skill-maker

skill-maker is a plugin for Claude Code from adamjali/claude-skills. Its manifest loads nothing; the 1 skill it bundles cost 170 tokens per session together, scanned A, original, MIT.

A scaffolding tool for creating Claude Code skills or slash commands in a consistent format, with structured phases, saved rules, checkpoints, and validation.

In plain words
What is it for?
Use it to gather requirements, generate the skill or command structure, validate the result, and support resuming interrupted work.
Why use it?
It provides a repeatable structure for creating these reusable coding-agent instructions instead of designing the workflow from scratch.

Plugin for 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.

Claude Code
/plugin marketplace add adamjali/claude-skills
agentmods
npx agentmods add plugins/adamjali/claude-skills/skill-maker
Clone the repo
git clone --depth 1 https://github.com/adamjali/claude-skills

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-maker

README.md
[![agentmods](https://agentmods.dev/badge/plugins/adamjali/claude-skills/skill-maker.svg)](https://agentmods.dev/plugins/adamjali/claude-skills/skill-maker)
Your own site
<a href="https://agentmods.dev/plugins/adamjali/claude-skills/skill-maker"><img src="https://agentmods.dev/badge/plugins/adamjali/claude-skills/skill-maker.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 170 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

skill-maker 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 3d 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.

plugins/skill-maker/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "skill-maker",
  "description": "Create new Claude Code skills or slash-commands in a clean, consistent house style — XML phases, state files, saved rules, checkpoint resumption, and 14 compaction patterns. Structured intake -> generate -> validate.",
  "version": "0.1.0",
  "author": { "name": "adamjali", "url": "https://github.com/adamjali" },
  "homepage": "https://github.com/adamjali/claude-skills",
  "license": "MIT",
  "keywords": ["skills", "skill-creator", "claude-code", "scaffolding", "meta"]
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 170 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 3d ago First seen · 10 lines scan A 2de171a4455c

Subscribe to this mod's changes

skill-maker is a plugin published in the GitHub repository adamjali/claude-skills (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.