Vector Hyperbolic
Skill Verified ActiveEmbed hierarchical data via npx ruvector@0.2.25 embed text and project into the Poincare ball in user code (no --model poincare flag in 0.2.25)
To enable users to embed hierarchical data effectively by leveraging the Poincare ball model for more accurate representation of hierarchical relationships.
Features
- Embed text data using ruvector@0.2.25
- Project embeddings into the Poincare ball space
- Calculate geodesic distance for hierarchical data
- Store hyperbolic embeddings for retrieval
Use Cases
- Analyzing dependency trees and module structures
- Mapping class hierarchies in codebases
- Discovering relationships in taxonomies and ontologies
- Navigating codebases by finding specific or general modules
Non-Goals
- Providing a first-class CLI flag for Poincare ball projection in ruvector@0.2.25
- Managing a full-fledged hyperbolic search index directly
- Automating the projection and distance calculation without user code
Workflow
- Ensure ruvector@0.2.25 is available
- Generate a base ONNX embedding
- Project the embedding into the Poincare ball (manual step)
- Calculate geodesic distance
- Store the projected coordinates
Prerequisites
- npm and Node.js installed
- ruvector@0.2.25 installed or installable via npm
Practical Utility
- info:Edge casesThe SKILL.md mentions the lack of a direct Poincare flag and the need for post-processing, which covers a limitation but not specific failure modes with recovery.
Installation
First, add the marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-ruvector@rufloQuality Score
VerifiedTrust Signals
Similar Extensions
Geniml
99Part of the AlterLab Academic Skills suite. This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
OraClaw Forecast
100Time series forecasting for AI agents. ARIMA and Holt-Winters predictions with confidence intervals. Predict revenue, traffic, prices, or any sequential data. Sub-5ms inference.
SHAP Model Interpretability
100Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
Arize Evaluator
100Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.
Rag Architect
100Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.
Vector Setup
100First-run setup for ruvector@0.2.25 — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via `doctor`