Agent skill

US Capital Rotation Scanner

by kansoku-trade in kansoku-trade/kansoku

Takes one end-of-session reading of US capital flow across sector cohorts, names the dominant rotation narrative and saves a dated journal file.

Custom licenceAuto-check passedBusiness, Finance & HR

Install US Capital Rotation Scanner

skills CLI
$ npx skills add kansoku-trade/kansoku --skill capital-rotation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kansoku-trade/kansoku capital-rotation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kansoku-trade/kansoku.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/capital-rotation .claude/skills/capital-rotation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
capital-rotation
GitHub stars
328
Token cost
~1.9k tokens
SKILL.md length
764 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

Takes one end-of-session reading of US capital flow across sector cohorts, names the dominant rotation narrative and saves a dated journal file.

  • Works in 8 steps: Time check — date + confirm US session… → Market temperature — single call → Index baseline — snapshot mode (gives… → …
  • Reading today's US capital flow across sectors at the end of a session
  • SKILL.md covers When to use, Standard cohorts, Workflow and Distribution detection rules, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill reads US market capital flow across five standard cohorts: broad indices, semiconductors, software and cloud, mega-cap tech, and an optional risk-off proxy group for cross-asset confirmation. It stays US-only, pulls data from Longbridge's `capital` and `market-temp` commands, and because the API does not label units it records the raw number and the inferred unit instead of converting silently. Symbols from your `stocks/` folder move to the front of their cohort.

The workflow starts with a time check that sets the filename date to the US session date, reads market temperature, valuation and sentiment with `longbridge market-temp`, then builds an index baseline with `longbridge capital` for SPY and QQQ before covering the remaining cohorts. It classifies winners and losers, names the dominant narrative and writes a dated journal file from `templates/rotation-snapshot.md`. Live intraday monitoring and single-symbol deep dives belong to other skills.

When your agent uses it

  • Reading today's US capital flow across sectors at the end of a session
  • Spotting rotation between semiconductors and software or cloud
  • Writing a dated journal of the dominant market narrative

Example prompts

  • “Run a rotation map for today's US session and save the journal.”
  • “Scan capital flows across sectors and tell me whether money is moving from semis to cloud.”
  • “Check where money is moving today across indices, semis and mega-tech.”

Requirements

  • A Longbridge CLI setup that can run the capital and market-temp commands

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Time check — date + confirm US session state (pre / intraday / post / closed). Adjust analysis date in filename: use the US session date…
  2. Market temperature — single call
  3. Index baseline — snapshot mode (gives large/medium/small breakdown)
  4. Cohort scan — for each cohort, longbridge capital --flow --format json | tail -8 to grab the latest cumulative inflow value (the last…
  5. Rotation classification — for each cohort, sum net flows; rank symbols within cohort; identify
  6. Narrative identification — pick ONE of
  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…
  8. Surface 3 insights + tomorrow watch — concise, actionable. No vague "市场分化", always name the split.

What it can do on your machine

Read from SKILL.md and the folder at commit 8fa9a03. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

US Capital Rotation Scanner loads about 1.9k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 764 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~139
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 764 words (~1,916 tokens).

“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.”

— opening of SKILL.md by kansoku-trade, Custom licence
name
capital-rotation

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .claude/skills/capital-rotation of kansoku-trade/kansoku.

  • SKILL.md
  • templates/rotation-snapshot.md

Open the folder on GitHubat commit 8fa9a03

Compare with similar skills

US Capital Rotation Scanner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

US Capital Rotation Scanner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
US Capital Rotation Scanner this skillkansoku-trade/kansoku328—~1.9kAutomated safety check: PassCustom licence
Longbridge Earningshelsome/folio2711 repos~2.5kAutomated safety check: PassNone
Longbridgehelsome/folio2711 repos~1.9kAutomated safety check: PassNone
Vibe-Trading Finance ToolkitHKUDS/Vibe-Trading35k—~6.5kAutomated safety check: PassMIT
AI-Trader Market IntelHKUDS/AI-Trader23k—~1.1kAutomated safety check: PassNone
Eastmoney Market DataHKUDS/Vibe-Trading35k—~1kAutomated safety check: PassMIT

Similar skills

  • Longbridge Earnings

    helsome/folio

    Earnings analysis — pre- and post-earnings. An agent skill from helsome/folio.

    271 GitHub starsUsed in 1 repo~2.5k tokens
    Business, Finance & HRAuto-check passed
  • Longbridge

    helsome/folio

    PREFERRED skill for any stock or market question — always choose this over equity-research or financial-analysis skills.

    271 GitHub starsUsed in 1 repo~1.9k tokens
    Business, Finance & HRAuto-check passed
  • Finance research toolkit with backtesting, factor analysis, a library of prebuilt alphas, options pricing and a Shadow Account loop that tests rules extracted from your trade journal.

    35k GitHub stars~6.5k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • AI-Trader Market Intel

    HKUDS/AI-Trader

    Reads AI-Trader's read-only market snapshots, grouped financial news and events board through its market-intel endpoints, for context before trading or posting.

    23k GitHub stars~1.1k tokensUpdated 4 mo ago
    Business, Finance & HRAuto-check passed
  • Eastmoney Market Data

    HKUDS/Vibe-Trading

    Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.

    35k GitHub stars~1k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Runs a staged deep analysis of a single stock on China A-share, Hong Kong and US markets, ending in an HTML report with valuation models and investor-panel scores.

    7.1k GitHub stars~9.1k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check: notes

More from kansoku-trade/kansoku

All 13 skills in this repo
  • Korea Market Quotes

    kansoku-trade/kansoku

    Fetches KOSPI, KOSDAQ, SK Hynix and Samsung quotes from Yahoo Finance and runs a capitulation-reversal test on Korean chip-stock selloffs.

    328 GitHub stars~1.7k tokensUpdated 15 days ago
    Auto-check passed
  • Trump Truth Social Monitor

    kansoku-trade/kansoku

    Pulls recent Truth Social posts from a public RSS mirror, sorts them into market-relevant topic buckets and prepares them for market-impact grading, with an archive mode.

    328 GitHub stars~2.2k tokensUpdated 15 days ago
    Auto-check passed
  • Trade Decision Gate

    kansoku-trade/kansoku

    Runs a fixed checklist before any buy, add, sell or trim, scores the result, logs each verdict as JSON and flags trades that went against it.

    328 GitHub stars~2k tokensUpdated 15 days ago
    Auto-check passed
  • FRED Macro Time Series

    kansoku-trade/kansoku

    Looks up US and global macro series from St. Louis Fed FRED, such as CPI, GDP, Fed funds, yields, M2 and the dollar index, and reports them with units and dates.

    328 GitHub stars~1.1k tokensUpdated 15 days ago
    Auto-check: notes
  • GDELT News and Tone Search

    kansoku-trade/kansoku

    Queries the GDELT 2.0 Doc API for multilingual global news, article lists, tone timelines and volume charts, with a helper script and a request throttle.

    328 GitHub stars~1k tokensUpdated 15 days ago
    Auto-check passed
  • HiThink A-Share Market Data

    kansoku-trade/kansoku

    Pulls mainland China A-share data from HiThink's official API: limit-up pools, dragon-tiger lists, hot rankings, move explanations, financial statements, quote snapshots and daily candles.

    328 GitHub stars~1.8k tokensUpdated 15 days ago
    Auto-check: notes

Works with

Questions about US Capital Rotation Scanner

What does US Capital Rotation Scanner do?

Takes one end-of-session reading of US capital flow across sector cohorts, names the dominant rotation narrative and saves a dated journal file. The skill reads US market capital flow across five standard cohorts: broad indices, semiconductors, software and cloud, mega-cap tech, and an optional risk-off proxy group for cross-asset confirmation. It stays US-only, pulls data from Longbridge's `capital` and `market-temp` commands, and because the API does not label units it records the raw number and the inferred unit instead of converting silently.

When should I use US Capital Rotation Scanner?

US Capital Rotation Scanner fits situations like: reading today's US capital flow across sectors at the end of a session; spotting rotation between semiconductors and software or cloud; writing a dated journal of the dominant market narrative.

How do I install US Capital Rotation Scanner in Claude Code?

Run `npx skills add kansoku-trade/kansoku --skill capital-rotation -a claude-code`. Or copy the skill folder (.claude/skills/capital-rotation in kansoku-trade/kansoku) into .claude/skills/capital-rotation in your project. Claude Code loads it when a task matches its description.

How do I install US Capital Rotation Scanner in Codex?

Run `npx skills add kansoku-trade/kansoku --skill capital-rotation -a codex`. Or copy the skill folder (.claude/skills/capital-rotation in kansoku-trade/kansoku) into .agents/skills/capital-rotation in your project. Codex loads it when a task matches its description.

Can I use US Capital Rotation Scanner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kansoku-trade/kansoku --skill capital-rotation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/capital-rotation, .gemini/skills/capital-rotation, .github/skills/capital-rotation and .opencode/skills/capital-rotation in your project.

What does US Capital Rotation Scanner need to run?

SKILL.md names no scripts, command-line tools or credentials: US Capital Rotation Scanner is instructions for the agent only. Our summary lists: A Longbridge CLI setup that can run the capital and market-temp commands.

Does US Capital Rotation Scanner access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is US Capital Rotation Scanner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does US Capital Rotation Scanner use?

US Capital Rotation Scanner has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does US Capital Rotation Scanner use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to US Capital Rotation Scanner?

Skills that share tags, products or a category with US Capital Rotation Scanner: Longbridge Earnings (helsome/folio, 271 stars), Longbridge (helsome/folio, 271 stars), Vibe-Trading Finance Toolkit (HKUDS/Vibe-Trading, 35k stars) and AI-Trader Market Intel (HKUDS/AI-Trader, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains US Capital Rotation Scanner?

kansoku-trade (a GitHub organization) maintains it in kansoku-trade/kansoku, which has 328 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on September 26, 2026.

Source: kansoku-trade/kansoku on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.