Skill Create
SkillFiles & storageskill-create is a skill that analyzes local git history to extract coding patterns and generate SKILL.md files. It helps you turn your team's actual practices into reusable instructions for an AI agent. The result is a set of skill files that describe how your team writes code, based on what is already in the repository.
Use Skill Create in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Skill Create and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Skill Create
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Have a local git repository with commit history you want to analyze.
What your AI can do with it
- Analyze local git history to find recurring coding patterns
- Generate SKILL.md files that describe team practices
- Extract patterns from commits and diffs in the repository
- Produce skill files that can be used by an AI agent
Getting started
- Have a local git repository with commit history you want to analyze.
- Make sure the skill-create skill is available to your AI agent.
- Ask the agent to run skill-create on the repository.
- Review the generated SKILL.md files and adjust them as needed.
What this skill tells your AI
The instructions your AI receives, as published by luohaothu/everything-codex in skills/skill-create/SKILL.md and read by Ahel’s review.
Analyze your repository's git history to extract coding patterns and generate SKILL.md files.
Usage
/skill-create # Analyze current repo
/skill-create --commits 100 # Analyze last 100 commits
/skill-create --output ./skills # Custom output directory
Analysis Steps
Step 1: Gather Git Data
# Get recent commits with file changes
git log --oneline -n 200 --name-only --pretty=format:"%H|%s|%ad" --date=short
# Get commit frequency by file
git log --oneline -n 200 --name-only | sort | uniq -c | sort -rn | head -20
# Get commit message patterns
git log --oneline -n 200 | cut -d' ' -f2- | head -50
Step 2: Detect Patterns
| Pattern | Detection Method |
|---|---|
| Commit conventions | Regex on commit messages |
| File co-changes | Files that always change together |
| Workflow sequences | Repeated file change patterns |
| Architecture | Folder structure and naming conventions |
| Testing patterns | Test file locations, naming, coverage |
Step 3: Generate SKILL.md
---
name: <repo-name>-patterns
description: Coding patterns extracted from <repo-name>
---
# <Repo Name> Patterns
## Commit Conventions
<detected patterns>
## Code Architecture
<detected structure>
## Workflows
<detected file change patterns>
## Testing Patterns
<detected test conventions>
Process
- Ask user to confirm before saving
- Generate SKILL.md to specified output directory
- Report patterns found and confidence levels
Signals
- GitHub stars
- 25
- Forks
- 5
- Last commit
- Aug 2026
Questions
- What kind of files does it generate?
- It generates SKILL.md files that capture coding patterns from your git history.
- Does it work with remote repositories?
- It analyzes local git history, so the repository must be available locally.
- What do I need before using it?
- You need a local git repository with commit history and access to the skill-create skill through your AI agent.
- Can I edit the generated skill files?
- Yes, the generated SKILL.md files can be reviewed and adjusted as needed.
Advanced
- Item type
- skill
- Key
skill-create- Source
- github.com/luohaothu/everything-codex
github.com/luohaothu/everything-codex