🇯🇵日本語
FinViz Screener
Overview
Translate natural-language stock screening requests into FinViz screener filter codes, build the URL, and open it in Chrome. No API key required for public screener; FINVIZ Elite is auto-detected from $FINVIZ_API_KEY for enhanced functionality.
Key Features:
- Natural language → filter code mapping (Japanese + English)
- URL construction with view type and sort order selection
- Elite/Public auto-detection (environment variable or explicit flag)
- Chrome-first browser opening with OS-appropriate fallbacks
- Strict filter validation to prevent URL injection
When to Use This Skill
Explicit Triggers:
- "高配当で成長している小型株を探したい"
- "Find oversold large caps near 52-week lows"
- "テクノロジーセクターの割安株をスクリーニングしたい"
- "Screen for stocks with insider buying"
- "FinVizでブレイクアウト候補を表示して"
- "Show me high-growth small caps on FinViz"
- "配当利回り5%以上でROE15%以上の銘柄を探して"
Implicit Triggers:
- User describes stock screening criteria using fundamental or technical terms
- User mentions FinViz screener or stock filtering
- User asks to find stocks matching specific financial characteristics
When NOT to Use:
- Deep fundamental analysis of a specific stock (use us-stock-analysis)
- Portfolio review with holdings (use portfolio-manager)
- Chart pattern analysis on images (use technical-analyst)
- Earnings-based screening (use earnings-trade-analyzer or pead-screener)
Workflow
Step 1: Load Filter Reference
Read the filter knowledge base:
cat references/finviz_screener_filters.md
Step 2: Interpret User Request
Map the user's natural-language request to FinViz filter codes. Use the Common Concept Mapping table below for quick translation, and reference the full filter list for precise code selection.
Note: For range criteria (e.g., "dividend 3-8%", "P/E between 10 and 20"), use the {from}to{to} range syntax as a single filter token (e.g., fa_div_3to8, fa_pe_10to20) instead of combining separate _o and _u filters.
Common Concept Mapping:
| User Concept (EN) | User Concept (JP) | Filter Codes |
|---|
| High dividend | 高配当 | fa_div_o3 or fa_div_o5 |
| Small cap | 小型株 | cap_small |
| Mid cap | 中型株 | cap_mid |
| Large cap | 大型株 | cap_large |
| Mega cap | 超大型株 | cap_mega |
Step 3: Present Filter Selection
Before executing, present the selected filters in a table for user confirmation:
| Type | Value | Meaning |
|---|---|---|
| Theme | artificialintelligence | Artificial Intelligence |
| Sub-theme | aicloud | AI - Cloud & Infrastructure |
| Filter | cap_small | Small Cap ($300M–$2B) |
| Filter | fa_div_o3 | Dividend Yield > 3% |
| Filter | fa_pe_u20 | P/E < 20 |
| Filter | geo_usa | USA |
View: Overview (v=111)
Mode: Public / Elite (auto-detected)
Ask the user to confirm or adjust before proceeding.
Step 4: Execute Script
Run the screener script to build the URL and open Chrome:
python3 scripts/open_finviz_screener.py \
--filters "cap_small,fa_div_o3,fa_pe_u20,geo_usa" \
--view overview
# Theme-only screening (no --filters required)
python3 scripts/open_finviz_screener.py \
--themes "artificialintelligence,cybersecurity" \
--url-only
# Theme + sub-theme + filters combined
python3 scripts/open_finviz_screener.py \
--themes "artificialintelligence" \
--subthemes "aicloud,aicompute" \
--filters "cap_midover" \
--url-only
Script arguments:
--filters (optional): Comma-separated filter codes. Note: theme_* and subtheme_* tokens are not allowed here — use --themes / --subthemes instead.--themes (optional): Comma-separated theme slugs (e.g., artificialintelligence,cybersecurity). Accepts bare slugs or theme_-prefixed values.--subthemes (optional): Comma-separated sub-theme slugs (e.g., aicloud,aicompute). Accepts bare slugs or -prefixed values.
At least one of --filters, --themes, or --subthemes must be provided.
Step 5: Report Results
After opening the screener, report:
- The constructed URL
- Elite or Public mode used
- Summary of applied filters
- Suggested next steps (e.g., "Sort by dividend yield", "Switch to Financial view for detailed ratios")
Usage Recipes
Real-world screening patterns distilled from repeated use. Each recipe includes a starter filter set, recommended view, and tips for iterative refinement.
Recipe 1: High-Dividend Growth Stocks (Kanchi-Style)
Goal: High yield + dividend growth + earnings growth, excluding yield traps.
--filters "fa_div_3to8,fa_sales5years_pos,fa_eps5years_pos,fa_divgrowth_5ypos,fa_payoutratio_u60,geo_usa"
--view financial
| Filter Code | Purpose |
|---|
fa_div_3to8 | Yield 3-8% (caps high-yield traps) |
fa_sales5years_pos | Positive 5Y revenue growth |
fa_eps5years_pos | Positive 5Y EPS growth |
fa_divgrowth_5ypos | Positive 5Y dividend growth |
fa_payoutratio_u60 | Payout ratio < 60% (sustainability) |
geo_usa | US-listed stocks |
Iterative refinement: Start broad with fa_div_o3 → review results → add fa_div_3to8 to cap yield → add fa_payoutratio_u60 to exclude traps → switch to financial view for payout and growth columns.
Recipe 2: Minervini Trend Template + VCP
Goal: Stocks in a Stage 2 uptrend with volatility contraction (VCP setup).
--filters "ta_sma50_pa,ta_sma200_pa,ta_sma200_sb50,ta_highlow52w_0to25-bhx,ta_perf_26wup,sh_avgvol_o300,cap_midover"
--view technical
| Filter Code | Purpose |
|---|
ta_sma50_pa | Price above 50-day SMA |
ta_sma200_pa | Price above 200-day SMA |
ta_sma200_sb50 | 200 SMA below 50 SMA (uptrend) |
ta_highlow52w_0to25-bhx | Within 25% of 52W high |
ta_perf_26wup | Positive 26-week performance |
sh_avgvol_o300 | Avg volume > 300K |
VCP tightening filters (add to narrow): ta_volatility_wo3,ta_highlow20d_b0to5h,sh_relvol_u1 — low weekly volatility, near 20-day high, below-average relative volume (contraction signal).
Recipe 3: Unfairly Sold-Off Growth Stocks
Goal: Fundamentally strong companies with recent sharp declines — potential mean reversion candidates.
--filters "fa_sales5years_o5,fa_eps5years_o10,fa_roe_o15,fa_salesqoq_pos,fa_epsqoq_pos,ta_perf_13wdown,ta_highlow52w_10to30-bhx,cap_large,sh_avgvol_o200"
--view overview
| Filter Code | Purpose |
|---|
fa_sales5years_o5 | 5Y sales growth > 5% |
fa_eps5years_o10 | 5Y EPS growth > 10% |
fa_roe_o15 | ROE > 15% |
fa_salesqoq_pos | Positive QoQ sales growth |
fa_epsqoq_pos | Positive QoQ EPS growth |
ta_perf_13wdown | Negative 13-week performance |
After review: Switch to valuation view to check P/E and P/S for entry attractiveness.
Recipe 4: Turnaround Stocks
Goal: Companies with previously declining earnings now showing recovery — bottom-fishing with fundamental confirmation.
--filters "fa_eps5years_neg,fa_epsqoq_pos,fa_salesqoq_pos,ta_highlow52w_b30h,ta_perf_13wup,cap_smallover,sh_avgvol_o200"
--view performance
| Filter Code | Purpose |
|---|
fa_eps5years_neg | Negative 5Y EPS growth (prior decline) |
fa_epsqoq_pos | Positive QoQ EPS growth (recovery) |
fa_salesqoq_pos | Positive QoQ sales growth (recovery) |
ta_highlow52w_b30h | Within 30% of 52W high (not at bottom) |
ta_perf_13wup | Positive 13-week performance |
cap_smallover |
Recipe 5: Momentum Trade Candidates
Goal: Short-term momentum leaders near 52W highs with increasing volume.
--filters "ta_sma50_pa,ta_sma200_pa,ta_highlow52w_b0to3h,ta_perf_4wup,sh_relvol_o1.5,sh_avgvol_o1000,cap_midover"
--view technical
| Filter Code | Purpose |
|---|
ta_sma50_pa | Price above 50-day SMA |
ta_sma200_pa | Price above 200-day SMA |
ta_highlow52w_b0to3h | Within 3% of 52W high |
ta_perf_4wup | Positive 4-week performance |
sh_relvol_o1.5 | Relative volume > 1.5x |
sh_avgvol_o1000 | Avg volume > 1M |
Recipe 6: Theme Screening (AI + Sub-theme Drill-Down)
Goal: Find mid-cap+ AI stocks focused on cloud infrastructure and compute acceleration.
--themes "artificialintelligence"
--subthemes "aicloud,aicompute"
--filters "cap_midover"
--view overview
| Type | Value | Purpose |
|---|
| Theme | artificialintelligence | AI theme universe |
| Sub-theme | aicloud | Cloud & Infrastructure vertical |
| Sub-theme | aicompute | Compute & Acceleration vertical |
| Filter | cap_midover | Mid cap and above |
Multi-theme example: --themes "artificialintelligence,cybersecurity" selects stocks tagged with either theme (OR logic via | grouping).
Tips: Iterative Refinement Pattern
Screening works best as a dialogue, not a one-shot query:
- Start broad — use 3-4 core filters to get an initial result set
- Review count — if too many results (>100), add tightening filters; if too few (<5), relax constraints
- Switch views — start with
overview for a quick scan, then switch to financial or valuation for deeper inspection
- Layer in technicals — after confirming fundamental quality, add
ta_ filters to time entries
- Save and iterate — bookmark the URL, then adjust one filter at a time to understand its impact
Resources
references/finviz_screener_filters.md — Complete filter code reference with natural language keywords (includes industry code examples; full 142-code list is in the Industry Codes section)scripts/open_finviz_screener.py — URL builder and Chrome opener
Weekly Installs
103
Repository
tradermonty/cla…g-skills
GitHub Stars
412
First Seen
Feb 27, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
cursor98
gemini-cli97
github-copilot97
amp97
cline97
codex97
