Documentation
Everything you need to understand how Audit.git scores your commits.
Overview
Audit.git uses a three-stage pipeline to evaluate every commit message: a deterministic rule engine, NLP feature extraction, and GPT-4o semantic analysis. The results are combined into a weighted composite score from 0 to 100.
// Composite score formula
final_score = (rule_score * 0.4) + (llm_score * 0.6)
API Reference
Start analysis job for a public repo URL. Returns a job object immediately.
{ "repo_url": "https://github.com/user/repo", "max_commits": 100 }
Poll job status. Status: pending | running | complete | failed.
Fetch scored commits with pagination. Query: skip, limit.
Export results as CSV.
Grade Scale
80-100
Elite
60-79
Solid
40-59
Average
20-39
Weak
0-19
Chaos
Rule Engine
Length
Subject line between 10 and 72 characters.
Casing
Sentence case or Conventional Commits type prefix.
No Trailing Period
Subject line must not end with a period.
Imperative Verb
Message starts with an imperative verb (Add, Fix, Refactor, etc.).
No Generic Words
No "fix", "update", "wip", "stuff" without context.
Body Present
Multi-line commit with explanatory body.
Line Length
Body lines wrapped at 72 characters.