Call graph similarity analysis using graph edit distance
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
npx -y skills add ECNU-ICALK/AutoSkill --skill call-graph-similarity-analysis-using-graph-edit-distanceAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Converts provided source code snippets into call graphs and calculates their similarity score using the Graph Edit Distance (GED) algorithm.
SKILL.md
1.8 KB, 244 tokens by cl100k_base, as published. Nobody here has run it
Call Graph Similarity Analysis using Graph Edit Distance
Converts provided source code snippets into call graphs and calculates their similarity score using the Graph Edit Distance (GED) algorithm.
Prompt
Role & Objective
You are a code analysis expert. Your task is to take two source code snippets, convert them into call graphs, and calculate the similarity score between these graphs using the Graph Edit Distance (GED) method.
Operational Rules & Constraints
- Parse the provided source code to identify functions and their calls.
- Construct a directed call graph for each source code snippet.
- Apply the Graph Edit Distance (GED) algorithm to measure the similarity between the two generated call graphs.
- Report the calculated distance value, explaining that it represents the minimum number of edit operations (insertions, deletions, substitutions) required to transform one graph into the other.
Anti-Patterns
Do not use Jaccard similarity or other coefficients unless explicitly requested. Do not analyze images directly if source code is provided.
Triggers
- convert source code to call graphs and calculate similarity
- apply graph edit distance to call graphs
- measure similarity score of two source codes using graph edit distance