← Back to list
correlation-analysis Checked
Cross-asset correlation analysis including rolling correlation, hierarchical clustering, tail dep…
7.5Overall 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 "correlation-analysis" skill by following the instructions at https://skill123.me/install/correlation-analysis.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/correlation-analysis.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 · 22 KBAbout this skill
Overview
Cross-asset correlation analysis including rolling correlation, hierarchical clustering, tail dependence, and regime-dependent correlation
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/correlation-analysis
Score breakdown
Trigger
4.5
What-only description with method keywords; no When/When-Not, no trigger phrase variants, no Chinese keywords.
Structure
9.3
275-line SKILL.md, clean references/scripts split, Files table describes each file; progressive disclosure implied by file descriptions rather than explicit load-when guidance.
Workflow
6.8
Reference-heavy SKILL.md offset by two operational scripts with CLI args, --demo synthetic-data mode, rate-limit delay and fetch error handling; no explicit result-verification guidance.
Content
9.0
Concise, concrete code snippets with interpretive tables; consistent formatting.
Engineering
8.0
Valid frontmatter; shebangs and deps declared in docstrings, but --demo fails on missing httpx despite 'None required for demo mode' claim (module-level import); all referenced paths exist.
Security
9.0
Manifest: GET-only market data from api.coingecko.com (official public API; sends only coin id/days params, no local data), no file/env/credential reads, no writes, no persistence. Scripts declare the dependency; SKILL.md description does not mention network fetching — minor declared-scope gap noted. No injection, no secrets.
Well-structured stats reference (Pearson/Spearman/Kendall, EWMA, eigen-decomposition, clustering, tail dependence, regimes) with two CLI scripts incl. demo modes. Weak trigger description (no When/When-Not). Bug: demo mode claims 'no deps' but module-level httpx import breaks demo without install.