market-session-tracker

Name: market-session-tracker
Author: kansoku-trade

226stars19forks

How to install market-session-tracker?

kansoku-trade/kansoku/market-session-tracker

$npx -y skills add kansoku-trade/kansoku --skill market-session-tracker

Installs into the current project.

Summary

Use when monitoring stocks/ETFs/indices across pre-market, open, intraday, or close — especially when the user is reading session action live and may revise their take as it unfolds. Triggers include 盘前/盘中/收盘 sessions, multi-symbol watchlists (e.g. MU/TSM/SMH semi tracking), user

Files · 1

View on GitHub

SKILL.md

1	# Market Session Tracker
2
3	Real-time US-market analysis pattern. Sits on top of `longbridge-quote`, `longbridge-kline`, `longbridge-capital-flow`, `longbridge-market-temp` — adds orchestration, breakout verification, distribution detection, tier classification, and revision discipline.
4
5	## Standard symbol sets
6
7	\| Theme \| Symbols \|
8	\| -------------- \| ------------------------------------------------------------------------ \|
9	\| Semi / memory \| `MU.US`, `TSM.US`, `DRAM.US` (Roundhill Memory ETF), `SMH.US`, `SOXX.US` \|
10	\| Indices \| `QQQ.US`, `SPY.US`, `DIA.US`, `IWM.US` \|
11	\| Vol / risk-off \| `VXX.US`, `UVXY.US`, `TLT.US`, `GLD.US` \|
12
13	`.SOX.US` is unavailable on Longbridge — use `SMH`/`SOXX` ETF proxies.
14
15	## Seven protocols
16
17	0. Trump-feed sweep (pre-cash) — before any pre-market read, run `python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --hours 14`. Any `high`-tier post touching watchlist sectors (tariff_trade / semi_tech / energy / fed_macro / geopolitical) goes into the session report as a candidate explanation for any gap, before running quote-based exuberance math. Skip when the watchlist has no policy-exposed names. See `trump-truth-monitor` skill for tier grading.
18
19	1. Pre-market verification — compute pre vol % of prev day full vol, and pre high % over `prev_close`. Flag exuberance when pre vol > 5% of prev day and pre high > `prev_close × 1.07`.
20
21	2. Failed-breakout 6-signal stack — count how many fire in the cash session:
22
23	1. Pre-market high NOT touched in first 30 min of cash
24	2. New intraday high breaks → price falls back below the broken level within minutes
25	3. Volume does NOT expand at the breakout
26	4. Sector ETF (`SMH`/`SOXX`) does NOT confirm by going green
27	5. Leader stock (MU for memory; TSM for foundry; NVDA for AI) does NOT make new high
28	6. Capital flow: all 3 buckets net selling
29
30	≥ 4 signals fired = failed breakout / distribution. Name the tier (§5).
31
32	3. Capital flow triple-bucket — `longbridge capital <SYM> --format json`. Net = `capital_in − capital_out` for each of large / medium / small. All 3 net out = textbook distribution. Use `--flow` for accelerating-outflow detection.
33
34	4. Cross-asset sentiment matrix
35
36	\| Pattern \| Interpretation \|
37	\| ------------------------------------- \| --------------------------------------- \|
38	\| DIA > SPY > QQQ + VXX down \| Rotation (defensive), not panic \|
39	\| VXX up + GLD up + TLT up \| True risk-off \|
40	\| Sector red + SPY flat + VXX down \| Isolated distribution \|
41	\| HK/CN valuation ≥ 80 + sentiment ≤ 35 \| Known-bubble (overvalued, retail knows) \|
42
43	5. Pullback tier classification
44
45	\| Tier \| Triggers \|
46	\| ---------- \| ------------------------------------------ \|
47	\| 1 震荡 \| Stock −2% from intraday high; closes green \|
48	\| 2 实质回调 \| Stock −5% from peak; sector ETF turns red \|
49	\| 3 板块下跌 \| Sector −3%+; broad indices flat-to-red \|
50	\| 4 风险传染 \| SPY −1%+; VXX +5%+; defensives also fall \|
51
52	Always name the tier explicitly — never vague "weakening".
53
54	6. Scenario probabilities — always 3 scenarios (Bull / Base / Bear) with explicit % (sum=100) and trigger conditions. Mark probabilities as subjective. Revise as data flows with timestamps: `09:30 初判 → 09:54 修正 → 09:56 再修正`.
55
56	7. Thesis revision discipline — when user says "突破"/"冲高"/"回调":
57
58	1. Re-pull live quote + intraday minute tail — do NOT auto-agree
59	2. Check cash intraday high vs pre-market high vs prior intraday high
60	3. Distinguish: true breakout (new high > pre high, holds 5+ min) vs partial (breaks prior intra high but not pre high) vs recovery (only bounces from intra low)
61	4. If data contradicts user, disagree with evidence
62
63	## Output format (each snapshot)
64
65	- Time (ET) — always
66	- Symbol table — last, change%, intra high/low, vs pre high, vol
67	- Key signal (one sentence)
68	- Tier (if pullback context)
69	- Next watch levels (explicit prices, not "around X")
70	- Source: 长桥证券 · Disclaimer: ⚠️ 仅供参考，不构成投资建议
71
72	## Session report logging
73
74	After a session, write a structured log using `templates/session-report.md` in this skill. Default path: `~/git/trade/journal/YYYY-MM-DD-<theme>.md` (a dedicated git repo; `jo

People who liked this also viewed

6 picks

Type

market-session-tracker

226stars19forks

View on GitHub

How to install market-session-tracker?

kansoku-trade/kansoku/market-session-tracker

$npx -y skills add kansoku-trade/kansoku --skill market-session-tracker

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Market Session Tracker
2
3	Real-time US-market analysis pattern. Sits on top of `longbridge-quote`, `longbridge-kline`, `longbridge-capital-flow`, `longbridge-market-temp` — adds orchestration, breakout verification, distribution detection, tier classification, and revision discipline.
4
5	## Standard symbol sets
6
7	\| Theme \| Symbols \|
8	\| -------------- \| ------------------------------------------------------------------------ \|
9	\| Semi / memory \| `MU.US`, `TSM.US`, `DRAM.US` (Roundhill Memory ETF), `SMH.US`, `SOXX.US` \|
10	\| Indices \| `QQQ.US`, `SPY.US`, `DIA.US`, `IWM.US` \|
11	\| Vol / risk-off \| `VXX.US`, `UVXY.US`, `TLT.US`, `GLD.US` \|
12
13	`.SOX.US` is unavailable on Longbridge — use `SMH`/`SOXX` ETF proxies.
14
15	## Seven protocols
16
17	0. Trump-feed sweep (pre-cash) — before any pre-market read, run `python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --hours 14`. Any `high`-tier post touching watchlist sectors (tariff_trade / semi_tech / energy / fed_macro / geopolitical) goes into the session report as a candidate explanation for any gap, before running quote-based exuberance math. Skip when the watchlist has no policy-exposed names. See `trump-truth-monitor` skill for tier grading.
18
19	1. Pre-market verification — compute pre vol % of prev day full vol, and pre high % over `prev_close`. Flag exuberance when pre vol > 5% of prev day and pre high > `prev_close × 1.07`.
20
21	2. Failed-breakout 6-signal stack — count how many fire in the cash session:
22
23	1. Pre-market high NOT touched in first 30 min of cash
24	2. New intraday high breaks → price falls back below the broken level within minutes
25	3. Volume does NOT expand at the breakout
26	4. Sector ETF (`SMH`/`SOXX`) does NOT confirm by going green
27	5. Leader stock (MU for memory; TSM for foundry; NVDA for AI) does NOT make new high
28	6. Capital flow: all 3 buckets net selling
29
30	≥ 4 signals fired = failed breakout / distribution. Name the tier (§5).
31
32	3. Capital flow triple-bucket — `longbridge capital <SYM> --format json`. Net = `capital_in − capital_out` for each of large / medium / small. All 3 net out = textbook distribution. Use `--flow` for accelerating-outflow detection.
33
34	4. Cross-asset sentiment matrix
35
36	\| Pattern \| Interpretation \|
37	\| ------------------------------------- \| --------------------------------------- \|
38	\| DIA > SPY > QQQ + VXX down \| Rotation (defensive), not panic \|
39	\| VXX up + GLD up + TLT up \| True risk-off \|
40	\| Sector red + SPY flat + VXX down \| Isolated distribution \|
41	\| HK/CN valuation ≥ 80 + sentiment ≤ 35 \| Known-bubble (overvalued, retail knows) \|
42
43	5. Pullback tier classification
44
45	\| Tier \| Triggers \|
46	\| ---------- \| ------------------------------------------ \|
47	\| 1 震荡 \| Stock −2% from intraday high; closes green \|
48	\| 2 实质回调 \| Stock −5% from peak; sector ETF turns red \|
49	\| 3 板块下跌 \| Sector −3%+; broad indices flat-to-red \|
50	\| 4 风险传染 \| SPY −1%+; VXX +5%+; defensives also fall \|
51
52	Always name the tier explicitly — never vague "weakening".
53
54	6. Scenario probabilities — always 3 scenarios (Bull / Base / Bear) with explicit % (sum=100) and trigger conditions. Mark probabilities as subjective. Revise as data flows with timestamps: `09:30 初判 → 09:54 修正 → 09:56 再修正`.
55
56	7. Thesis revision discipline — when user says "突破"/"冲高"/"回调":
57
58	1. Re-pull live quote + intraday minute tail — do NOT auto-agree
59	2. Check cash intraday high vs pre-market high vs prior intraday high
60	3. Distinguish: true breakout (new high > pre high, holds 5+ min) vs partial (breaks prior intra high but not pre high) vs recovery (only bounces from intra low)
61	4. If data contradicts user, disagree with evidence
62
63	## Output format (each snapshot)
64
65	- Time (ET) — always
66	- Symbol table — last, change%, intra high/low, vs pre high, vol
67	- Key signal (one sentence)
68	- Tier (if pullback context)
69	- Next watch levels (explicit prices, not "around X")
70	- Source: 长桥证券 · Disclaimer: ⚠️ 仅供参考，不构成投资建议
71
72	## Session report logging
73
74	After a session, write a structured log using `templates/session-report.md` in this skill. Default path: `~/git/trade/journal/YYYY-MM-DD-<theme>.md` (a dedicated git repo; `jo

People who liked this also viewed

6 picks

Type