AugmentClaude

Financial Charts

Render interactive financial charts with technical indicators and market data.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/chart-innei/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Render financial charts via the local chart web app (`app/` — 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, trend template, volume profile, divergence/beichi detection) in TypeScript; the caller only POSTs `{type, symbol...}` to `/api/charts` and gets back `{id, url, technicals?}`. Charts persist as data JSON under `journal/charts/data/`. `url` now points at where the chart actually lives: sepa/intraday land on the symbol page (`http:/localhost:5199/symbol/<SYM>?analysis=<id>`), flow/cohort land on the home page for that date (`http:/localhost:5199?date=YYYY-MM-DD`); old `http:/localhost:5199/charts/<id>` links still work and redirect there. Triggers: K SEPA KMACDrender chart, plot, visualise, sepa dashboard, intraday prediction dashboard.

What this skill does

This skill renders interactive financial charts through a local web application, letting you visualize market data, technical indicators, and trading analysis in one place instead of reviewing tables. The server fetches market data from Longbridge, computes all technical indicators (moving averages, MACD, divergence detection, volume profiles, and pattern recognition) in TypeScript, and stores charts as versioned JSON files that persist across sessions.

What it does

  • Four chart types: intraday capital-flow line charts and cross-symbol comparison bars (both Recharts); SEPA strategy dashboards and short-term multi-timeframe prediction dashboards (both TradingView Lightweight Charts)
  • Multi-timeframe K-line review with 5-minute, 15-minute, and hourly candles plus automatic technical signals (golden crosses, divergence, pattern 123 reversals)
  • Automatic technical detection: 14 classic candlestick patterns, MACD structure signals, swing pivots, volume profiles, and support/resistance zones
  • Real-time data: server fetches Longbridge market data and capital flows; charts update themselves in the browser while open
  • Persistent storage: charts save as JSON under journal/charts/data/ with stable URLs for journal references
  • Symbol cockpit dashboard: aggregated live data with the latest analysis for any symbol at http://localhost:5199/symbol/<SYM>

How to use it

The local chart app must be running on port 5199 (start it with cd app && pnpm start if needed). POST a JSON request to /api/charts with the chart type and symbol—for example, {"type": "intraday", "symbol": "MU.US"} for a multi-timeframe prediction dashboard. The server returns an ID and URL; paste the URL into your journal entry. For intraday predictions, use a two-step pattern: POST without prediction to preview technicals, then PATCH the ID with your scenario analysis to finalize the dashboard.

Related skills