Skills › Financial Services › idea-generation
idea-generation
The facts
Its description
Systematic stock screening and investment idea sourcing. Combines quantitative screens, thematic research, and pattern recognition to surface new long and short ideas. Use when looking for new ideas, running screens, or conducting thematic sweeps. Triggers on "idea generation", "stock screen", "find ideas", "what looks interesting", "screen for", "new ideas", or "pitch me something".
The description the agent reads to decide when to use it.
From its settingsline 3
When it starts
The agent sees only the name and description, which say this skill does systematic stock screening and idea sourcing by combining quantitative screens, thematic research, and pattern recognition. A person asking for new long or short ideas, a screen, or a thematic sweep would make the agent pick it.
Things a person might say (the model's guesses)
- “What looks interesting in small-cap value right now?”
- “Run a screen for high-growth SaaS names with strong net retention”
- “Pitch me a short idea in retail — something the market is missing”
A model's summary of when it is used.
A model's reading
Stops for a person
1 line stops to ask a person
Lines that stop and wait for a person before going on. Found by matching words, so treat them as pointers.
Found by matching wordsline 12
What leads to it
- market-researcher calls this market-researcher, line 25
Other skills that hand off to this one, call it, require it or offer it instead, as a model read them.
A model's reading
Licence
Apache-2.0, from LICENSE
The terms its author shares it under, which let it be shown here.
From the repositorylicence text
The text
Most marks come from matching words in the file, so treat them as pointers.
1---
2name: idea-generation
3description: Systematic stock screening and investment idea sourcing. Combines quantitative screens, thematic research, and pattern recognition to surface new long and short ideas. Use when looking for new ideas, running screens, or conducting thematic sweeps. Triggers on "idea generation", "stock screen", "find ideas", "what looks interesting", "screen for", "new ideas", or "pitch me something".
4---
6# Idea Generation
Idea Generation
Raw lines 1 to 7Workflow
Raw lines 8 to 910### Step 1: Define Search Criteria
12Ask the user for parameters:
13- **Direction**: Long ideas, short ideas, or both
14- **Market cap**: Large, mid, small, micro
15- **Sector**: Specific sector or cross-sector
16- **Style**: Value, growth, quality, special situation, event-driven
17- **Geography**: US, international, global
18- **Theme**: Any specific thematic angle (AI, reshoring, aging demographics, etc.)
Step 1: Define Search Criteria
Ask the user for parameters:
- Direction: Long ideas, short ideas, or both
- Market cap: Large, mid, small, micro
- Sector: Specific sector or cross-sector
- Style: Value, growth, quality, special situation, event-driven
- Geography: US, international, global
- Theme: Any specific thematic angle (AI, reshoring, aging demographics, etc.)
Involves a person Ask the user :12
20### Step 2: Quantitative Screens
22Run screens based on the style:
24**Value Screen**
25- P/E below sector median
26- EV/EBITDA below historical average
27- Free cash flow yield >5%
28- Price/book below 1.5x
29- Insider buying in last 90 days
30- Dividend yield above market average
32**Growth Screen**
33- Revenue growth >15% YoY
34- Earnings growth >20% YoY
35- Revenue acceleration (growth rate increasing)
36- Expanding margins
37- High return on invested capital (>15%)
38- Strong net retention (>110% for SaaS)
40**Quality Screen**
41- Consistent revenue growth (5+ years)
42- Stable or expanding margins
43- ROE >15%
44- Low debt/equity
45- High free cash flow conversion
46- Insider ownership >5%
48**Short Screen**
49- Declining revenue or decelerating growth
50- Margin compression
51- Rising receivables / inventory vs. sales
52- Insider selling
53- Valuation premium to peers without justification
54- High short interest with deteriorating fundamentals
55- Accounting red flags (auditor changes, restatements)
57**Special Situation Screen**
58- Recent IPOs / SPACs with lockup expirations
59- Spin-offs in last 12 months
60- Companies emerging from restructuring
61- Activist involvement
62- Management changes at underperforming companies
Step 2: Quantitative Screens
Run screens based on the style:
Value Screen
- P/E below sector median
- EV/EBITDA below historical average
- Free cash flow yield >5%
- Price/book below 1.5x
- Insider buying in last 90 days
- Dividend yield above market average
Growth Screen
- Revenue growth >15% YoY
- Earnings growth >20% YoY
- Revenue acceleration (growth rate increasing)
- Expanding margins
- High return on invested capital (>15%)
- Strong net retention (>110% for SaaS)
Quality Screen
- Consistent revenue growth (5+ years)
- Stable or expanding margins
- ROE >15%
- Low debt/equity
- High free cash flow conversion
- Insider ownership >5%
Short Screen
- Declining revenue or decelerating growth
- Margin compression
- Rising receivables / inventory vs. sales
- Insider selling
- Valuation premium to peers without justification
- High short interest with deteriorating fundamentals
- Accounting red flags (auditor changes, restatements)
Special Situation Screen
- Recent IPOs / SPACs with lockup expirations
- Spin-offs in last 12 months
- Companies emerging from restructuring
- Activist involvement
- Management changes at underperforming companies
64### Step 3: Thematic Sweep
66For thematic ideas, research the theme and identify beneficiaries:
681. Define the thesis (e.g., "AI infrastructure spending accelerates through 2026")
692. Map the value chain — who benefits directly vs. indirectly?
703. Identify pure-play vs. diversified exposure
714. Assess which names are already "priced in" vs. under-appreciated
725. Look for second-order beneficiaries that the market hasn't connected to the theme
Step 3: Thematic Sweep
For thematic ideas, research the theme and identify beneficiaries:
- Define the thesis (e.g., "AI infrastructure spending accelerates through 2026")
- Map the value chain — who benefits directly vs. indirectly?
- Identify pure-play vs. diversified exposure
- Assess which names are already "priced in" vs. under-appreciated
- Look for second-order beneficiaries that the market hasn't connected to the theme
74### Step 4: Idea Presentation
76For each idea that passes the screen, present:
78**[Company Name] — [Long/Short] — [One-Line Thesis]**
80| Metric | Value | vs. Peers |
81|--------|-------|-----------|
82| Market cap | | |
83| EV/EBITDA (NTM) | | |
84| P/E (NTM) | | |
85| Revenue growth | | |
86| EBITDA margin | | |
87| FCF yield | | |
89**Thesis (3-5 bullets):**
90- Why this is mispriced
91- What the market is missing
92- Catalyst to realize value
94**Key Risks:**
95- What would make this wrong
97**Suggested Next Steps:**
98- Build full model? Deep-dive diligence? Expert call?
Step 4: Idea Presentation
For each idea that passes the screen, present:
[Company Name] — [Long/Short] — [One-Line Thesis]
| Metric | Value | vs. Peers |
|---|---|---|
| Market cap | ||
| EV/EBITDA (NTM) | ||
| P/E (NTM) | ||
| Revenue growth | ||
| EBITDA margin | ||
| FCF yield |
Thesis (3-5 bullets):
- Why this is mispriced
- What the market is missing
- Catalyst to realize value
Key Risks:
- What would make this wrong
Suggested Next Steps:
- Build full model? Deep-dive diligence? Expert call?
100### Step 5: Output
102- Shortlist of 5-10 ideas with one-page summaries
103- Screening criteria and methodology documented
104- Comparison table across all ideas
105- Prioritized list: which ideas to research first
Step 5: Output
- Shortlist of 5-10 ideas with one-page summaries
- Screening criteria and methodology documented
- Comparison table across all ideas
- Prioritized list: which ideas to research first
107## Important Notes
109- Screens surface candidates, not conclusions — every screen output needs fundamental work
110- The best ideas often come from intersections (e.g., quality company at value price due to temporary headwind)
111- Avoid crowded trades — check ownership data, short interest, and how many analysts cover the name
112- Contrarian ideas need a catalyst — being early without a catalyst is the same as being wrong
113- Track idea hit rates over time — which screens and approaches produce the best ideas?
114- Short ideas need higher conviction — timing is harder and risk is asymmetric
Important Notes
- Screens surface candidates, not conclusions — every screen output needs fundamental work
- The best ideas often come from intersections (e.g., quality company at value price due to temporary headwind)
- Avoid crowded trades — check ownership data, short interest, and how many analysts cover the name
- Contrarian ideas need a catalyst — being early without a catalyst is the same as being wrong
- Track idea hit rates over time — which screens and approaches produce the best ideas?
- Short ideas need higher conviction — timing is harder and risk is asymmetric
From anthropics/financial-services at 6056506, 2026-10-28. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.