agentleFS
ShubhamkumartrichyShubhamkumartrichy/claude-trading-skills-india/skills/fibonacci-trading/SKILL.md

fibonacci-trading

Skill64 starsChanged 17 days agoMITView on GitHub

Fibonacci retracement entry zones and extension targets for NSE/BSE stocks and indices, with automatic swing detection (ta.py fib), trend-based extensions from the pullback point, and confluence with moving averages, support/resistance, round numbers and option OI strikes.

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

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use a completed swing of at least about 5% (stocks) or 3% (indices), not one still in progress.

    line 60
  2. Distinctive:

    Use split-adjusted data. A bonus or split inside the swing ruins the levels.

    line 62
  3. Distinctive:

    Treat each level as a zone (±1% for stocks, ±0.5% for indices).

    line 76
  4. Distinctive:

    Wait for a reaction candle in the zone (hammer, engulfing, 75-min reversal).

    line 77
  5. Distinctive:

    Stop goes beyond the next Fib level or the swing extreme, with a buffer of at least 1 ATR.

    line 78
  6. Very specific:

    Check R:R after costs before entering (risk-reward-ratio).

    line 80

“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

Fibonacci Trading

Fibonacci levels mark zones where pullbacks often pause and where extended moves often stall. Use them as zones that need confirmation, never as standalone signals.

Compute

# Manual swing (e.g. NIFTY rallied 22,000 → 24,000)
python3 ../technical-analysis/scripts/ta.py fib --high 24000 --low 22000 --trend up
# Add the pullback low (point C) for trend-based extension targets
python3 ../technical-analysis/scripts/ta.py fib --high 24000 --low 22000 --trend up --pivot 23200
# Down-swing (rally retracements are sell zones)
python3 ../technical-analysis/scripts/ta.py fib --high 24000 --low 22000 --trend down
# Automatic: largest swing in the last 120 bars, with current price position
python3 ../technical-analysis/scripts/ta.py fib --symbol NIFTY          # or --csv / --candles

The user's phrasing "from 24,000 to 22,000" means a down-swing (high first). Draw retracements upward from the low.

Retracements (entry zones)

LevelCharacterUse
23.6%ShallowVery strong trend; aggressive entries only
38.2%NormalStandard pullback entry zone
50.0%Deep (not a true Fib ratio, widely watched)Valid with confirmation
61.8%Golden ratioLast good defence of the trend; best R:R if it holds
78.6%Very deepTrend likely failing; tight stop or avoid

The best zone in healthy trends is 38.2%–61.8% on falling volume, followed by a reversal candle. A close beyond 78.6% invalidates the swing.

Extensions (targets)

LevelUse
100%Measured move (AB = CD)
127.2%Conservative target, partial profit
161.8%Standard swing target
200% / 261.8%Strong trends only

With --pivot (point C, the end of the retracement) the script projects trend-based extensions: C ± (B − A) × level. Without it, extensions are measured from A, which is the classic extension beyond B.

Drawing rules

  1. Use a completed swing of at least about 5% (stocks) or 3% (indices), not one still in progress.
  2. Uptrend: anchor at the swing low and drag to the swing high. Downtrend: the reverse.
  3. Use split-adjusted data. A bonus or split inside the swing ruins the levels.
  4. Draw from more than one timeframe. Where weekly and daily Fib levels overlap is a strong zone.

Confluence (strength ladder)

CombinationStrength
Fib aloneModerate
Fib + horizontal S/R or gap zoneStrong
Fib + SMA50/SMA200Strong
Fib + round number (₹1,000; NIFTY 24,500) or a big option-OI strikeStrong (India-specific magnet)
Fib + S/R + MA, or multi-timeframe Fib overlapVery strong

Rules

  1. Treat each level as a zone (±1% for stocks, ±0.5% for indices).
  2. Wait for a reaction candle in the zone (hammer, engulfing, 75-min reversal).
  3. Stop goes beyond the next Fib level or the swing extreme, with a buffer of at least 1 ATR.
  4. Take partial profits at 127.2%, trail the rest (trailing-stops).
  5. Check R:R after costs before entering (risk-reward-ratio).

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.