fibonacci-trading
Skill36 starsChanged 8 months agoMITView on GitHub
Fibonacci retracement and extension trading for NSE/BSE equities. Covers entry zones using retracement levels, profit targets using extension levels, and confluence zone identification.
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
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
- Distinctive: line 18
No dependencies required. Just provide a swing high and swing low price — Claude calculates all Fib levels instantly.
- Distinctive: line 38
After a significant move up, price often pulls back to these levels before continuing:
- Distinctive: line 53
After a retracement completes and price resumes the trend:
“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.
Files
Fibonacci Trading
Fibonacci levels identify high-probability zones where price tends to react — for entries on pullbacks and targets on extensions.
Prerequisites
No dependencies required. Just provide a swing high and swing low price — Claude calculates all Fib levels instantly. Enhanced with Groww MCP (auto-identifies swings from candles) or yfinance.
Data Needed
- Swing high and swing low: From
fetch_historical_candle_dataor user-provided prices - Current price:
get_quotes_and_depthfrom Groww, or user-provided - For precise calculation, you can compute in Python:
diff = swing_high - swing_low levels = { "23.6%": swing_high - diff * 0.236, "38.2%": swing_high - diff * 0.382, "50.0%": swing_high - diff * 0.500, "61.8%": swing_high - diff * 0.618, "78.6%": swing_high - diff * 0.786, }
Retracement Levels (Entry Zones)
After a significant move up, price often pulls back to these levels before continuing:
| Level | Character | Trading Implication |
| 23.6% | Shallow pullback | Strong trend — buyers eager, enter aggressively |
| 38.2% | Normal pullback | Healthy trend — standard entry zone |
| 50.0% | Deep pullback | Trend weakening but viable — enter with caution |
| 61.8% | Golden ratio | Last stand for the trend — high reward if it holds |
| 78.6% | Very deep | Trend likely failed — avoid or use tight stop |
For downtrend retracements (price bouncing up):
Same levels but inverted — measure from swing high down to swing low.
Extension Levels (Profit Targets)
After a retracement completes and price resumes the trend:
| Level | Use |
| 100% | Measured move — equal to the prior swing |
| 127.2% | Conservative target — good for partial profit |
| 161.8% | Standard target — most common for swing trades |
| 200.0% | Extended target — for strong trends |
| 261.8% | Full extension — rare, only in powerful moves |
Calculating Extensions
# For uptrend: price resumed from point C (retracement low)
ext_127 = C + (swing_high - swing_low) * 1.272
ext_161 = C + (swing_high - swing_low) * 1.618
ext_200 = C + (swing_high - swing_low) * 2.000How to Draw Fibs
- Identify the swing: Find the most recent significant high and low (at least 5% move)
- Direction matters:
- Uptrend retracement: Anchor at swing low, drag to swing high
- Downtrend retracement: Anchor at swing high, drag to swing low
- Use the right swing: The most recent completed swing, not one still in progress
- Multiple swings: You can draw Fibs from different timeframes. When levels from different swings overlap, that's a confluence zone (very strong).
Confluence Zones
The most powerful Fibonacci levels are where they align with other technical factors. These zones have the highest probability of price reaction.
| Confluence Combination | Strength |
| Fib level alone | Moderate |
| Fib + horizontal S/R | Strong |
| Fib + moving average (SMA50/200) | Strong |
| Fib + trendline | Strong |
| Fib + S/R + MA | Very strong |
| Fib from multiple timeframes overlapping | Very strong |
Practical Examples
- Fib 38.2% from daily swing aligns with SMA50 → strong buy zone
- Fib 61.8% from weekly swing aligns with horizontal support from 3 months ago → high-probability entry
- Fib extension 161.8% aligns with a round number (Rs.2,000) → likely profit target
Fibonacci Trading Rules
- Don't use Fibs in isolation — they work best as confirmation alongside S/R, volume, and indicators
- Zone, not line — treat each level as a zone (±1-2%), not a precise price
- Wait for reaction — don't blindly buy at a Fib level. Wait for a reversal candle (hammer, engulfing, etc.)
- Strongest entries: Fib 38.2% to 61.8% zone in a healthy trend with volume confirmation
- If 78.6% breaks: The trend is likely over — exit or reverse
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- SKE-Labs/agent-trading-skills★ 17same name
- Shubhamkumartrichy/claude-trading-skills-india★ 7same name
- IngAs8/ClaudeSkill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- multi-timeframe-analysisSkill
- nse-trading-toolkitSkill
- position-sizingSkill
- risk-reward-ratioSkill
- rsi-divergenceSkill
- stop-loss-strategiesSkill
- technical-analysisSkill
- trailing-stopsSkill
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
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.

