe Construction
Inclusion Criteria
| Criterion | Pure-Play | Diversified |
| Revenue Exposure | >75% | >10% |
| Strategic Commitment | High | Moderate |
| Growth Attribution | >50% | >30% |
| Daily Volume | >$5M | >$5M |
Exposure Categories
- Pure-Play (>75%): Highest beta, often premium valuation
- Significant (25-75%): Meaningful leverage with diversification
- Enabler (10-25%): Indirect beneficiary, downside protection
- Optionality (<10%): Strategic upside, early-stage exposure
Screening Factors
Quantitative: Market cap, ADV, revenue CAGR, margins, ROIC, leverage, valuation, momentum Qualitative: Management quality, technology leadership, customer quality, IP strength, ESG, governance
Universe Documentation Fields
Company ID | Thematic Classification | Fundamental Snapshot | Thematic Thesis | Research Status | Catalysts & Risks
→ For detailed criteria: See references/universe-construction.md
Phase IV: Company Deep Dives
Selection Criteria (10-20 companies)
- Highest thematic purity
- Attractive fundamental profile
- Strategic value chain importance
- Differentiated insight potential
- Sufficient liquidity
Business Quality Assessment
Competitive Moat: Network effects, switching costs, intangibles, cost advantages, efficient scale Management: Track record, incentive alignment, strategic vision, board composition
Financial Analysis Framework
| Area | Key Metrics |
| Revenue | Segment breakdown, volume/price/mix, recurring %, customer concentration |
| Profitability | Gross margin drivers, operating leverage, R&D intensity, path to profit |
| Cash Flow | OCF conversion, working capital, capex (maintenance vs. growth), FCF margin |
| Balance Sheet | Leverage, liquidity, asset quality, return capacity |
Thematic Leverage Assessment
- Revenue attribution (current % and projected trajectory)
- Strategic positioning and share dynamics
- Technology alignment and disruption risk
- Customer relationship quality
- Execution capability and track record
Financial Model Requirements
- 5+ years historical, 5-10 years forecast
- Bottom-up revenue by segment with theme drivers
- Margin assumptions tied to scale/competition/mix
- Capital requirements: capex, working capital, M&A
Scenario Framework
| Scenario | Theme Assumption | Probability |
| Bull | Accelerates; company gains share | 20-25% |
| Base | Develops as expected; executes to plan | 50-60% |
| Bear | Disappoints/delays; loses position | 20-25% |
| Stress | Theme fails or thesis breaks | 5-10% |
→ For detailed templates: See references/company-analysis.md
Phase V: Valuation Architecture
Methodology Selection
| Method | Best For | Limitations |
| DCF/FCFF | Profitable, visible cash flows | Terminal value sensitivity |
| Reverse DCF | Expectation gap identification | Requires assumed WACC/margins |
| EV/Revenue | High-growth unprofitable | Ignores profitability |
| EV/EBITDA | Profitable comparisons | Capex/D&A differences |
| Sum-of-Parts | Diversified theme exposure | Segment data quality |
| rNPV | Pipeline/binary outcomes | Probability subjectivity |
| LTV/CAC | Subscription models | Requires cohort data |
DCF Construction
Revenue: TAM trajectory → SAM → market share → pricing → cross-check Margins: Material costs (learning curves) → pricing power → mix → target vs. mature peers WACC: Beta (historical vs. implied), size premium, country risk, execution premium Terminal Value: Extended forecast (10+ years), conservative perpetual growth, exit multiple cross-check
Valuation Integration
- Scenario-weighted DCF (probability × value per scenario)
- Comparable multiples on forecast financials
- Sum-of-parts where applicable
- Triangulate to conviction range
- Set target at weighted average or conservative bound
→ For detailed methodologies: See references/valuation-methods.md
Phase VI: Risk Assessment
Theme-Level Risks
| Risk | Description | Monitoring |
| Timing | Longer development than anticipated | Adoption curves, milestones |
| Magnitude | TAM overestimated | Market size revisions, unit economics |
| Displacement | Alternative supersedes thesis | Patents, VC activity, breakthroughs |
| Regulatory | Policy undermines economics | Legislation, political shifts |
| Crowding | Consensus; valuations discount gains | Fund flows, ETF assets, multiples |
Company-Level Risks
- Execution: Management track record, guidance accuracy
- Competitive: Win/loss tracking, customer surveys
- Financial: Cash runway, covenants, capital access
- Key Person: Management depth, succession
- Technology: Patent strength, R&D productivity
- ESG/Reputation: Ratings, controversy tracking
Risk Scoring Matrix
| Low Impact (1) | Medium (2) | High (3) | |
| Low Prob (1) | 1: Monitor | 2: Monitor | 3: Plan |
| Med Prob (2) | 2: Monitor | 4: Plan | 6: Mitigate |
| High Prob (3) | 3: Plan | 6: Mitigate | 9: Critical |
Thesis Killer Definition
Must be: Specific & measurable, Observable, Pre-committed, Action-triggering
Examples:
- Theme: "EV battery costs rise for two consecutive quarters"
- Company: "Market share falls below 15% in core segment"
- Valuation: "Stock trades above 50x forward for 6+ months"
→ For detailed frameworks: See references/risk-assessment.md
Phase VII: Report Construction
Standard Structure
| Section | Length | Content |
| Executive Summary | 1-2 pp | Thesis, findings, recommendations, risks, sizing |
| Theme Deep Dive | 5-10 pp | Drivers, TAM, value chain, competition, regulation |
| Company Profiles | 3-5 pp each | Overview, positioning, financials, valuation, risks |
| Risk Assessment | 2-3 pp | Theme/company risks, thesis killers, mitigants |
| Implementation | 1-2 pp | Portfolio construction, timing, monitoring, exits |
| Appendices | Variable | Models, universe, sources, glossary, disclosures |
Quality Standards
- All claims sourced or derived from explicit assumptions
- Forecasts include sensitivity analysis
- Competing hypotheses acknowledged
- Logic chain explicit: drivers → recommendations
- Executive summary enables standalone decision-making
→ For detailed templates: See references/report-structure.md
Phase VIII: Implementation & Monitoring
Position Sizing
| Conviction | Size | Criteria | Review |
| High | 4-6% | Deep dive complete; multiple valuation support; clear catalysts | Monthly |
| Medium | 2-4% | Fundamental work complete; timing/execution uncertainty | Bi-weekly |
| Speculative | 1-2% | High potential but significant risks; option-like payoff | Weekly |
| Watch List | 0% | Interesting but valuation/thesis not compelling | Quarterly |
Adjust for: volatility, correlation, downside scenario survival, portfolio constraints
Entry Execution
- Timing: Catalyst proximity, technical context, liquidity, market regime
- Staged Entry: Initial (40-50%) → Confirmation (30-40%) → Catalyst (10-30%)
Monitoring Framework
| Level | Indicators | Frequency |
| Theme | Adoption, pricing, competition, policy, sentiment | Monthly-Quarterly |
| Company | Earnings, KPIs, strategy, positioning, valuation | Post-earnings minimum |
Exit Criteria
| Type | Trigger | Action |
| Target Achieved | Price at target; thesis reflected | Trim 50-100% |
| Thesis Broken | Assumption invalidated; killer triggered | Exit 100% |
| Better Opportunity | Superior risk/reward in theme | Rotate |
| Theme Maturation | Consensus; crowding elevated | Reduce systematically |
| Risk Management | Position exceeds limits | Trim to target |
Review Cadence
- Position: After earnings; monthly minimum
- Theme: Quarterly
- Universe Refresh: Semi-annually
- Full Research Update: Annually
→ For detailed frameworks: See references/implementation.md
Quick Reference: Checklists
Use checklists in assets/ for standardized execution:
theme-validation-checklist.md: DRIVER framework validationcompany-deep-dive-checklist.md: Fundamental analysis completionrisk-scoring-template.md: Probability/impact assessment
Research Sources Reference
Data: Bloomberg, FactSet, Capital IQ, Refinitiv, PitchBook Industry: Gartner, IDC, IHS Markit, Wood Mackenzie, IQVIA, BloombergNEF Alternative: Google Trends, SimilarWeb, Glassdoor, Orbital Insight, Thinknum
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

