ワンクリックで
using-agent-skills
Discover and compose skills from this framework to guide your work
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Discover and compose skills from this framework to guide your work
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Build UIs that work for all users including keyboard navigation, screen readers, and WCAG 2.2
Design multi-agent systems with robust tool interfaces, state management, and failure handling
Build ML systems with disciplined training, evaluation, deployment, and safety practices
Design APIs that are stable, ergonomic, and evolvable
Design systems at the right scale with explicit trade-off documentation
Design services that are reliable, observable, secure, and maintainable
| name | using-agent-skills |
| description | Discover and compose skills from this framework to guide your work |
| difficulty | junior |
| domains | ["general"] |
This meta-skill teaches you how to use the AI Agent Skills framework. Load it first in any new session.
Load this skill at the start of every session when working in a project that has this framework installed.
Map what you're about to do to one of the 8 core commands:
/spec/plan/build/test/review/simplify/ship/incidentRead the skill file for your task: skills/<name>/SKILL.md
Check AGENTS.md for the skill composition table. Load supporting skills if they apply.
If working in a specific domain (AI/ML, data, frontend), load the matching pack from packs/.
Follow each step in the skill. Do not skip steps. At each checkpoint, produce evidence.
"The task is simple enough that I don't need a skill" Simple tasks still benefit from structured thinking. The overhead of loading a skill is seconds; the cost of a missed step can be days.
"I already know how to do this" Skills encode accumulated engineering wisdom beyond what any individual knows. They also prevent bad days from becoming bad commits.