skill-create

skill-create is a command for Claude Code from raja21068/AutoResearch. It costs 6 tokens per session (536 once invoked), scanned A, a copy of skill-create, MIT.

A command that examines a project's Git commit history—the record of code changes—to identify recurring practices and generate skill documentation.

In plain words
What is it for?
Use it to study commit messages, file structures, coding patterns, review feedback, and recurring fixes, then create a SKILL.md file and learning notes.
Why use it?
It turns patterns buried in past commits into written guidance, so project conventions are easier to reuse and teach.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: agent in frontmatter; mentions Claude Code.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/raja21068/autoresearch/skill-create
Clone the repo
git clone --depth 1 https://github.com/raja21068/AutoResearch

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/raja21068/autoresearch/skill-create.svg)](https://agentmods.dev/commands/raja21068/autoresearch/skill-create)
Your own site
<a href="https://agentmods.dev/commands/raja21068/autoresearch/skill-create"><img src="https://agentmods.dev/badge/commands/raja21068/autoresearch/skill-create.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00006 $0.00536
Opus 5 $0.00003 $0.00268
Sonnet 5 $0.00001 $0.00107
Haiku 4.5 $0.00001 $0.00054

Measured 2d ago against content hash 0603e3735ea7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

92% identical to skill-create — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/commands/skill-create.md · 118 lines

What it actually says

Skill Create Command

Analyze git history to generate Claude Code skills: $ARGUMENTS

Your Task

  1. Analyze commits - Pattern recognition from history
  2. Extract patterns - Common practices and conventions
  3. Generate SKILL.md - Structured skill documentation
  4. Create instincts - For continuous-learning-v2

Analysis Process

Step 1: Gather Commit Data

# Recent commits
git log --oneline -100

# Commits by file type
git log --name-only --pretty=format: | sort | uniq -c | sort -rn

# Most changed files
git log --pretty=format: --name-only | sort | uniq -c | sort -rn | head -20

Step 2: Identify Patterns

Commit Message Patterns:

  • Common prefixes (feat, fix, refactor)
  • Naming conventions
  • Co-author patterns

Code Patterns:

  • File structure conventions
  • Import organization
  • Error handling approaches

Review Patterns:

  • Common review feedback
  • Recurring fix types
  • Quality gates

Step 3: Generate SKILL.md

# [Skill Name]

## Overview
[What this skill teaches]

## Patterns

### Pattern 1: [Name]
- When to use
- Implementation
- Example

### Pattern 2: [Name]
- When to use
- Implementation
- Example

## Best Practices

1. [Practice 1]
2. [Practice 2]
3. [Practice 3]

## Common Mistakes

1. [Mistake 1] - How to avoid
2. [Mistake 2] - How to avoid

## Examples

### Good Example
```[language]
// Code example

Anti-pattern

// What not to do

### Step 4: Generate Instincts

For continuous-learning-v2:

```json
{
  "instincts": [
    {
      "trigger": "[situation]",
      "action": "[response]",
      "confidence": 0.8,
      "source": "git-history-analysis"
    }
  ]
}

Output

Creates:

  • skills/[name]/SKILL.md - Skill documentation
  • skills/[name]/instincts.json - Instinct collection

TIP: Run /skill-create --instincts to also generate instincts for continuous learning.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 118 lines · 6 tokens per session scan A 0603e3735ea7

Subscribe to this mod's changes

skill-create is a command published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 536 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to skill-create, differing in 2 lines, and is treated as a copy.