chart
Render financial charts via the local chart web app (workspace at the repo root — Hono server + React front end, port 5199). Four chart types: intraday capital-flow line (`flow`) and cross-symbol signed-bar comparison (`cohort`) — both Recharts — plus SEPA strategy dashboard (`sepa`) and short-term multi-timeframe prediction dashboard (`intraday`) — both TradingView Lightweight Charts. Multi-timeframe K-line review lives inside `intraday` (the standalone kline chart type was removed). The server fetches Longbridge data itself (kline / capital flow) and computes all indicators (MA, MACD, RS, tr
npx skills add kansoku-trade/kansoku --skill chart --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Creates financial charts by sending structured POST requests to a local chart API to render and persist chart data. It supports four chart types (flow, cohort, sepa, intraday) through a local Hono-based server and React front end, with data fetched and indicators computed server-side. The agent posts a type-specific JSON payload to /api/charts and receives {id, url, technicals?}. Charts are stored as versioned data JSON under journal/charts/data/ and rendered by the latest front-end.
How it works
- Ensure the local chart app is running on port 5199 (pnpm start). 2) POST to /api/charts with a JSON body containing type and symbol (and optional fields like title, context, or position) to create a chart. 3) The server fetches data (Longbridge for flow/kline) and computes indicators (MA, MACD, RS, trend template, volume profile, divergence/beichi detection) in TypeScript. 4) The response returns {id, url, technicals?}. 5) The created chart JSON is written to journal/charts/data/<id>.json. 6) Access the chart via the URL or deep link (kansoku://route/...). 7) For intraday two-call flow: POST preview to get data. If predicting, PATCH /api/charts/:id with {
# chart Creates charts through the local chart app so the user can browse them in one place instead of squinting at tables. The server pulls market data and computes everything; charts are stored as versioned data JSON and always rendered by the latest front-end code. > **Response language**: match the user — 简体 / 繁體 / English. ## When to call - After running `longbridge capital --flow` context or when the user wants a flow visual ⇒ `flow` - For K-line review (multi-timeframe candles + MACD + auto signals) ⇒ `intraday` - After collecting cumulative net inflow across a cohort of symbols ⇒ `cohort` - After running `sepa-strategy` on a single name ⇒ `sepa` - When inside `intraday-signal` ⇒ `intraday` (two-call pattern: POST preview → PATCH prediction) - When inside `capital-rotation` / `market-session-tracker` / `stock-deep-dive`, call this as the LAST step and append the chart URL to the markdown journal entry. Skip when the user only wants a single number or a tiny series — a Unicode sparkline in the chat reply is faster. ## Data-root scenario (kansoku-cli) 在 Kansoku 数据目录里跑（外部 Claude Code、无本地 dev server），走 `kansoku-cli` 而不是 HTTP。判据：环境变量 `$KANSOKU_CLI` 有值 → 走 CLI； 无 → 回退 HTTP。 CLI 与
- When to call
- Data-root scenario (kansoku-cli)
- Server lifecycle
- API
- Symbol cockpit (/symbol/<SYM>)
- POST body per type
- sepa context schema
- intraday two-call pattern
- context — AI-classified news + conclusion (optional, schemaversion 2)
- Realtime prediction upkeep
- 桌面版模式
- Storage
- Sparkline alternative (no API)
- Related skills
set -a
set +a
open "$(echo "$response" | jq -r .deepLink)"
curl -s http://localhost:5199/api/health # {"ok":true,...} = up
pnpm start # serves API + built web UI on :5199What does the chart skill do?
Render financial charts via the local chart web app (workspace at the repo root — Hono server + React front end, port 5199). Four chart types: intraday capital-flow line (`flow`) and cross-symbol signed-bar comparison (`cohort`) — both Recharts — plus SEPA strategy dashboard (`sepa`) and short-term multi-timeframe prediction dashboard (`intraday`) — both TradingView Lightweight Charts. Multi-timeframe K-line review lives inside `intraday` (the standalone kline chart type was removed). The server fetches Longbridge data itself (kline / capital flow) and computes all indicators (MA, MACD, RS, tr
How do I install it?
Run `npx skills add kansoku-trade/kansoku --skill chart --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.