agentleFS
Sign inStart free
Bhala-SrinivashBhala-Srinivash/nse-trading-skills/technical-analysis/SKILL.md

technical-analysis

Skill36 starsChanged 8 months agoMITView on GitHub

Systematic chart reading and technical analysis for NSE/BSE Indian equities. Covers trend identification, support/resistance mapping, volume analysis, indicator dashboards, and probabilistic scenario building. Uses Groww MCP for live data and yfinance for history.

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Read the chart systematically — don't cherry-pick indicators that confirm a bias.

    line 17
  2. Distinctive:

    No hard dependencies. Works best with Groww MCP or yfinance for live data, but can analyze any stock if you provide prices manually.

    line 21
  3. Distinctive:

    When data tools are available, fetch in this order:

    line 25
  4. Distinctive:

    Always present 2-3 scenarios with rough probabilities.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Technical Analysis

Read the chart systematically — don't cherry-pick indicators that confirm a bias.

Prerequisites

No hard dependencies. Works best with Groww MCP or yfinance for live data, but can analyze any stock if you provide prices manually.

Data Collection

When data tools are available, fetch in this order:

  1. Resolve symbol: search_stock_and_others_symbol on Groww
  2. Live quote: get_quotes_and_depth for current price, volume, day range
  3. Indicators: get_historical_technical_indicators for SMA, EMA, RSI, MACD, Bollinger, ADX
  4. Candles: fetch_historical_candle_data with interval=1d for at least 200 days
  5. Long history (if needed): yf.download("SYMBOL.NS", period="2y") via yfinance

Step 1: Trend Identification

  • Primary trend (weekly): Higher highs & higher lows = uptrend. Lower highs & lower lows = downtrend.
  • Secondary trend (daily): Current swing direction within the primary trend.
  • Moving average alignment:
    • Price > SMA20 > SMA50 > SMA200 = strong uptrend
    • Price < SMA20 < SMA50 < SMA200 = strong downtrend
    • Mixed = transitional / choppy
  • Cross signals: Golden cross (SMA50 > SMA200) = bullish. Death cross = bearish.

Step 2: Support & Resistance

  • Horizontal S/R: Recent swing highs and lows with at least 2 touches
  • Round numbers: Psychological levels (Rs.1,000, Rs.1,500, Rs.2,000)
  • Volume clusters: Zones where heavy trading occurred (act as magnets)
  • Dynamic S/R: SMA20 (short-term), SMA50 (medium), SMA200 (major)
  • Gap zones: Unfilled gaps act as support (gap up) or resistance (gap down)

Step 3: Volume Analysis

Price ActionVolumeInterpretation
Rising priceRising volumeStrong move — trend healthy
Rising priceFalling volumeWeak rally — suspect, may reverse
Falling priceRising volumeStrong selling — trend acceleration
Falling priceFalling volumeSelling exhaustion — bounce possible
Spike volume at support—Potential capitulation / reversal
Spike volume at resistance—Breakout attempt or distribution

Compare current volume to 20-day average. >1.5x = significant.

Step 4: Indicator Dashboard

Pull via get_historical_technical_indicators:

IndicatorBullishBearishNeutral
RSI(14)>50, rising from <30<50, falling from >7040-60, flat
MACDLine > Signal, histogram growingLine < Signal, histogram shrinkingNear zero line
Bollinger BandsPrice bouncing off lower bandPrice rejected at upper bandWalking the band
ADX>25 with +DI > -DI>25 with -DI > +DI<20 (no trend)
Stochastic%K crosses above %D below 20%K crosses below %D above 80Mid-range

Count bullish vs bearish signals to gauge overall bias.

Step 5: Probabilistic Scenarios

Always present 2-3 scenarios with rough probabilities. Assign higher probability to the scenario with more technical evidence.

SCENARIO A (Bullish) — XX% probability
- Trigger: [specific price/indicator condition]
- Target: Rs.XXX (nearest resistance / Fib level)
- Invalidation: Close below Rs.XXX

SCENARIO B (Bearish) — XX% probability
- Trigger: [specific condition]
- Target: Rs.XXX (nearest support)
- Invalidation: Close above Rs.XXX

SCENARIO C (Sideways) — XX% probability
- Range: Rs.XXX to Rs.XXX
- Duration estimate: X days/weeks
- Breakout signal: [what to watch]

Probabilities should sum to ~100%. Base them on: trend alignment, indicator consensus, volume confirmation, and S/R proximity.

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.

Check your setup, free