agentleFS
ajeeshworkspaceajeeshworkspace/indian-trading-skills/skills/nse-vcp-screener/SKILL.md

nse-vcp-screener

Skill75 starsChanged 8 months agoMITView on GitHub

Screen Nifty 500 stocks for Mark Minervini's Volatility Contraction Pattern (VCP) — identifying Stage 2 uptrends with tightening price ranges and declining volume before potential breakouts. Use this skill when the user requests VCP screening, Minervini-style setups, Stage 2 breakout candidates, or volatility contraction patterns on NSE/BSE stocks.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Run the Python script with desired parameters:

    line 47
  2. Distinctive:

    Check for upcoming F&O expiry or result season impacts

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

NSE VCP Screener

Overview

This skill screens Indian stocks (Nifty 50/200/500) for Mark Minervini's Volatility Contraction Pattern (VCP). The VCP identifies stocks in Stage 2 uptrends that are forming tightening bases with declining volume — the classic setup before a potential breakout.

The screening pipeline has 3 phases:

  1. Pre-filter: Quick quote-based filtering to eliminate obvious non-candidates
  2. Trend Template: Apply Minervini's 7-point Stage 2 criteria using 260-day histories
  3. VCP Detection & Scoring: Pattern analysis with 5-component composite scoring

Data Source

This screener uses yfinance with .NS suffix for NSE stocks and the niftystocks package for stock universe lists. No paid API keys required.

Execution

python3 scripts/screen_vcp.py --universe nifty500

Command-Line Arguments

ArgumentDefaultDescription
--universenifty50Stock universe: nifty50, nifty200, nifty500, or custom
--custom-tickers—Comma-separated tickers for custom universe (e.g., RELIANCE,TCS,INFY)
--min-contractions2Minimum number of contractions (2-4)
--t1-depth-min10Minimum T1 contraction depth %
--t1-depth-max40Maximum T1 contraction depth %
--contraction-ratio0.75Each contraction must be ≤ this ratio of the previous
--min-contraction-days5Minimum days per contraction
--lookback-days120Days to look back for pattern detection
--breakout-volume-ratio1.5Minimum volume ratio for breakout confirmation
--trend-min-score85Minimum trend template score (0-100)
--output-dirreports/Output directory for results

Workflow

Step 1: Execute the Screener

Run the Python script with desired parameters:

python3 skills/nse-vcp-screener/scripts/screen_vcp.py \
  --universe nifty500 \
  --output-dir reports/

Step 2: Review Results

Load and review the generated reports:

  • JSON: reports/vcp_screener_YYYY-MM-DD_HHMMSS.json (structured data)
  • Markdown: reports/vcp_screener_YYYY-MM-DD_HHMMSS.md (human-readable report)

Step 3: Load References for Interpretation

Read: references/vcp_methodology.md
Read: references/scoring_system.md

Step 4: Present Top Candidates

For each top-scoring candidate, present:

  1. Composite Score (0-100)
  2. Contraction Structure (T1/T2/T3 depths and durations)
  3. Volume Pattern (dry-up ratio)
  4. Pivot Level (breakout price)
  5. Relative Strength vs Nifty 50

Step 5: Actionable Insights

For the top 5-10 candidates:

  • Note proximity to pivot/breakout level
  • Assess if volume is confirming or diverging
  • Check for upcoming F&O expiry or result season impacts
  • Identify F&O lot size (if stock is in F&O segment)

Scoring System

The composite score (0-100) weights 5 components:

ComponentWeightWhat It Measures
Trend Template25%Minervini's 7-point Stage 2 criteria
Contraction Quality25%Tightening base structure
Volume Pattern20%Volume dry-up ratio
Pivot Proximity15%Distance from breakout level
Relative Strength15%Performance vs Nifty 50

Indian Market Adaptations

  • Universe: Nifty 50/200/500 instead of S&P 500
  • Benchmark: Relative strength measured vs Nifty 50 (^NSEI) instead of S&P 500
  • Volatility: T1 depth range widened to 10-40% (vs 8-35% for US) due to higher small-cap volatility
  • Circuit Limits: Stocks hitting circuits may show false VCP patterns — flagged in results
  • Liquidity Filter: Minimum average daily volume of ₹1 crore to filter illiquid stocks
  • F&O Availability: Results indicate whether the stock is in the F&O segment

Resources

references/vcp_methodology.md

Mark Minervini's VCP theory, Stage 2 criteria, contraction rules, and entry methodology adapted for Indian markets.

references/scoring_system.md

Detailed breakdown of the 5-component composite scoring system with thresholds and examples.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.