Agentprivacy wiki skill anatomy

Skill mitchuski/agentprivacy-skills/agentprivacy-skills-v5/wikis/agentprivacy-wiki-skill-anatomy

What a Claude Code skill is — the SKILL.md folder format, frontmatter, storage location, and how skills are invoked (auto via description, or explicitly via /skill-name). Activates when explaining skills to a newcomer, authoring a new skill, or onboarding an agent into the skill model. The conceptual entry to the Librarian's 🗃️ Wikis.From its SKILL.md

Install

npx -y skills add mitchuski/agentprivacy-skills --skill agentprivacy-wiki-skill-anatomy

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.9 KB, 477 tokens by cl100k_base, as published. Nobody here has run it

Claude Skills

Claude Code skills are markdown files that teach Claude how to perform specific tasks — reusable, invocable instructions that extend Claude's behaviour without modifying its core settings.

What is a Skill?

A skill is a folder containing a SKILL.md file. The frontmatter declares the skill's name and description. The body contains instructions, examples, patterns and checklists that Claude follows when the skill is invoked.

Where Skills are Stored

Skills live in ~/.claude/skills/. Each skill is a named subfolder:

~/.claude/skills/
    fedwiki-page/
        SKILL.md
    another-skill/
        SKILL.md
        references/
        assets/
        scripts/

Skill Structure

A minimal SKILL.md looks like this:

---
name: my-skill
description: What this skill does and when to trigger it.
---

# Instructions

Step by step guidance for Claude...

The description field is the primary triggering mechanism — Claude reads it to decide whether to use the skill for a given request. A good description is specific about both what the skill does and when it should trigger.

Invoking a Skill

Skills can be invoked in two ways:

Automatically — Claude reads the description and decides the skill applies to the current request
Explicitly — by typing /skill-name in the prompt

Creating a Skill

Create a new folder under ~/.claude/skills/ and write a SKILL.md file inside it. The /skill-creator skill can help design, test and optimise new skills iteratively with evals.

The fedwiki-page skill on this wiki is an example — it captures the patterns for creating fedwiki page JSON files and is stored at ~/.claude/skills/fedwiki-page/SKILL.md.

Verify: agentprivacy.ai · kept by the Librarian 🗃️ in the Tower's Wikis (the git-less onboarding layer) Upstream: skill.fedwiki.club/claude-skills — vendored + re-framed; not original agentprivacy authorship

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.