# apply-anthropic-skill-best-practices

A skill that walks you through Anthropic's official skill-authoring rules while you build your own. Useful once a skill file grows past a few screens.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 1787
- Author: NeoLabHQ
- License: GPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/apply-anthropic-skill-best-practices/SKILL.md
- Updated: 2026-08-26
- HTML: https://affpapa.org/en/nevibecode/skills/apply-anthropic-skill-best-practices

## What it does

This skill takes Anthropic's authoring guidance and applies it to whatever skill you are writing. It covers the two frontmatter fields, `name` (up to 64 characters) and `description` (up to 1024), and insists the description states both the action and the trigger. Write it in third person — the text is injected into the system prompt, and the wrong point of view breaks discovery.

Structure comes next. Keep the `SKILL.md` body under 500 lines and move material into separate files as you approach that. Name skills with a gerund: “Processing PDFs”, not “Helper”. At startup only the metadata loads; the body is read when the skill becomes relevant, so every extra token in it competes with the conversation.

Test on each model you expect to use. Guidance that is enough for a strong reasoning model may leave a smaller one without enough to go on. Install with `npx skills add NeoLabHQ/context-engineering-kit --skill apply-anthropic-skill-best-practices -a claude-code`; the file lands at `~/.claude/skills/apply-anthropic-skill-best-practices/SKILL.md`. If that path is empty afterwards, the skill will not fire — check it.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill apply-anthropic-skill-best-practices -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/apply-anthropic-skill-best-practices/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/apply-anthropic-skill-best-practices/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill apply-anthropic-skill-best-practices -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/apply-anthropic-skill-best-practices/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill apply-anthropic-skill-best-practices -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/apply-anthropic-skill-best-practices/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NeoLabHQ/context-engineering-kit apply-anthropic-skill-best-practices
```

2. **Manually: put the files in place**
- File: `.github/skills/apply-anthropic-skill-best-practices/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill apply-anthropic-skill-best-practices -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/apply-anthropic-skill-best-practices
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/apply-anthropic-skill-best-practices/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill apply-anthropic-skill-best-practices -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/apply-anthropic-skill-best-practices/SKILL.md

## When to use it
- write a `description` that gets the right skill selected
- split an oversized `SKILL.md` into linked files
- pick consistent names across a skill collection
- check a skill against both small and large models

## Example prompts
- Review my `SKILL.md` against Anthropic's authoring rules and fix the description
- This skill body is over 500 lines — propose which parts to move into separate files
- Suggest a name and `description` for a skill that cleans up log files

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [neolabhq/context-engineering-kit](https://affpapa.org/en/nevibecode/by/neolabhq/context-engineering-kit.md) — 64 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md