divergence-trading

Name: divergence-trading
Author: SKE-Labs

15stars2forks

How to install divergence-trading?

ske-labs/agent-trading-skills/divergence-trading

$npx -y skills add SKE-Labs/agent-trading-skills --skill divergence-trading

Installs into the current project.

Summary

Define and test regular or hidden divergence at objective pivots. Use when aligning RSI, MACD, Stochastic, MFI, or volume features to exact price-pivot timestamps without counting correlated indicators as independent votes.

Files · 1

View on GitHub

SKILL.md

1	# Divergence Trading
2
3	Divergence occurs when price and an indicator move in opposite directions, signaling potential trend change or continuation.
4
5	## Divergence Types
6
7	### Regular Divergence (Reversal)
8
9	\| Type \| Price \| Indicator \| Signal \|
10	\| --- \| --- \| --- \| --- \|
11	\| Bullish Regular \| Lower Low \| Higher Low \| Momentum weakening, potential reversal up \|
12	\| Bearish Regular \| Higher High \| Lower High \| Momentum weakening, potential reversal down \|
13
14	### Hidden Divergence (Continuation)
15
16	\| Type \| Price \| Indicator \| Signal \|
17	\| --- \| --- \| --- \| --- \|
18	\| Bullish Hidden \| Higher Low \| Lower Low \| Uptrend pullback ending, continuation up \|
19	\| Bearish Hidden \| Lower High \| Higher High \| Downtrend rally ending, continuation down \|
20
21	## Multi-Indicator Detection
22
23	\| Indicator \| Best For \| Extreme Zone \|
24	\| --- \| --- \| --- \|
25	\| RSI \| OB/OS exhaustion \| <30 or >70 for regular div \|
26	\| MACD histogram \| Momentum shifts \| Compare histogram peaks/troughs with price \|
27	\| Stochastic \| Ranging markets \| <20 or >80 (skip mid-range div) \|
28	\| MFI (price/volume transform) \| Volume-aware momentum \| Define pivots and compare slopes \|
29
30	RSI, MACD, and Stochastic are correlated transforms of price, while MFI also uses volume. Do not count them as independent votes or map the count to probability; compare each feature and any combination with a price-only baseline.
31
32	## Validation Rules
33
34	- Use an objective pivot algorithm with fixed left/right bars or ATR reversal and exclude the unconfirmed right-edge pivot.
35	- Calibrate minimum/maximum spacing and optional oscillator zones by instrument/timeframe.
36	- Match indicator values at the exact price-pivot timestamps; use closed data and specify equality tolerance.
37
38	## Workflow
39
40	1. Get indicator data:
41	```
42	get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
43	get_indicators(indicator_code="macd", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
44	get_indicators(indicator_code="stoch", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
45	```
46
47	2. Compare swings: For each indicator, identify last two significant peaks/troughs and compare direction vs price direction
48
49	3. Evaluate: report each divergence and contextual feature separately; use a numeric score only if calibrated on held-out labels.
50
51	4. Get candles for chart drawing:
52	```
53	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<date>)
54	```
55
56	5. Mark divergence on chart:
57	```
58	draw_chart_analysis(action="create", drawing={
59	"type": "trend",
60	"points": [
61	{"time": <first_low_time>, "price": <first_low_price>},
62	{"time": <second_low_time>, "price": <second_low_price>}
63	],
64	"options": {"text": "Bullish Divergence (RSI + MACD)"}
65	})
66	```
67
68	6. Wait for confirmation candle (engulfing, hammer, pin bar) at the divergence zone before entry
69
70	## Evidence and Validation
71
72	- Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
73	- Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
74	- Include spread, fees, slippage, borrow or funding, partial fills, and latency. Reject the setup when net expectancy is not positive or depends on one narrow parameter.
75	- Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
76	- Research basis: The [technical-analysis evidence review](https://papers.ssrn.com/sol3/Delivery.cfm/SSRN_ID603481_code17745.pdf?abstractid=603481) finds mixed performance and common data-snooping problems; multiple correlated oscillators do not create independent confirmation.
77
78	## Key Rules
79
80	- Do not treat multiple price-derived oscillators as independent confirmation.
81	- Calibrate oscillator zones rather than declaring mid-range values meaningless.
82	- Define an objective closed-bar entry and invalidate beyond the second pivot plus buffer.
83	- Test timeframe and regime interactions; no timeframe is universally more reliable.
84	- Keep unresolved divergences and failures in the evaluation sample.
85	- Entry on confirmation candle close; stop beyond the second divergence swing point
86
87	## Related Skills
88
89	- rsi-divergence — focused RSI divergence framework; this skill extends it to multiple indicators
90	- macd-trading — MACD histogram divergence is one of the four indicators in multi-indicator scoring

People who liked this also viewed

6 picks

Type

divergence-trading

15stars2forks

View on GitHub

How to install divergence-trading?

ske-labs/agent-trading-skills/divergence-trading

$npx -y skills add SKE-Labs/agent-trading-skills --skill divergence-trading

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Divergence Trading
2
3	Divergence occurs when price and an indicator move in opposite directions, signaling potential trend change or continuation.
4
5	## Divergence Types
6
7	### Regular Divergence (Reversal)
8
9	\| Type \| Price \| Indicator \| Signal \|
10	\| --- \| --- \| --- \| --- \|
11	\| Bullish Regular \| Lower Low \| Higher Low \| Momentum weakening, potential reversal up \|
12	\| Bearish Regular \| Higher High \| Lower High \| Momentum weakening, potential reversal down \|
13
14	### Hidden Divergence (Continuation)
15
16	\| Type \| Price \| Indicator \| Signal \|
17	\| --- \| --- \| --- \| --- \|
18	\| Bullish Hidden \| Higher Low \| Lower Low \| Uptrend pullback ending, continuation up \|
19	\| Bearish Hidden \| Lower High \| Higher High \| Downtrend rally ending, continuation down \|
20
21	## Multi-Indicator Detection
22
23	\| Indicator \| Best For \| Extreme Zone \|
24	\| --- \| --- \| --- \|
25	\| RSI \| OB/OS exhaustion \| <30 or >70 for regular div \|
26	\| MACD histogram \| Momentum shifts \| Compare histogram peaks/troughs with price \|
27	\| Stochastic \| Ranging markets \| <20 or >80 (skip mid-range div) \|
28	\| MFI (price/volume transform) \| Volume-aware momentum \| Define pivots and compare slopes \|
29
30	RSI, MACD, and Stochastic are correlated transforms of price, while MFI also uses volume. Do not count them as independent votes or map the count to probability; compare each feature and any combination with a price-only baseline.
31
32	## Validation Rules
33
34	- Use an objective pivot algorithm with fixed left/right bars or ATR reversal and exclude the unconfirmed right-edge pivot.
35	- Calibrate minimum/maximum spacing and optional oscillator zones by instrument/timeframe.
36	- Match indicator values at the exact price-pivot timestamps; use closed data and specify equality tolerance.
37
38	## Workflow
39
40	1. Get indicator data:
41	```
42	get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
43	get_indicators(indicator_code="macd", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
44	get_indicators(indicator_code="stoch", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
45	```
46
47	2. Compare swings: For each indicator, identify last two significant peaks/troughs and compare direction vs price direction
48
49	3. Evaluate: report each divergence and contextual feature separately; use a numeric score only if calibrated on held-out labels.
50
51	4. Get candles for chart drawing:
52	```
53	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<date>)
54	```
55
56	5. Mark divergence on chart:
57	```
58	draw_chart_analysis(action="create", drawing={
59	"type": "trend",
60	"points": [
61	{"time": <first_low_time>, "price": <first_low_price>},
62	{"time": <second_low_time>, "price": <second_low_price>}
63	],
64	"options": {"text": "Bullish Divergence (RSI + MACD)"}
65	})
66	```
67
68	6. Wait for confirmation candle (engulfing, hammer, pin bar) at the divergence zone before entry
69
70	## Evidence and Validation
71
72	- Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
73	- Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
74	- Include spread, fees, slippage, borrow or funding, partial fills, and latency. Reject the setup when net expectancy is not positive or depends on one narrow parameter.
75	- Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
76	- Research basis: The [technical-analysis evidence review](https://papers.ssrn.com/sol3/Delivery.cfm/SSRN_ID603481_code17745.pdf?abstractid=603481) finds mixed performance and common data-snooping problems; multiple correlated oscillators do not create independent confirmation.
77
78	## Key Rules
79
80	- Do not treat multiple price-derived oscillators as independent confirmation.
81	- Calibrate oscillator zones rather than declaring mid-range values meaningless.
82	- Define an objective closed-bar entry and invalidate beyond the second pivot plus buffer.
83	- Test timeframe and regime interactions; no timeframe is universally more reliable.
84	- Keep unresolved divergences and failures in the evaluation sample.
85	- Entry on confirmation candle close; stop beyond the second divergence swing point
86
87	## Related Skills
88
89	- rsi-divergence — focused RSI divergence framework; this skill extends it to multiple indicators
90	- macd-trading — MACD histogram divergence is one of the four indicators in multi-indicator scoring

People who liked this also viewed

6 picks

Type