corporate-network-analysis
Skill3 starsChanged 7 months agoMITView on GitHub
Systematic framework for analyzing corporate networks to generate investment alpha. Use when analyzing supplier-customer relationships, director interlocks, executive networks, insider holdings patterns, or identifying M&A signals through board connections. Triggers on supply chain analysis, customer momentum, board interlock, director network, connected party analysis, relationship mapping, or network-based investment research.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- HHFinAi/claude-equity-research-skillsedited, first seen Apr 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- HHFinAi/claude-equity-research-skills★ 1099% 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 repository15 other files it gives its agents.
- analyzing-financial-statementsSkill
- competitive-analysisSkill
- complex-logic-visualizerSkill
- creating-financial-modelsSkill
- dcf-valuationSkill
- earnings-analysisSkill
- financial-analysisSkill
- growth-stock-analysisSkill
- ib-excel-professionalSkill
- ib-infographicSkill
- ib-report-formattingSkill
- investment-report-readerSkill
- semi-dcf-modelerSkill
- supply-chain-pass-throughSkill
- thematic-investment-researchSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Supply Chain Momentum: When a customer gets a big order, upstream suppliers benefit with a lag (40% of shock diffuses over subsequent …
- Distinctive: line 33
Use free data sources in this priority order:
- Distinctive: line 79
Before acting on network signals, verify:
- Distinctive: line 91
All public SEC filings (10-K, DEF 14A, Form 4, 13D, 13F)
- Distinctive: line 103
When completing analysis, produce:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Corporate Network Analysis
This is an institutional-quality research and investment skill.
Exploit slow information diffusion through supply chain relationships and director interlocks to identify predictable stock returns. Academic research shows customer momentum yields ~150bps monthly alpha; board centrality generates ~4.68% annual risk-adjusted returns.
Core Investment Theses
- Supply Chain Momentum: When a customer gets a big order, upstream suppliers benefit with a lag (40% of shock diffuses over subsequent months)
- Director Interlock Signals: Shared board members facilitate information flow, M&A activity, and strategic alignment
- Cross-Holding Synergies: Executives/directors with positions in multiple companies may orchestrate beneficial strategic moves
Workflow
Phase 1: Identify Target Company Networks
1. Map supplier-customer relationships (>5% revenue materiality)
2. Identify board members and their other directorships
3. Track executive cross-company positions
4. Document insider holdings across connected firmsPhase 2: Data Collection
Use free data sources in this priority order:
| Relationship Type | Primary Source | How to Access |
| Suppliers/Customers | SEC 10-K Item 1/7 | EDGAR full-text search |
| Board Members | DEF 14A Proxy | EDGAR company filings |
| Insider Transactions | Form 3/4/5 | EDGAR insider filings |
| Beneficial Ownership | Schedule 13D/13G | EDGAR ownership filings |
| Institutional Holdings | Form 13F | EDGAR quarterly filings |
See references/sec-data-guide.md for detailed extraction procedures.
Phase 3: Network Construction
Build network graphs connecting companies through:
- Customer-supplier links (weighted by revenue %)
- Shared directors (first-degree: direct; second-degree: shared third board)
- Executive overlaps
- Cross-insider holdings
Calculate centrality metrics:
- Degree: Number of direct connections
- Betweenness: Importance in information flow paths
- Closeness: Speed of information propagation
See references/network-metrics.md for calculation methods.
Phase 4: Signal Generation
Customer Momentum Signal:
1. Calculate weighted 12-month returns of major customers
2. Rank universe by customer momentum
3. Long top quintile, short bottom quintile
4. Optimal: 4th-layer relationships (less crowded)Board Connection Signals:
- New shared director between firms → potential M&A signal
- Director clustered buying across positions → information signal
- High centrality + adverse event → watch for network contagion
See references/signal-generation.md for detailed procedures.
Phase 5: Due Diligence Checklist
Before acting on network signals, verify:
- Relationship confirmed via multiple sources
- Revenue materiality >5%
- Network position shows high centrality
- Relationship stable (duration >2 years)
- Information asymmetry present (limited analyst coverage)
- Sufficient liquidity for execution
- No MNPI exposure risk
Phase 6: Compliance Review
Permissible:
- All public SEC filings (10-K, DEF 14A, Form 4, 13D, 13F)
- Public earnings calls and press releases
- Mosaic theory: combining immaterial public info
Prohibited:
- Material non-public information from any source
- Shadow trading: using MNPI about Company A to trade Company B
See references/compliance-guide.md for legal boundaries.
Output Templates
When completing analysis, produce:
- Network Map: Visual or tabular representation of company relationships
- Signal Summary: Ranked opportunities with confidence scores
- Due Diligence Notes: Verification status for each relationship
- Risk Factors: Data quality issues, concentration risks, compliance flags
Key Academic References
- Cohen & Frazzini (2008): Customer-supplier momentum, 1.37-1.55% monthly alpha
- Ali & Hirshleifer (2020): Shared analyst coverage unifies spillover effects
- Larcker, So & Wang (2013): Board centrality predicts returns
- Cai & Sevilir (2012): Board connections in M&A transactions
See references/academic-papers.md for full bibliography.
Data Quality Considerations
- SEC disclosures only capture >10% revenue customers
- Companies may strategically withhold customer names
- Board data has survivorship bias (failed firms disappear)
- Post-publication alpha decay affects well-known signals
- Multi-source verification essential for high-confidence signals
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.

