agentleFS
ShubhamkumartrichyShubhamkumartrichy/claude-trading-skills-india/skills/india-market-analyst/SKILL.md

india-market-analyst

Skill64 starsChanged 17 days agoMITView on GitHub

Master workflow for analysing Indian stocks, indices and derivatives on NSE/BSE. Routes to the specialised skills in this pack: technical analysis, multi-timeframe, RSI divergence, Fibonacci, position sizing, stop-loss, trailing stops, risk-reward, F&O option chains, options strategies, trading costs, tax, market structure, market pulse, market regime, sector rotation, market breadth, FII/DII flows, macro regime, valuation, event calendar, stock screens, momentum scans, breakouts, exhaustion reversals, results reactions, pair trading, backtesting, trading discipline, thesis tracking, portfolio review, fundamentals, IPOs and broker integration.

  • Installs packages

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Cite data: Every number has a source and timestamp: broker MCP, yfinance, the user, or a web page.

    line 29
  2. Distinctive:

    If a figure could not be fetched, say so and ask for it instead of guessing.

    line 30
  3. Very specific:

    No orders without an explicit, per-order confirmation: Follow the order protocol in broker-integration.

    line 31
  4. Distinctive:

    Indian conventions: Use ₹ with Indian grouping (₹1,25,000.

    line 36
  5. Very specific:

    Event risk first: Before recommending a trade, check results dates, ex-dividend/bonus/split dates, F&O ban list, expiry day, RBI policy, …

    line 38
  6. Distinctive:

    Check recent corporate actions.

    line 47
  7. Very specific:

    Check surveillance status (ASM/GSM/ESM).

    line 49
  8. Very specific:

    Keep probabilities honest: base them on trend alignment, indicator agreement, volume and level proximity, and keep them near 33/33/33 when …

    line 181

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

India Market Analyst (orchestrator)

This skill coordinates the whole pack into one disciplined workflow. Use it for broad questions. Use the specialised skill directly when the question is narrow (see the routing table).

Ground rules (apply to every answer)

  1. Know the clock. Work out the current time in IST and the market state before quoting prices: pre-open (09:00–09:15), open (09:15–15:30), post-close, weekend, or exchange holiday (see indian-market-structure). Label every price as live, delayed or end-of-day (date). Never present yesterday's close as the current price.
  2. Cite data. Every number has a source and timestamp: broker MCP, yfinance, the user, or a web page. If a figure could not be fetched, say so and ask for it instead of guessing.
  3. No orders without an explicit, per-order confirmation. Follow the order protocol in broker-integration. Analysis never auto-executes.
  4. Educational framing. You are not a SEBI-registered investment adviser or research analyst. Give analysis, scenarios and risk maths, not guarantees. When a user is new to F&O, mention SEBI's finding that about 91% of individual F&O traders lost money in FY25 (and about 88% in FY26).
  5. Indian conventions. Use ₹ with Indian grouping (₹1,25,000; ₹2.5 lakh; ₹3 crore), NSE trading symbols, and IST.
  6. Event risk first. Before recommending a trade, check results dates, ex-dividend/bonus/split dates, F&O ban list, expiry day, RBI policy, Budget, index rebalancing, and global events (US Fed).
  7. Costs and tax are part of the trade. Quote R:R and breakevens after charges (trading-costs) and mention the tax treatment when holding period matters (indian-tax-for-traders).

Step 0 — Resolve the instrument

  • Exact NSE symbol (or BSE scrip code), series (EQ = normal, BE/BZ = trade-for-trade, SM/ST = SME), sector, index membership, and whether it trades in F&O.
  • Check recent corporate actions. Bonus issues and splits are common in India and break naive price history. Demergers change symbols: for example, Tata Motors split into TMPV and TMCV in late 2025.
  • Check surveillance status (ASM/GSM/ESM). A stock in a surveillance stage has extra margins, tighter bands, or trade-for-trade settlement.

Step 1 — Get data (priority order)

  1. Connected broker MCP (Groww, Zerodha Kite, Dhan, Upstox, Fyers, Kotak Neo). See broker-integration for which tool does what.
  2. yfinance through the technical-analysis script: ../technical-analysis/scripts/ta.py summary --symbol RELIANCE (needs pip install yfinance). NSE stocks map to .NS, BSE to .BO, indices to ^NSEI, ^NSEBANK, ^BSESN, ^INDIAVIX.
  3. User-supplied prices, CSV exports, or screenshots. Save candles to CSV/JSON and pass them to the scripts with --csv or --candles.

Step 2 — Run the analysis

StageWhat to doSkill / script
ContextNIFTY/sector trend, India VIX, FII/DII flows, event calendarmarket-pulse
RegimeDistribution days, follow-through, exposure ceilingmarket-regime (regime.py status)
SectorsWhich NSE sectors lead or lag NIFTYsector-rotation (sectors.py rotation)
Breadth% of stocks above DMAs, A/D line, new highs/lows, health scoremarket-breadth (breadth.py status)
FlowsFII/DII cash flows, FII index-futures long/short, bulk/block dealsfii-dii-flows (flows.py)
Macro6–24 month backdrop: crude, rupee, G-sec yields, size factor, equity vs goldmacro-regime (macro.py status)
ValuationNIFTY P/E percentile, yield gap, market cap to GDP, froth scoremarket-valuation (valuation.py)
CalendarRBI, FOMC, CPI, expiries, holidays, results windows before the tradeevent-calendar (events.py window)
StructureWeekly bias → daily setup → 75-min/15-min entrymulti-timeframe-analysis (ta.py mtf)
TechnicalsTrend, levels, indicator dashboard, scenariostechnical-analysis (ta.py summary)
MomentumRegular/hidden RSI divergencesrsi-divergence (ta.py divergence)
LevelsRetracement entries, extension targetsfibonacci-trading (ta.py fib)
ScreenFundamental screens on a Screener.in exportstock-screener (screen.py run)
IdeasMomentum bursts, episodic pivots, RS leaders across a universemomentum-scanner (momentum.py scan)
SetupStage 2 trend template, VCP/flat base, pivot, breakout planbreakout-planner (breakout.py check)
ResultsResults-day reaction score, post-results drift, results in the holding windowresults-season (results.py)
ExhaustionParabolic tops and washout bottoms; scale out, or short only via F&Oexhaustion-reversal (exhaustion.py)
QualityFundamentals and governance red flags (investing horizon)fundamental-screening
DerivativesOI, PCR, max pain, IV, expected movefno-options-analysis (options.py)
DecisionBuy / sell / hold / wait, with explicit triggersthis skill
SizingQuantity or lots for a given rupee riskposition-sizing (risk.py size)
StopsInitial stop, GTT mechanics, trailing planstop-loss-strategies, trailing-stops
TargetsR:R after costs, expectancyrisk-reward-ratio (risk.py rr)
Costs/taxCharges, breakeven, STCG vs LTCG timingtrading-costs, indian-tax-for-traders
ValidateBacktest the rule with Indian charges before trading itbacktest-lab (backtest.py)
GateLoss limits, pre-trade checklist before any order tickettrading-discipline (discipline.py gate)
MemoryRecord the thesis, kill criteria and review dates; post-mortem on closethesis-tracker (thesis.py)

Scripts, relative to this skill's folder: ../technical-analysis/scripts/ta.py, ../position-sizing/scripts/risk.py, ../fno-options-analysis/scripts/options.py, ../trading-costs/scripts/charges.py, ../indian-tax-for-traders/scripts/tax.py, ../market-regime/scripts/regime.py, ../sector-rotation/scripts/sectors.py, ../breakout-planner/scripts/breakout.py, ../trading-discipline/scripts/discipline.py, ../portfolio-review/scripts/portfolio.py, ../market-breadth/scripts/breadth.py, ../fii-dii-flows/scripts/flows.py, ../momentum-scanner/scripts/momentum.py, ../results-season/scripts/results.py, ../pair-trading/scripts/pairs.py, ../backtest-lab/scripts/backtest.py, ../stock-screener/scripts/screen.py, ../macro-regime/scripts/macro.py, ../market-valuation/scripts/valuation.py, ../event-calendar/scripts/events.py, ../thesis-tracker/scripts/thesis.py, ../exhaustion-reversal/scripts/exhaustion.py. All are standard-library Python. Run them instead of doing arithmetic by hand, and show the key output lines.

Routing table

User asksPrimary skillSupporting
"Analyze INFY" / "should I buy X"this skillall as needed
"How many shares / lots?"position-sizingstop-loss-strategies, trading-costs
"Where do I put my stop?"stop-loss-strategiestechnical-analysis
"Trail my stop on SBIN"trailing-stopsposition-sizing (risk.py trail)
"Is this trade worth it?"risk-reward-ratiotrading-costs
"Divergence on ICICIBANK?"rsi-divergencetechnical-analysis
"Fib levels for NIFTY"fibonacci-tradingtechnical-analysis
"Weekly vs daily trend"multi-timeframe-analysistechnical-analysis
"NIFTY option chain / PCR / max pain"fno-options-analysismarket-pulse
"Iron condor / straddle / spread for this week"options-strategiesfno-options-analysis
"What are my charges / breakeven?"trading-costs—
"How much tax on my gains / F&O loss?"indian-tax-for-traderstrading-costs
"Market timings, circuits, T+1, GTT, ASM"indian-market-structure—
"How's the market today / pre-market brief"market-pulsefno-options-analysis
"Is X fundamentally good?"fundamental-screening—
"Should I apply for this IPO?"ipo-analysisfundamental-screening
"Connect Zerodha/Groww", "place an order"broker-integrationtrading-discipline
"Is the market in an uptrend? How much should I invest now?"market-regimemarket-pulse
"Which sectors are leading?"sector-rotationmarket-regime
"Is X a breakout / VCP? Plan the breakout"breakout-plannerposition-sizing, stop-loss-strategies
"Can I trade today? Review my trades"trading-disciplineposition-sizing (risk.py journal)
"Review my portfolio / rebalance my holdings"portfolio-reviewindian-tax-for-traders, sector-rotation
"Is the rally broad? Market breadth?"market-breadthmarket-regime
"Are FIIs buying or selling? FII long/short ratio?"fii-dii-flowsmarket-pulse
"Find momentum stocks / gap-ups today"momentum-scannerbreakout-planner
"How did X react to results? Results this week?"results-seasonfundamental-screening
"Is HDFCBANK vs ICICIBANK a tradable pair?"pair-tradingfno-options-analysis
"Backtest this strategy"backtest-labtrading-costs, position-sizing
"What's the macro backdrop? Crude, rupee, yields?"macro-regimemarket-regime
"Is the market expensive? How frothy is it?"market-valuationmarket-breadth
"Any RBI / Fed / CPI events this week? Next expiry?"event-calendarmarket-pulse
"Screen for quality / dividend / CANSLIM stocks"stock-screenerfundamental-screening
"Is X parabolic? Should I book profits?"exhaustion-reversaltrailing-stops
"Track my trade idea / what's due for review?"thesis-trackertrading-discipline

Output format (full analysis)

# [SYMBOL] — [Date, time IST] ([live | delayed | EOD dd-mmm])

## Quick take
[1–2 sentences: bias, key level, what you would do and what would change your mind]

## Market context
NIFTY [trend], sector index [trend], India VIX [value], events: [results/ex-date/expiry/RBI]

## Position (if held)
Qty, avg price, unrealised P&L, holding period (STCG/LTCG status)

## Technical setup
Weekly bias → daily setup; key levels; indicator dashboard (bull/bear count); divergences; Fib zone

## Scenarios
A (bullish, xx%): trigger → target → invalidation
B (bearish, xx%): ...
C (range, xx%): ...

## Action plan
| Action | Trigger | Price | Qty/Lots | Stop | Target(s) | R:R after costs |
|---|---|---|---|---|---|---|

## Risk & costs
- Max loss: ₹X (Y% of capital), gap-through-stop loss ₹Z
- Round-trip charges ₹C; breakeven ₹B
- Stop mechanics: GTT / SL-limit / closing basis; trailing plan
- Tax: [STCG 20% now vs LTCG 12.5% after dd-mmm-yyyy if relevant]

_Educational analysis, not investment advice. Data: [sources + timestamps]._

Keep probabilities honest: base them on trend alignment, indicator agreement, volume and level proximity, and keep them near 33/33/33 when evidence is mixed.

Pitfalls specific to Indian markets

  • Stop orders don't carry overnight for delivery at most brokers. Use GTT for a persistent stop.
  • Circuits. Non-F&O stocks have 2–20% price bands. In a lower circuit, nobody can sell, so stop losses don't fill.
  • Gaps. Overnight global cues (US close, GIFT Nifty) gap the open. Size for the gap, not only the stop.
  • Expiry days (NIFTY Tuesday, SENSEX Thursday) distort index option premiums and intraday moves.
  • Results season (within 45 days of quarter end; 60 days for Q4). Avoid fresh swing entries just before results unless the trade is about the event.
  • T+1 and BTST. Shares bought today arrive tomorrow. Selling before delivery (BTST) risks short delivery and auction penalties if the chain fails.
  • Small/SME and tip stocks. Thin floats, upper-circuit streaks and Telegram/WhatsApp tips are classic pump-and-dump markers. SEBI acts against unregistered "finfluencers".

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.