legendtkl/agentic-skill-router/skill-143
Claude Code and agent skill by legendtkl/agentic-skill-router
- community
Checking that the SKILL.md file is still in the repository.
Analyze and measure the similarity between different hierarchical category paths for e-commerce applications using advanced distance metrics and visualization techniques.
Install
npx vskill@latest install legendtkl/agentic-skill-router/skill-143SKILL.md
The same SKILL.md was published earlier as legendtkl/agentic-skill-router/skill-143.
Taxonomy Path Similarity Analysis
Measure the similarity between hierarchical category paths and visualize the relationships to enhance product categorization and improve user experience.
Problem
Given diverse category paths such as "electronics -> computers -> laptops" and "tech -> gadgets -> laptops", we want to analyze the similarity between these paths to understand their relations and overlap. This can help in identifying redundant categories and optimizing product listings.
Methodology
- Distance Metrics: Use Jaccard similarity, cosine similarity, or Levenshtein distance to quantify the similarity between category paths.
- Visualization: Generate visual representations such as dendrograms or heatmaps to showcase the similarity between paths.
- Threshold-Based Linking: Establish thresholds for similarity scores to identify and merge closely related categories.
Output
A DataFrame with columns:
path_1: First category pathpath_2: Second category pathsimilarity_score: Calculated similarity score between pathsis_similar: Boolean flag indicating if paths are similar based on a threshold
Installation
4-Step Pipeline
Step 1: Load and Preprocess Paths (step1_load_and_preprocess.py)
- Input: List of category paths as strings.
- Process: Normalize paths, remove special characters, and convert to a standard format for analysis.
- Output: Cleaned list of category paths.
Step 2: Compute Similarity Matrix (step2_similarity_computation.py)
- Input: Cleaned list of category paths.
- Process: Compute a similarity matrix using chosen distance metrics.
- Output: DataFrame containing the similarity scores for all pairs of paths.
Step 3: Identify Similar Paths (step3_path_merging.py)
- Input: Similarity DataFrame from Step 2.
- Process: Apply thresholding to filter and merge similar paths.
- Output: DataFrame of merged paths with similarity scores.
Step 4: Visualize Similarity (step4_visualization.py)
- Input: Merged DataFrame.
- Process: Create visualizations (heatmaps/dendrograms) to represent the similarity relationships.
- Output: Generated visual outputs for analysis.
This pipeline will help in effectively quantifying and visualizing taxonomy path similarities, aiding in better decision-making for category management in e-commerce.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingexperiments/dci-compare/skillrouter-skills/skill-143/SKILL.md
Popularity
- Repository stars
- 6
- Repository forks
- 2
- 7-day trend score
- 15
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/legendtkl/agentic-skill-router/skill-143)