rsi-divergence

Name: rsi-divergence
Author: SKE-Labs

15stars2forks

How to install rsi-divergence?

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

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

Installs into the current project.

Summary

Define and test RSI divergence at confirmed price pivots. Use when aligning exact pivot timestamps, spacing, equality tolerances, oscillator zones, closed-bar entry, and invalidation.

Files · 1

View on GitHub

SKILL.md

1	# RSI Divergence Trading
2
3	RSI divergence is a geometric relationship between confirmed price pivots and RSI values at the same timestamps. It is a candidate feature, not a reversal signal by itself.
4
5	## Divergence Types
6
7	### Regular (Reversal)
8
9	\| Type \| Price Action \| RSI Action \| Signal \|
10	\| ----------- \| ------------ \| ---------- \| ----------- \|
11	\| Bullish \| Lower Low \| Higher Low \| Candidate bullish regular divergence \|
12	\| Bearish \| Higher High \| Lower High \| Candidate bearish regular divergence \|
13
14	### Hidden (Continuation)
15
16	\| Type \| Price Action \| RSI Action \| Signal \|
17	\| ----------- \| ------------ \| ----------- \| -------------------- \|
18	\| Bullish \| Higher Low \| Lower Low \| Trend continues up \|
19	\| Bearish \| Lower High \| Higher High \| Trend continues down \|
20
21	## RSI Zones
22
23	\| Level \| Interpretation \|
24	\| ----- \| -------------- \|
25	\| High percentile/band \| Context for bearish candidates; calibrate \|
26	\| Low percentile/band \| Context for bullish candidates; calibrate \|
27	\| Mid-range \| Descriptive only; test rather than discard universally \|
28
29	## Workflow
30
31	1. Get RSI:
32	```
33	get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
34	```
35
36	2. Identify confirmed pivots with fixed left/right bars or an ATR-reversal rule; exclude the unconfirmed right edge
37
38	3. Compare exact timestamps: sample RSI at the two price pivots and apply predeclared price/RSI equality tolerances and pivot-spacing limits.
39
40	4. Get candles for chart marking:
41	```
42	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<date>)
43	```
44
45	5. Mark divergence:
46	```
47	draw_chart_analysis(action="create", drawing={
48	"type": "trend",
49	"points": [
50	{"time": <first_swing_time>, "price": <first_swing_price>},
51	{"time": <second_swing_time>, "price": <second_swing_price>}
52	],
53	"options": {"text": "Bullish RSI Divergence"}
54	})
55	```
56
57	6. Wait for confirmation candle (engulfing, hammer, pin bar) at divergence zone before entry
58
59	### Entry
60
61	- Bullish: enter above confirmation candle at support; stop below swing low; target previous resistance
62	- Bearish: enter below confirmation candle at resistance; stop above swing high; target previous support
63
64	## Evidence and Validation
65
66	- Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
67	- Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
68	- 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.
69	- Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
70	- Research basis: The [technical-rule evidence](https://pmc.ncbi.nlm.nih.gov/articles/PMC4583561/) shows oscillator results vary materially across markets and often weaken after costs; RSI extremes and divergence spacing require calibration.
71
72	## Key Rules
73
74	- Define any support/resistance and entry trigger objectively before evaluation.
75	- Enter only from the specified closed-bar trigger; divergence alone is `watch`.
76	- Test timeframe interactions; no 1H minimum is universally reliable.
77	- Calibrate optional RSI zones and pivot spacing by instrument/regime.
78	- Do not convert correlated price/structure features into a high-probability claim without calibration.
79
80	## Related Skills
81
82	- divergence-trading — extends RSI divergence with multi-indicator scoring (MACD, Stochastic, OBV)
83	- macd-trading — MACD divergence combined with RSI divergence strengthens reversal signals

People who liked this also viewed

6 picks

Type

rsi-divergence

15stars2forks

View on GitHub

How to install rsi-divergence?

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

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

Installs into the current project.

Summary

Define and test RSI divergence at confirmed price pivots. Use when aligning exact pivot timestamps, spacing, equality tolerances, oscillator zones, closed-bar entry, and invalidation.

Files · 1

View on GitHub

SKILL.md

1	# RSI Divergence Trading
2
3	RSI divergence is a geometric relationship between confirmed price pivots and RSI values at the same timestamps. It is a candidate feature, not a reversal signal by itself.
4
5	## Divergence Types
6
7	### Regular (Reversal)
8
9	\| Type \| Price Action \| RSI Action \| Signal \|
10	\| ----------- \| ------------ \| ---------- \| ----------- \|
11	\| Bullish \| Lower Low \| Higher Low \| Candidate bullish regular divergence \|
12	\| Bearish \| Higher High \| Lower High \| Candidate bearish regular divergence \|
13
14	### Hidden (Continuation)
15
16	\| Type \| Price Action \| RSI Action \| Signal \|
17	\| ----------- \| ------------ \| ----------- \| -------------------- \|
18	\| Bullish \| Higher Low \| Lower Low \| Trend continues up \|
19	\| Bearish \| Lower High \| Higher High \| Trend continues down \|
20
21	## RSI Zones
22
23	\| Level \| Interpretation \|
24	\| ----- \| -------------- \|
25	\| High percentile/band \| Context for bearish candidates; calibrate \|
26	\| Low percentile/band \| Context for bullish candidates; calibrate \|
27	\| Mid-range \| Descriptive only; test rather than discard universally \|
28
29	## Workflow
30
31	1. Get RSI:
32	```
33	get_indicators(indicator_code="rsi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)
34	```
35
36	2. Identify confirmed pivots with fixed left/right bars or an ATR-reversal rule; exclude the unconfirmed right edge
37
38	3. Compare exact timestamps: sample RSI at the two price pivots and apply predeclared price/RSI equality tolerances and pivot-spacing limits.
39
40	4. Get candles for chart marking:
41	```
42	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<date>)
43	```
44
45	5. Mark divergence:
46	```
47	draw_chart_analysis(action="create", drawing={
48	"type": "trend",
49	"points": [
50	{"time": <first_swing_time>, "price": <first_swing_price>},
51	{"time": <second_swing_time>, "price": <second_swing_price>}
52	],
53	"options": {"text": "Bullish RSI Divergence"}
54	})
55	```
56
57	6. Wait for confirmation candle (engulfing, hammer, pin bar) at divergence zone before entry
58
59	### Entry
60
61	- Bullish: enter above confirmation candle at support; stop below swing low; target previous resistance
62	- Bearish: enter below confirmation candle at resistance; stop above swing high; target previous support
63
64	## Evidence and Validation
65
66	- Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
67	- Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
68	- 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.
69	- Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
70	- Research basis: The [technical-rule evidence](https://pmc.ncbi.nlm.nih.gov/articles/PMC4583561/) shows oscillator results vary materially across markets and often weaken after costs; RSI extremes and divergence spacing require calibration.
71
72	## Key Rules
73
74	- Define any support/resistance and entry trigger objectively before evaluation.
75	- Enter only from the specified closed-bar trigger; divergence alone is `watch`.
76	- Test timeframe interactions; no 1H minimum is universally reliable.
77	- Calibrate optional RSI zones and pivot spacing by instrument/regime.
78	- Do not convert correlated price/structure features into a high-probability claim without calibration.
79
80	## Related Skills
81
82	- divergence-trading — extends RSI divergence with multi-indicator scoring (MACD, Stochastic, OBV)
83	- macd-trading — MACD divergence combined with RSI divergence strengthens reversal signals

People who liked this also viewed

6 picks

Type