skill-create

skill-create is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 0 tokens per session (992 once invoked), scanned A, original, MIT.

A command that studies recent Git history and generates a new skill file from repeated patterns in the project's changes.

In plain words
What is it for?
Use it when the repository contains several similar commits and you want to turn their shared process into a documented skill.
Why use it?
It helps capture recurring implementation or debugging workflows so they can be reused later.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Use it when the repository contains several similar commits and you want to turn their shared process into a documented skill.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kumaran-is/claude-code-onboarding/skill-create
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.

Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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/kumaran-is/claude-code-onboarding/skill-create.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/skill-create)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/skill-create"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/skill-create.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00000 $0.00992
Opus 5 $0.00000 $0.00496
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 4d ago against content hash f6e827bfcfc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 4d 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.

.claude/commands/skill-create.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/skill-create — Generate a New Skill from Git History

Analyzes git log to detect patterns, then generates a new skill file that matches the workspace's writing-skills spec.

When to Use

  • You've noticed a repeated workflow not yet captured in a skill
  • A pattern has emerged from 3+ similar commits
  • You want to codify a debugging or implementation technique

Process

Step 1: Analyze git history

git log --oneline -n 200 --name-only | head -300

Detect:

  • Commit conventions — what prefixes appear? (feat:, fix:, refactor:)
  • File co-changes — which files always change together? (signals a workflow)
  • Workflow sequences — do commits follow a pattern? (e.g., schema → service → controller → test)
  • Architecture patterns — which directories are touched most often?

Step 2: Identify the pattern

State the pattern in one sentence:

"Every time we add a NestJS endpoint, we touch: DTO → service → controller → e2e test, in that order."

If no clear pattern emerges from 200 commits, report: "No repeated pattern detected. Provide a manual description of the skill you want to create."

Step 3: Generate the skill

Output a complete skill file matching the writing-skills spec:

Required frontmatter fields:

---
name: {skill-name}
description: {CSO trigger words — "Use when...", specific scenario, not vague}
allowed-tools: {minimal set — only what the skill needs}
metadata:
  triggers: {comma-separated trigger words}
  related-skills: {comma-separated related skill names}
  domain: {backend|frontend|mobile|infrastructure|quality|architecture}
  role: {specialist|reviewer|generator}
  scope: {implementation|review|design|testing}
  output-format: {code|report|plan}
last-reviewed: "{YYYY-MM-DD}"
---

Required body sections (in this order):

  1. **Iron Law:** — one mandatory rule, no exceptions
  2. Summary — 2-3 sentences on what this skill does
  3. Process — numbered steps
  4. Key patterns — code examples
  5. Anti-patterns — at least 1 explicit "don't do this"
  6. Error handling — what to do when things go wrong
  7. References section — links to related files

Read the full file on GitHub · 117 lines

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. 4d ago First seen · 117 lines · 0 tokens per session scan A f6e827bfcfc1

Subscribe to this mod's changes

skill-create is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 992 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.