← Back to list
portfolio-analytics Checked
Portfolio-level performance measurement including return metrics, risk metrics, risk-adjusted rat…
8.1Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "portfolio-analytics" skill by following the instructions at https://skill123.me/install/portfolio-analytics.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/portfolio-analytics.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 21 KBAbout this skill
Overview
Portfolio-level performance measurement including return metrics, risk metrics, risk-adjusted ratios, rolling analysis, and HTML reports
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/portfolio-analytics
Score breakdown
Trigger
6.5
Description enumerates metric families well (good keyword coverage); a When-to-Use section exists in the body but not in the description; no When-Not boundary, no trigger-phrase variants.
Structure
8.0
References and scripts correctly separated; SKILL.md at 413 lines is acceptable but duplicates many full function definitions also present in scripts; Files table annotates contents but not consultation timing.
Workflow
7.6
Library/tool-wrapper hybrid: concrete executable paths (pandas code, quantstats one-liners, vectorbt integration) rather than pure description; scripts have CLI modes, demo data, and zero-division guards; ranking output in compare_strategies provides a soft verification loop.
Content
9.0
Clean imperative style; every snippet is copy-runnable; consistent formatting.
Engineering
10.0
Frontmatter valid; shebangs present; dependencies explicitly declared (pandas, numpy, quantstats); all referenced paths exist.
Security
9.0
6.0 manifest: scripts read local CSV and write only stdout/report files locally; no network egress, no credential access, no persistence. Capabilities match declared scope (HTML report generation is declared). No injection text or keys.
Comprehensive portfolio performance-measurement skill: full metric library (Sharpe/Sortino/Calmar/Omega/IR, VaR/CVaR, drawdown, rolling) with two runnable scripts (single-portfolio analysis with --demo/--csv, multi-strategy comparison) and a quantstats guide for HTML tearsheets. Deductions: description lacks When-Not; 413-line SKILL.md carries many inline function bodies that belong in references; no explicit load guidance beyond the Files table.