Agent skill · AI & Agents

market-session-tracker

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 observations like "突破"/"冲高"/"回调"/"假突破", capital flow checks, market temperature checks, semi/AI/memory plays, and any request that bundles a position context with a live read.

kansoku-tradegithub.com/kansoku-tradeGitHub ↗
claude-codeships scriptsNOASSERTION
Install
npx skills add kansoku-trade/kansoku --skill market-session-tracker --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 5
SKILL.md size: 6 KB
Bundled scripts: yes
Path: .claude/skills/market-session-tracker/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 272
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Market Session Tracker 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. ## Standard symbol sets | Theme | Symbols | | -------------- | ------------------------------------------------------------------------ | | Semi / memory | `MU.US`, `TSM.US`, `DRAM.US` (Roundhill Memory ETF), `SMH.US`, `SOXX.US` | | Indices | `QQQ.US`, `SPY.US`, `DIA.US`, `IWM.US` | | Vol / risk-off | `VXX.US`, `UVXY.US`, `TLT.US`, `GLD.US` | `.SOX.US` is unavailable on Longbridge — use `SMH`/`SOXX` ETF proxies. ## Seven protocols **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. **1. P

What's inside
Steps it walks through
  1. Standard symbol sets
  2. Seven protocols
  3. Output format (each snapshot)
  4. Session report logging
  5. Optional: position context
  6. Anti-patterns
Ships with 4 files
  • launchd/README.md
  • launchd/dev.innei.trade.weekly-watch.plist
  • scripts/weekly-watch.py
  • templates/session-report.md
More from kansoku
All skills →
About this skill
What does the market-session-tracker skill do?

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 observations like "突破"/"冲高"/"回调"/"假突破", capital flow checks, market temperature checks, semi/AI/memory plays, and any request that bundles a position context with a live read.

How do I install it?

Run `npx skills add kansoku-trade/kansoku --skill market-session-tracker --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From kansoku-trade/kansoku, a repository with 272 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going