gap-trading

Name: gap-trading
Author: SKE-Labs

15stars2forks

How to install gap-trading?

ske-labs/agent-trading-skills/gap-trading

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

Installs into the current project.

Summary

Identify and test opening-gap continuation or fade setups. Use when price opens away from the prior session and the user needs a normalized gap definition, catalyst context, entry, invalidation, and cost-aware plan.

Files · 1

View on GitHub

SKILL.md

1	# Gap Trading
2
3	Trade price gaps by classifying gap type first -- different types require opposite strategies.
4
5	## Identification
6
7	Distinguish a full gap (open above the prior high or below the prior low) from a body gap (open away from the prior close). State the exchange session, corporate-action adjustment, and overnight-trading treatment.
8
9	```
10	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval="1D", date=<date>)
11	```
12
13	Compute both percentage gap and `abs(Open - Previous Close) / prior ATR`. Set the minimum from tick size, spread, and the instrument's historical gap distribution; do not use a universal percentage cutoff.
14
15	## Gap Classification
16
17	Classify observable context rather than assigning universal fill rates:
18
19	\| Context \| Evidence to record \| Candidate hypothesis \|
20	\| --- \| --- \| --- \|
21	\| Range / no catalyst \| Gap remains inside an established range \| Fade after a defined reversal trigger \|
22	\| Level break / catalyst \| Gap clears a predeclared level with unusual participation \| Continuation after an opening range \|
23	\| Extended move \| Gap follows an objectively extended trend \| Test fade and continuation separately \|
24
25	## Workflow
26
27	### 1. Detect and Classify
28
29	```
30	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval="1D", date=<date>)
31	get_indicators(indicator_code="mfi", symbol=<symbol>, exchange=<exchange>, interval="1D")
32	```
33
34	Calculate both normalized gap measures. Compare volume with the same time-of-day baseline and document the catalyst from a primary source when available.
35
36	### 2. Check Trend Context
37
38	```
39	get_indicators(indicator_code="dmi", symbol=<symbol>, exchange=<exchange>, interval="1D")
40	get_indicators(indicator_code="ema", symbol=<symbol>, exchange=<exchange>, interval="1D")
41	```
42
43	Determine if ranging, starting trend, mid-trend, or extended trend to confirm classification.
44
45	### 3. Mark Gap Zone
46
47	```
48	draw_chart_analysis(action="create", drawing={
49	"type": "highlight",
50	"points": [
51	{"time": <previous_close_time>, "price": <previous_close>},
52	{"time": <gap_open_time>, "price": <gap_open>}
53	],
54	"options": {"text": "<Gap Type> Gap (+/-X.X%)"}
55	})
56	```
57
58	### 4. Apply Strategy
59
60	- Fade: enter only after the predeclared reversal or failed-break trigger; use the prior close as a scenario target, not an assumed fill.
61	- Continuation: define an opening-range length in bars, enter on its closed-bar break, and invalidate on a tested return through the range or gap level.
62	- Compare several opening-range lengths in training data only and retain a rule only when it survives held-out costs.
63
64	### 5. Report to Orchestrator
65
66	Gap type and rationale, gap size, volume confirmation, strategy recommendation, gap boundaries, fill target, stop level.
67
68	## Evidence and Validation
69
70	- Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
71	- Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
72	- 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.
73	- Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
74	- Research basis: [Research on overnight versus intraday price formation](https://www.sciencedirect.com/science/article/pii/S1059056024006610) supports treating the open as a distinct information period, not assigning universal fill rates to named gap types.
75
76	## Key Rules
77
78	- Do not assume the open is noise or that a named gap type has a fixed fill probability.
79	- Use a time-stamped session definition and adjusted prior prices.
80	- Treat event-driven gaps separately and model opening-auction spread, slippage, and halt risk.
81	- A wider stop must reduce position size; never widen it solely to avoid an exit.
82	- Return `no trade` when the gap is too small relative to total execution cost.
83
84	## Related Skills
85
86	- breakout-trading -- gap-and-go follows breakout principles
87	- momentum-trading -- breakaway gaps create momentum moves

People who liked this also viewed

6 picks

Type

gap-trading

15stars2forks

View on GitHub

How to install gap-trading?

ske-labs/agent-trading-skills/gap-trading

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Gap Trading
2
3	Trade price gaps by classifying gap type first -- different types require opposite strategies.
4
5	## Identification
6
7	Distinguish a full gap (open above the prior high or below the prior low) from a body gap (open away from the prior close). State the exchange session, corporate-action adjustment, and overnight-trading treatment.
8
9	```
10	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval="1D", date=<date>)
11	```
12
13	Compute both percentage gap and `abs(Open - Previous Close) / prior ATR`. Set the minimum from tick size, spread, and the instrument's historical gap distribution; do not use a universal percentage cutoff.
14
15	## Gap Classification
16
17	Classify observable context rather than assigning universal fill rates:
18
19	\| Context \| Evidence to record \| Candidate hypothesis \|
20	\| --- \| --- \| --- \|
21	\| Range / no catalyst \| Gap remains inside an established range \| Fade after a defined reversal trigger \|
22	\| Level break / catalyst \| Gap clears a predeclared level with unusual participation \| Continuation after an opening range \|
23	\| Extended move \| Gap follows an objectively extended trend \| Test fade and continuation separately \|
24
25	## Workflow
26
27	### 1. Detect and Classify
28
29	```
30	get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval="1D", date=<date>)
31	get_indicators(indicator_code="mfi", symbol=<symbol>, exchange=<exchange>, interval="1D")
32	```
33
34	Calculate both normalized gap measures. Compare volume with the same time-of-day baseline and document the catalyst from a primary source when available.
35
36	### 2. Check Trend Context
37
38	```
39	get_indicators(indicator_code="dmi", symbol=<symbol>, exchange=<exchange>, interval="1D")
40	get_indicators(indicator_code="ema", symbol=<symbol>, exchange=<exchange>, interval="1D")
41	```
42
43	Determine if ranging, starting trend, mid-trend, or extended trend to confirm classification.
44
45	### 3. Mark Gap Zone
46
47	```
48	draw_chart_analysis(action="create", drawing={
49	"type": "highlight",
50	"points": [
51	{"time": <previous_close_time>, "price": <previous_close>},
52	{"time": <gap_open_time>, "price": <gap_open>}
53	],
54	"options": {"text": "<Gap Type> Gap (+/-X.X%)"}
55	})
56	```
57
58	### 4. Apply Strategy
59
60	- Fade: enter only after the predeclared reversal or failed-break trigger; use the prior close as a scenario target, not an assumed fill.
61	- Continuation: define an opening-range length in bars, enter on its closed-bar break, and invalidate on a tested return through the range or gap level.
62	- Compare several opening-range lengths in training data only and retain a rule only when it survives held-out costs.
63
64	### 5. Report to Orchestrator
65
66	Gap type and rationale, gap size, volume confirmation, strategy recommendation, gap boundaries, fill target, stop level.
67
68	## Evidence and Validation
69
70	- Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
71	- Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
72	- 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.
73	- Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
74	- Research basis: [Research on overnight versus intraday price formation](https://www.sciencedirect.com/science/article/pii/S1059056024006610) supports treating the open as a distinct information period, not assigning universal fill rates to named gap types.
75
76	## Key Rules
77
78	- Do not assume the open is noise or that a named gap type has a fixed fill probability.
79	- Use a time-stamped session definition and adjusted prior prices.
80	- Treat event-driven gaps separately and model opening-auction spread, slippage, and halt risk.
81	- A wider stop must reduce position size; never widen it solely to avoid an exit.
82	- Return `no trade` when the gap is too small relative to total execution cost.
83
84	## Related Skills
85
86	- breakout-trading -- gap-and-go follows breakout principles
87	- momentum-trading -- breakaway gaps create momentum moves

People who liked this also viewed

6 picks

Type