write-a-skill

Buat keterampilan agen baru dengan struktur yang tepat, pengungkapan progresif, dan sumber daya yang terpaket. Gunakan saat pengguna ingin membuat, menulis, atau membangun keterampilan baru.

npx skills add https://github.com/sanity-io/sanity --skill write-a-skill

Writing Skills

Process

  1. Gather requirements - ask user about:

    • What task/domain does the skill cover?
    • What specific use cases should it handle?
    • Does it need executable scripts or just instructions?
    • Any reference materials to include?
  2. Draft the skill - create:

    • SKILL.md with concise instructions
    • Additional reference files if content exceeds 500 lines
    • Utility scripts if deterministic operations needed
  3. Review with user - present draft and ask:

    • Does this cover your use cases?
    • Anything missing or unclear?
    • Should any section be more/less detailed?

Skill Structure

skill-name/
├── SKILL.md           # Main instructions (required)
├── REFERENCE.md       # Detailed docs (if needed)
├── EXAMPLES.md        # Usage examples (if needed)
└── scripts/           # Utility scripts (if needed)
    └── helper.js

SKILL.md Template

---
name: skill-name
description: Brief description of capability. Use when [specific triggers].
---

# Skill Name

## Quick start

[Minimal working example]

## Workflows

[Step-by-step processes with checklists for complex tasks]

## Advanced features

[Link to separate files: See [REFERENCE.md](REFERENCE.md)]

Description Requirements

The description is the only thing your agent sees when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.

Goal: Give your agent just enough info to know:

  1. What capability this skill provides
  2. When/why to trigger it (specific keywords, contexts, file types)

Format:

  • Max 1024 chars
  • Write in third person
  • First sentence: what it does
  • Second sentence: "Use when [specific triggers]"

Good example:

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.

Bad example:

Helps with documents.

The bad example gives your agent no way to distinguish this from other document skills.

When to Add Scripts

Add utility scripts when:

  • Operation is deterministic (validation, formatting)
  • Same code would be generated repeatedly
  • Errors need explicit handling

Scripts save tokens and improve reliability vs generated code.

When to Split Files

Split into separate files when:

  • SKILL.md exceeds 100 lines
  • Content has distinct domains (finance vs sales schemas)
  • Advanced features are rarely needed

Review Checklist

After drafting, verify:

  • Description includes triggers ("Use when...")
  • SKILL.md under 100 lines
  • No time-sensitive info
  • Consistent terminology
  • Concrete examples included
  • References one level deep

Lebih banyak skill dari sanity-io

performance-optimization
sanity-io
Mengoptimalkan kinerja aplikasi. Gunakan ketika ada persyaratan kinerja, ketika Anda mencurigai adanya regresi kinerja, atau ketika Core Web Vitals atau waktu muat…
official
rxjs-like-a-pro
sanity-io
Keterampilan ini membantu Anda menulis kode RxJS yang idiomatis, dapat dikomposisikan, dan bebas dari jebakan umum. Filosofi intinya: simpan logika di dalam rantai observable. Setiap kali Anda menggunakan .subscribe(), tanyakan apakah pekerjaan tersebut dapat diekspresikan sebagai transformasi di dalam .pipe().
official
find-skills
sanity-io
Membantu pengguna menemukan dan memasang skill agen saat mereka mengajukan pertanyaan seperti "bagaimana cara melakukan X", "cari skill untuk X", "apakah ada skill yang bisa...", atau menyatakan...
official
next-cache-components
sanity-io
Komponen Cache Next.js 16 - PPR, gunakan arahan cache, cacheLife, cacheTag, updateTag
official
vercel-react-best-practices
sanity-io
Panduan optimasi performa React dan Next.js dari Vercel Engineering. Skill ini harus digunakan saat menulis, meninjau, atau merefaktor kode React/Next.js…
official
frontend-design
sanity-io
Ciptakan antarmuka frontend yang khas dan berkualitas produksi dengan kualitas desain tinggi. Gunakan keterampilan ini ketika pengguna meminta untuk membangun komponen web, halaman, atau…
official
plugin-transfer
sanity-io
Memandu agen dalam memigrasi plugin yang sudah ada ke dalam monorepo ini menggunakan alur kerja generator copy-plugin.
official
test-studio-script-runner
sanity-io
Menjelaskan alat Script Runner dev/test-studio. Gunakan saat menambahkan, mengedit, menjalankan, atau mendokumentasikan skrip di dev/test-studio/src/script-runner, atau ketika…
official