Trader Portfolio
- 651 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
trader-portfolio is a Claude agent skill that optimizes portfolio allocation with neural-trader mean-variance math and claude-flow memory tools for developers who automate live trading rebalancing.
About
trader-portfolio is a ruflo skill that runs neural-trader's mean-variance portfolio engine inside Claude agent workflows. It ensures neural-trader is installed via npm ls or npm install --ignore-scripts neural-trader, loads current holdings through mcp__claude-flow__memory_search, and applies optional --risk-target constraints when generating a rebalancing plan. Allowed tools include Bash, Read, and five claude-flow MCP operations: memory_store, memory_retrieve, memory_search, neural_predict, and agentdb_pattern-search for signal and pattern context. The workflow ties AI-driven predictions to concrete allocation adjustments rather than static spreadsheets. Developers reach for trader-portfolio when building agentic trading pipelines that must read persisted portfolio state, compute risk-bounded weights, and output actionable rebalance steps from terminal sessions integrated with ruflo memory and prediction MCP tools during ongoing market operations.
- Automates portfolio construction from risk parameters and market signals
- Tracks real-time performance with AI-powered rebalancing suggestions
- Generates trade execution plans compatible with broker APIs
- Supports backtesting against historical data before live deployment
- 426 installs across indie trading and quant projects
Trader Portfolio by the numbers
- 651 all-time installs (skills.sh)
- +6 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #196 of 1,106 Finance & Trading skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill trader-portfolioAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 651 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you optimize portfolio allocation with mean-variance math?
Generate, track, and optimize a live trading portfolio using AI-driven signals and market data.
Who is it for?
Developers running ruflo or claude-flow agent stacks who store portfolio holdings in memory MCP and want neural-trader mean-variance rebalancing from Bash.
Skip if: Developers building unrelated application backends or teams without claude-flow MCP and neural-trader npm dependencies configured.
When should I use this skill?
The user asks to rebalance a portfolio, optimize allocation with risk targets, or load current holdings from claude-flow memory for trading decisions.
What you get
Risk-constrained allocation weights, rebalancing plan steps, and updated claude-flow memory records for holdings.
- Mean-variance rebalancing plan
- Updated portfolio memory records
By the numbers
- Integrates five claude-flow MCP tools for memory, prediction, and pattern search
- Supports optional --risk-target NUMBER argument for allocation constraints
Files
Optimize portfolio allocation using neural-trader's portfolio engine.
Steps: 1. Ensure neural-trader is available: npm ls neural-trader 2>/dev/null || npm install --ignore-scripts neural-trader 2. Load current portfolio: mcp__claude-flow__memory_search({ query: "current portfolio holdings", namespace: "trading-portfolio" }) 3. Run portfolio optimization:
npx neural-trader --portfolio optimizeWith risk target:
npx neural-trader --portfolio optimize --risk-target <number>4. Get risk metrics:
npx neural-trader --risk assess --portfolio current
npx neural-trader --var --portfolio current
npx neural-trader --correlation --portfolio current --flag-threshold 0.85. Use SONA for expected return prediction: mcp__claude-flow__neural_predict({ input: "expected returns for [HOLDINGS] given current regime" }) 6. Generate rebalancing plan:
npx neural-trader --portfolio rebalanceOutput: trades needed, current vs target weights, estimated costs 7. Search for similar allocations in history: mcp__claude-flow__agentdb_pattern-search({ query: "optimized portfolio Sharpe > 1", namespace: "trading-portfolio" }) 8. Store optimized allocation: mcp__claude-flow__memory_store({ key: "portfolio-optimal-TIMESTAMP", value: "ALLOCATION_JSON", namespace: "trading-portfolio" })
Related skills
Wind Mcp SkillGive their AI coding agent instant access to comprehensive Chinese and global equity, fund, bond, and macroeconomic data from Wind.77.6k74
Upgrade StripeSafely upgrade their Stripe API version and SDKs without introducing breaking changes.55.6k1.7k
Recipe Create Expense TrackerInstantly create a ready-to-use Google Sheets expense tracker with headers, sample data, and sharing permissions.24.4k30.2k
Backtesting FrameworksCreate realistic event-driven backtesters that simulate order execution, slippage, commissions, and position tracking before committing capital to a trading strategy.13.5k38.5k
Grimoire PolymarketQuery live Polymarket odds, search events, and manage conditional order flow directly from Claude or Cursor without leaving the IDE.11.9k6
CoinglassGive their AI coding agents real-time access to crypto derivatives market data such as funding rates, open interest, long/short ratios, liquidations, and futures OHLC h11.4k21How it compares
Pick trader-portfolio over generic finance prompts when claude-flow memory and neural-trader mean-variance rebalancing must run inside an agent Bash workflow.
FAQ
What npm package does trader-portfolio require?
trader-portfolio checks for neural-trader with npm ls and installs it via npm install --ignore-scripts neural-trader when missing. The skill then calls neural-trader's mean-variance portfolio engine to produce allocation and rebalancing output constrained by optional --risk-targe
Which MCP tools does trader-portfolio use for holdings?
trader-portfolio uses claude-flow MCP memory_search to load current portfolio holdings, plus memory_store, memory_retrieve, neural_predict, and agentdb_pattern-search. Bash and Read are also allowed for npm checks and inspecting local trading scripts or configs.