agentmods.dev

skill-maker

skill-maker is a skill for Claude Code, Codex from Major-Woolfi/Skills_for_AI-Agents. It costs 42 tokens per session (1,098 once invoked), scanned A, original, MIT.

A meta-skill for creating new agent skills: written instructions that guide an agent through a repeatable task.

In plain words
What is it for?
Use it to define a skill’s purpose, write its SKILL.md, follow the agentskills.io format, and test and improve the result.
Why use it?
It gives you a structured way to turn a workflow into a tested, maintainable skill instead of leaving it as informal prompts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 1mo ago A scan 42 tokens original MIT

Good fit Use it to define a skill’s purpose, write its SKILL.md, follow the agentskills.io format, and test and improve the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/major-woolfi/skills_for_ai-agents/skill-maker
View source ↗ Major-Woolfi/Skills_for_AI-Agents
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.

Any agent
npx skills add Major-Woolfi/Skills_for_AI-Agents --skill skill-maker
Clone the repo
git clone --depth 1 https://github.com/Major-Woolfi/Skills_for_AI-Agents

Made for: Claude Code, Codex.

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/skills/major-woolfi/skills_for_ai-agents/skill-maker/github.svg)](https://agentmods.dev/skills/major-woolfi/skills_for_ai-agents/skill-maker)
Your own site
<a href="https://agentmods.dev/skills/major-woolfi/skills_for_ai-agents/skill-maker"><img src="https://agentmods.dev/badge/skills/major-woolfi/skills_for_ai-agents/skill-maker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-maker

Your own site · 80×15
<a href="https://agentmods.dev/skills/major-woolfi/skills_for_ai-agents/skill-maker"><img src="https://agentmods.dev/badge/skills/major-woolfi/skills_for_ai-agents/skill-maker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,098 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 $0.00042 $0.01098
Opus 5.5 $0.00017 $0.00439
Sonnet 5.5 $0.00008 $0.00220
Haiku 4.5 $0.00004 $0.00110

Measured 2mo ago against content hash 2353d48cea38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

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 2mo 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.

SKILLS/skill-maker/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-maker — Создание навыков

Описание

Мета-навык для создания новых навыков агентов, соответствующих открытому стандарту agentskills.io.

Когда активировать

  • Пользователь хочет создать новый навык для агента
  • Есть рабочий процесс, который нужно превратить в навык
  • Нужен черновик, тесты или итерация существующего навыка

Философия

Навык — это не код, а инструкция. Хороший навык объясняет не только «что делать», но и «почему».

Принципы создания навыков

  1. Ясность. Описание должно быть однозначным — ни двусмысленностей, ни расплывчатых формулировок.
  2. Практичность. Навык должен реально работать, а не быть теоретическим упражнением.
  3. Итеративность. Первый черновик почти всегда требует доработки — тестируй и улучшай.
  4. Соответствие стандарту. Следуй спецификации agentskills.io.

Обязательный цикл

Шаг 1: Определение намерений

Начни с понимания целей пользователя. Возможно, в истории чата уже есть рабочий процесс, который нужно превратить в навык. Извлеки из контекста: используемые инструменты, последовательность шагов, исправления пользователя, форматы ввода/вывода.

  1. Что этот навык должен позволить делать Koda?
  2. Когда навык должен срабатывать? (фразы пользователя, контекст).
  3. Какой ожидаемый формат вывода?
  4. Нужно ли настраивать тест-кейсы? Навыки с объективно проверяемым результатом (преобразование файлов, извлечение данных, генерация кода) выигрывают от тестов. Для субъективных навыков (стиль письма, искусство) тесты часто не нужны.

Шаг 2: Интервью и исследование

Проактивно спрашивай о пограничных случаях, форматах, примерах файлов и критериях успеха. Не пиши тесты, пока не прояснишь эти детали.

Проверьте доступные MCP и инструменты — используйте их для поиска документации или лучших практик.

Шаг 3: Написание SKILL.md

Документ должен быть на русском языке.

Заполни frontmatter:

  • name: Идентификатор навыка. Требования: латиница в нижнем kebab-case, 1-64 символов, должно совпадать с именем директории
  • description: Когда срабатывает и что делает. Требования: 1-1024 символов, краткое описание навыка на русском языке. Это основной механизм активации. Пиши описание немного «настойчивым», чтобы Koda не игнорировал навык там, где он полезен.

Read the full file on GitHub · 110 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. 2mo ago First seen · 110 lines · 42 tokens per session scan A 2353d48cea38

Subscribe to this mod's changes

skill-maker is a skill published in the GitHub repository Major-Woolfi/Skills_for_AI-Agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,098 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents
Related

skill-maker compared with skills from other repositories

skill-maker next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skill-makerMajor-Woolfi/Skills_for_AI-AgentsSkill21mo agoMITA42Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code