agentleFS
ShubhamkumartrichyShubhamkumartrichy/claude-trading-skills-india/skills/multi-timeframe-analysis/SKILL.md

multi-timeframe-analysis

Skill64 starsChanged 16 days agoMITView on GitHub

Three-screen multi-timeframe analysis for NSE/BSE stocks and indices: weekly (or monthly) sets the bias, daily finds the setup, and 75-minute / 15-minute bars time the entry, with a 6-factor confluence score that sets position size. Uses ta.py mtf to resample daily data into weekly and monthly views automatically.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    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:

    Wait for the lower timeframe to turn in your direction: a reversal candle at the level, a 75-min close back above VWAP or EMA20, an RSI …

    line 56
  2. Distinctive:

    Avoid entries in the first 15 minutes (pre-open imbalance) and the last 30 minutes (closing-VWAP window) unless that is your method.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 3 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

Multi-Timeframe Analysis

Higher timeframes decide direction; lower timeframes refine timing. Trading against the weekly trend needs a much stronger reason than trading with it.

The three screens (Indian session adaptation)

ScreenPositional / swingShort-term swingIntraday
1 — BiasMonthly + weeklyWeeklyDaily
2 — SetupDailyDaily / 125-min75-min
3 — Entry75-min / 60-min15-min5-min / 3-min

The NSE session is 375 minutes (09:15–15:30). 75-minute candles divide it into exactly five bars, and 125-minute into three, so many Indian traders use them instead of 1h/4h, which leave a stub bar. Most Indian charting tools (Kite, TradingView, Groww) offer custom intervals.

Run it

python3 ../technical-analysis/scripts/ta.py mtf --symbol HDFCBANK      # or --csv / --candles
python3 ../technical-analysis/scripts/ta.py mtf --csv nifty.csv --json

The script builds weekly and monthly bars from daily data, using ISO weeks for Monday–Friday sessions. The current week is partial until Friday's close. For each timeframe it gives structure, the indicator dashboard and a bias. It then scores a long and a short setup. For screen 3, fetch intraday candles from the broker MCP, or with ta.py summary --symbol X --interval 15m --period 1mo.

Screen 1 — weekly bias

  • Swing structure (HH/HL or LH/LL) and price vs 20- and 50-week SMA.
  • Weekly RSI above or below 50; weekly MACD histogram direction.
  • Major horizontal levels with multiple weekly touches and the 52-week range.
  • Verdict: bullish / bearish / neutral. Neutral weekly means smaller size or range tactics only.

Screen 2 — daily setup (in the weekly direction)

  • Uptrend: look for pullbacks to SMA20/50, prior breakout levels, or Fib 38.2–61.8% on declining volume. Downtrend: the mirror image.
  • Patterns: flags, bases, double bottoms or tops, breakouts with volume and rising delivery %.
  • Verdict: setup present / no setup / counter-trend (risky).

Screen 3 — entry timing

  • Wait for the lower timeframe to turn in your direction: a reversal candle at the level, a 75-min close back above VWAP or EMA20, an RSI hook from 40, or a MACD cross.
  • The stop goes beyond the lower-timeframe swing, which tightens risk and improves R:R.
  • Avoid entries in the first 15 minutes (pre-open imbalance) and the last 30 minutes (closing-VWAP window) unless that is your method.

Confluence score (1 point each; the script computes it)

Factor
Weekly trend agrees with direction+1
Daily shows a valid setup (pullback to MA/level in trend)+1
Daily RSI supports (rising 40–70 for longs)+1
Daily MACD histogram improving+1
Clear S/R within ~2 ATR for stop or target+1
Volume confirms (up-day expansion or quiet pullback)+1
ScoreAction
5–6Strong: full planned size
4Good: full size
3Marginal: half size
2Weak: skip or paper trade
0–1No trade

The score is mechanical. Sanity-check it visually and override with stated reasons.

Common mistakes

  • Fighting the weekly trend because the daily RSI is oversold.
  • Using one timeframe only, or switching timeframes until one agrees.
  • Ignoring the index: on big index days most large caps move with NIFTY. Check NIFTY's weekly bias as screen 0.
  • Treating a partial current week as a completed weekly candle.

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.