跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
效率与协作

capital-rotation

Use when reading today's US-market capital flow across multiple sectors to identify rotation direction — e.g. "今天资金流向", "板块强弱", "rotation map", "卖芯买云", "where is money moving today", "scan flows across sectors". Produces a cross-section snapshot of net inflows by cohort (indices / semis / software-cloud / mega-tech / AI applications), names the dominant narrative, and writes a dated journal file. Different from `market-session-tracker` (intraday live monitoring of a single watchlist) — this is a one-shot end-of-session rotation read.

kansoku-trade · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add kansoku-trade/kansoku --skill capital-rotation

技能说明


name: capital-rotation description: Use when reading today's US-market capital flow across multiple sectors to identify rotation direction — e.g. "今天资金流向", "板块强弱", "rotation map", "卖芯买云", "where is money moving today", "scan flows across sectors". Produces a cross-section snapshot of net inflows by cohort (indices / semis / software-cloud / mega-tech / AI applications), names the dominant narrative, and writes a dated journal file. Different from market-session-tracker (intraday live monitoring of a single watchlist) — this is a one-shot end-of-session rotation read.

Capital Rotation Scanner (US-only)

Scans capital flow across standard US cohorts in one session, identifies rotation direction, classifies winners / losers, names the dominant narrative, and logs a journal file.

Scope: US-only. Do NOT query HK / CN / SG markets (user preference). Sources: Longbridge capital, market-temp. Cite as 长桥证券. Units: ambiguous — see TD-UNIT-01 in trading-discipline. Longbridge does not label the unit. Record the raw API number and the unit you inferred; do NOT silently convert (no 亿).

When to use

  • "今天的资金流向", "板块强弱", "rotation map"
  • "卖芯买云", "AI 资金挪去哪了"
  • "软件 / 云强不强", "半导体板块今天主力撤了吗"
  • End-of-session debrief or pre-Asia-open prep
  • Not for single-symbol deep-dive (use longbridge-capital-flow directly)
  • Not for live intraday tracking (use market-session-tracker)

Standard cohorts

CohortSymbols
IndicesSPY, QQQ, DIA, IWM
SemisNVDA, AMD, MU, MRVL, TSM, AVGO, SMH, SOXX, AMKR, ASX
Software / CloudNOW, ORCL, CRM, ADBE, SNOW, DDOG, MDB, PLTR, PANW, CRWD, NET, IGV, CLOU
Mega-techAAPL, MSFT, GOOGL, AMZN, META, TSLA
Risk-off proxyVXX, TLT, GLD (optional, for cross-asset confirmation)

User watchlist override: read stocks/ directory for symbols the user already tracks; promote those to first-tier in their respective cohort.

Workflow

  1. Time check — date + confirm US session state (pre / intraday / post / closed). Adjust analysis date in filename: use the US session date, not Asia local date.

  2. Market temperature — single call:

    longbridge market-temp US --format json
    

    Report Temperature / Valuation / Sentiment.

  3. Index baseline — snapshot mode (gives large/medium/small breakdown):

    longbridge capital SPY.US --format json
    longbridge capital QQQ.US --format json
    

    Net large = capital_in.large - capital_out.large. Flag distribution if large net ≪ 0 while small net > 0 (主力—散户背离).

  4. Cohort scan — for each cohort, longbridge capital <SYM> --flow --format json | tail -8 to grab the latest cumulative inflow value (the last array element is the running total in 万 USD). Parallelize across symbols.

  5. Rotation classification — for each cohort, sum net flows; rank symbols within cohort; identify:

    • Cohort net (sector-level direction)
    • Cohort leader (largest +)
    • Cohort outlier (largest −, especially if cohort net is positive)
    • Cross-cohort rotation: which cohort gained vs lost net flow
  6. Narrative identification — pick ONE of:

    • 卖芯买云 (semis − / software +)
    • 卖云买芯 (inverse)
    • 全板派发 (all cohorts negative + indices large-out)
    • 全板吸金 (all positive + indices large-in)
    • 窄口集中 (one cohort dominated by 1-2 names; rest flat)
    • 风险偏好切换 (cyclicals out / defensives in)
    • AI 已变现 vs 未变现 (rank by AI revenue maturity, see §Narrative criteria)
  7. Write journal file — ~/git/trade/journal/YYYY-MM-DD-flow.md using the US session date. Use templates/rotation-snapshot.md as scaffold. If the file exists (e.g. re-run same day), append a new section with timestamp; do not overwrite.

  8. Surface 3 insights + tomorrow watch — concise, actionable. No vague "市场分化", always name the split.

Distribution detection rules

Use these triggers to label index behavior:

PatternLabel
SPY large net < 0 AND |large net| > 5 × small net机构派发
All 3 buckets (large / medium / small) net < 0全档抛压
Large net < 0, small net > 0, magnitudes similar主力—散户背离
Large net > 0, small net < 0主力吸筹
All 3 buckets > 0全档吸金

Always state the pattern explicitly; do not say "weak / strong" vaguely.

Narrative criteria — "AI 已变现 vs 未变现"

A common useful narrative axis. Classify cohort flow winners / losers by AI revenue maturity:

  • 已变现 (likely to attract flow): MU (HBM revenue confirmed), NOW (AI workflow ARR), ORCL (AI cloud bookings), AMD (MI-series sales), AMZN (AWS Bedrock), PLTR (gov + commercial AIP)
  • 未变现 / 纯叙事: SNOW, MRVL (AI guidance hasn't translated), CRWD (AI security narrative), AAPL (Apple Intelligence vague), GOOGL (Gemini monetization weak)

When flow winners cluster in "已变现" and losers in "未变现", call out "narrative 收敛至 AI 已变现窄口" — this is a key macro signal of late-cycle AI selectivity.

CLI quick reference

longbridge market-temp US --format json
longbridge capital SPY.US --format json                       # snapshot (large/med/small)
longbridge capital QQQ.US --flow --format json | tail -8      # time-series cumulative
longbridge capital --flow --format
阅读完整来源 ↗