Git-history-informed repository analysis for technical debt, hotspot files, architectural anti-patterns, repeated churn, complexity risk, and refactoring priority. Use when the user asks to analyze git history, find code hotspots, identify debt accumulation, rank risky modules, or plan refactoring from repository evolution evidence.
Scanned 9/12/2026
Install to Claude Code
npx -y skills add whyzsm/tiny-agents --skill agent-git-oracle --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Agent Git Oracle?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/whyzsm-agent-git-oracle)More formats (shields.io, HTML) on the badges page.
---
name: agent-git-oracle
description: "Git-history-informed repository analysis for technical debt, hotspot files, architectural anti-patterns, repeated churn, complexity risk, and refactoring priority. Use when the user asks to analyze git history, find code hotspots, identify debt accumulation, rank risky modules, or plan refactoring from repository evolution evidence."
---
# Agent Git Oracle
Analyze repository history and structure to guide safe refactoring. This skill performs deep-scan audits of your local git repositories, identifying areas of high complexity, potential logic leaks, and opportunities for Agent-Native refactoring.
## Features
- **Debt Detection**: Highlights "Dirty Code" that increases cognitive load.
- **Agentic Mapping**: Suggests how to convert traditional modules into autonomous tools.
- **Commit Wisdom**: Summarizes the "Why" behind large architectural shifts in your project.
## Usage
```bash
# Run local git and code analysis commands in the target repository
git log --stat --oneline --decorate --date=short -- .
```
## Codex Notes
Use local repository evidence by default. Do not call external paid services or blockchain/payment endpoints unless the user explicitly requests that integration and confirms credentials, network access, and cost.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
一个全面的 Claude Code 会话验证系统。
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.