Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth stock analysis, momentum stock identification, or wants to find stocks with strong earnings and price momentum following O'Neil's investment system.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
This skill screens US stocks using William O'Neil's proven CANSLIM methodology, a systematic approach for identifying growth stocks with strong fundamentals and price momentum. CANSLIM analyzes 7 key components: Current Earnings, Annual Growth, Newness/New Highs, Supply/Demand, Leadership/RS Rank, Institutional Sponsorship, and Market Direction.
Phase 3 implements all 7 of 7 components (C, A, N, S, L, I, M), representing 100% of the full methodology.
Two-Stage Approach:
Key Features:
Read references/scoring_overview.md for the Phase 3.1 component weights, the weighted RS formula and the RS fallback hierarchy.
Future Phases:
Explicit Triggers:
Implicit Triggers:
When NOT to Use:
API Requirements:
site.financialmodelingprep.com/pricing-plans)
export FMP_API_KEY=your_key_herePython Dependencies:
requests (FMP API calls)beautifulsoup4 (Finviz web scraping)lxml (HTML parsing)Installation:
pip install requests beautifulsoup4 lxmlOutput Directory: reports/ (default) or custom via --output-dir
Generated Files:
canslim_screener_YYYY-MM-DD_HHMMSS.json - Structured data for programmatic usecanslim_screener_YYYY-MM-DD_HHMMSS.md - Human-readable reportReport Contents:
Rating Bands:
The L calculator requires positive, finite, non-boolean closes at the exact
full-window and available 3m/6m/12m return endpoints. Missing or invalid consumed
stock or supplied benchmark closes produce data_available: false, an
Unavailable RS rating, and dated data_gaps. The zero score is an internal
placeholder, not measured weak performance. These candidates are excluded from
ranking; JSON metadata and Markdown warn when screening is incomplete. If no
rankable candidates remain and any candidate was excluded for RS price gaps,
the CLI exits with code 1 before writing reports. Unused interior closes do not
change returns, and bars are not dropped or compressed. Absent or insufficient
benchmark history retains the existing absolute-performance fallback and 20%
penalty. --disable-rs retains its explicit neutral L=50 behavior.
Check if user has FMP API key configured:
# Check environment variable
echo $FMP_API_KEY
# If not set, prompt user to provide itRequirements:
requests (FMP API calls)beautifulsoup4 (Finviz web scraping)lxml (HTML parsing)Installation:
pip install requests beautifulsoup4 lxmlIf API key is missing, guide user to:
export FMP_API_KEY=your_key_hereOption A: Default Universe (Recommended) Use top 40 S&P 500 stocks by market cap (predefined in script):
python3 skills/canslim-screener/scripts/screen_canslim.pyOption B: Custom Universe User provides specific symbols or sector:
python3 skills/canslim-screener/scripts/screen_canslim.py \
--universe AAPL MSFT GOOGL AMZN NVDA META TSLAOption C: Sector-Specific User can provide sector-focused list (Technology, Healthcare, etc.)
API Budget Considerations (Phase 3):
--max-candidates 35 for free tier (35 × 7 + 3 = 248 calls), or use a paid FMP plan (see site.financialmodelingprep.com/pricing-plans in a browser) for full 40-stock screeningRun the main screening script with appropriate parameters:
cd skills/canslim-screener/scripts
# Basic run (40 stocks, top 20 in report)
python3 screen_canslim.py --api-key $FMP_API_KEY
# Custom parameters
python3 screen_canslim.py \
--api-key $FMP_API_KEY \
--max-candidates 40 \
--top 20 \
--output-dir ../../../
# Custom RS benchmark (Phase 3.1)
python3 screen_canslim.py --rs-benchmark SPY
# Disable L component (saves per-stock 365-day fetch; L fixed at neutral 50)
python3 screen_canslim.py --disable-rsScript Workflow (Phase 3 - Full CANSLIM):
Expected Execution Time (Phase 3):
Finviz Fallback Behavior:
sharesOutstanding unavailable✅ Using Finviz institutional ownership for NVDA: 68.3%The script generates two output files:
canslim_screener_YYYY-MM-DD_HHMMSS.json - Structured datacanslim_screener_YYYY-MM-DD_HHMMSS.md - Human-readable reportRead the Markdown report to identify top candidates:
# Find the latest report
ls -lt canslim_screener_*.md | head -1
# Read the report
cat canslim_screener_YYYY-MM-DD_HHMMSS.mdReport Structure (Phase 3 - Full CANSLIM):
Component Details in Report:
A new Summary Table appears above the candidate list in Phase 3.1 reports, showing rank, symbol, composite score, rating, RS rating, and RS percentile for quick scanning.
Review the top-ranked stocks and cross-reference with knowledge bases:
Reference Documents to Consult:
references/interpretation_guide.md - Understand rating bands and portfolio sizingreferences/canslim_methodology.md - Deep dive into component meanings (now includes S and I)references/scoring_system.md - Understand scoring formulas (Phase 3 weights)Analysis Framework:
For Exceptional+ stocks (90-100 points):
For Exceptional stocks (80-89 points):
For Strong stocks (70-79 points):
For Above Average stocks (60-69 points):
Bear Market Override:
Create a concise, actionable summary for the user:
Report Format: Read references/report_template.md for the user-facing report template.
scripts/)Read references/script_inventory.md for what each script, calculator and supporting module does.
references/)Knowledge Bases:
references/canslim_methodology.md (27KB) - Complete CANSLIM explanation
references/scoring_system.md (21KB) - Technical scoring specification (Phase 3)
references/fmp_api_endpoints.md (18KB) - API integration guide (Phase 3)
references/interpretation_guide.md (18KB) - User guidance
How to Use References:
references/canslim_methodology.md first to understand O'Neil's system (now includes S and I)references/interpretation_guide.md when analyzing resultsreferences/scoring_system.md if scores seem unexpectedreferences/fmp_api_endpoints.md for API troubleshooting or Finviz fallback issuesRead references/troubleshooting.md when a run fails or returns unexpected results. It covers rate limits, missing libraries, slow or failing Finviz fallback, no stocks meeting thresholds and data quality warnings.
Read references/implementation_notes.md for Phase 3 implementation status, Finviz integration benefits, planned Phase 4 and data source attribution.
This screener is for educational and informational purposes only.
Version: Phase 3.1 (multi-period RS)
Last Updated: 2026-05-03
API Requirements: FMP API (free tier: up to 35 stocks; a paid plan recommended for 40 stocks) + BeautifulSoup/requests/lxml for Finviz
Execution Time: ~2 minutes for 40 stocks
Output Formats: JSON + Markdown (now includes Summary Table and schema_version: "3.1")
Components Implemented: C, A, N, S, L, I, M (7 of 7, 100% coverage)
Phase 3.1 additions: multi-period RS (3m/6m/12m), --rs-benchmark, --disable-rs,
new RS fields (rs_rating, rs_rank_percentile, rs_3m_return, rs_6m_return,
rs_12m_return, rs_benchmark, rs_benchmark_relative_return, rs_component_score,
benchmark_52w_performance).
tradermonty/claude-trading-skills
a627d17
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.