What is portfolio-optimization-ai?

A workflow for researching portfolio allocations with Riskfolio-Lib, a Python library for risk-based investment analysis. It covers data checks, investment rules, optimization, diagnostics, and audits of the results.

Use it to construct long-only or constrained portfolios, compare risk and return choices, inspect generated weights, and produce audited allocation reports.

It makes the assumptions, constraints, input data, and limitations of calculated portfolio weights explicit and repeatable.

portfolio-optimization-ai — Skill for Claude Code by nutdnuy

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/nutdnuy/portfolio-optimization-ai-plugin

agentmods

npx agentmods add skills/nutdnuy/portfolio-optimization-ai-plugin/portfolio-optimization-ai

Made for: Claude Code.

Or install portfolio-optimization-ai-plugin, the plugin that ships this one along with the rest of its 1 skill, 5 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nutdnuy/portfolio-optimization-ai-plugin/portfolio-optimization-ai.svg)](https://agentmods.dev/skills/nutdnuy/portfolio-optimization-ai-plugin/portfolio-optimization-ai)

Your own site

<a href="https://agentmods.dev/skills/nutdnuy/portfolio-optimization-ai-plugin/portfolio-optimization-ai"><img src="https://agentmods.dev/badge/skills/nutdnuy/portfolio-optimization-ai-plugin/portfolio-optimization-ai.svg" alt="Measured on agentmods" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 806 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.00806
Opus 5	$0.00023	$0.00403
Sonnet 5	$0.00009	$0.00161
Haiku 4.5	$0.00005	$0.00081

Measured 8d ago against content hash 1ba9a49685f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

portfolio-optimization-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/portfolio-optimization-ai/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Portfolio Optimization AI

This skill helps Claude Code or Codex run disciplined portfolio optimization research using Riskfolio-Lib behind the scenes when runtime dependencies are available.

Default user-facing language is Thai. Write reusable artifacts, schemas, technical docs, and code comments in English.

Read First

Before optimizing a portfolio or changing files, read the relevant references:

references/riskfolio-workflow.md for the supported Riskfolio-Lib workflow.
references/limitations-and-validation.md for required limitations and audit checks.

Core Workflow

Use this sequence unless the user asks for only one stage:

Data intake: identify whether the file contains returns or prices. Record frequency, date column, assets, sample range, missing data, and the source.
Mandate and constraints: clarify or infer long-only vs shorting, max single-asset weight, minimum weight, risk-free rate, risk measure, and objective. Default to long-only and no leverage.
Run folder: create a reproducible run folder with the CLI before running optimization when filesystem access is available.
Optimization: use Riskfolio-Lib only after checking runtime dependencies. Do not hand-calculate a substitute and present it as Riskfolio output.
Diagnostics: report weight sum, gross exposure, concentration, rough sample return, volatility, Sharpe, and sample max drawdown.
Limitations: always include data, model, constraint, cost, liquidity, and no-guarantee limitations.
Audit: run audit-output before finalizing file-based results.

Artifact CLI

Check runtime:

python3 scripts/portfolio_optimizer_ai.py setup-check

Create a run folder:

python3 scripts/portfolio_optimizer_ai.py init-run \
  --name "<portfolio name>" \
  --data-path "<returns-or-prices.csv>" \
  --data-kind returns \
  --frequency daily \
  --risk-measure MV \
  --objective Sharpe \
  --max-weight 0.40 \
  --output-root outputs

Read the full file on GitHub · 110 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 110 lines · 45 tokens per session scan A 1ba9a49685f1

Subscribe to this mod's changes

portfolio-optimization-ai is a skill published in the GitHub repository nutdnuy/portfolio-optimization-ai-plugin (25 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 806 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Finance and fintech

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

portfolio-optimization-ai