write-a-skill

Crie novas habilidades de agente com estrutura adequada, divulgação progressiva e recursos agrupados. Use quando o usuário quiser criar, escrever ou construir uma nova habilidade.

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

Mais skills de sanity-io

performance-optimization
sanity-io
Otimiza o desempenho da aplicação. Use quando existirem requisitos de desempenho, quando suspeitar de regressões de desempenho, ou quando os Core Web Vitals ou tempos de carregamento…
official
rxjs-like-a-pro
sanity-io
Esta habilidade ajuda você a escrever código RxJS idiomático, composável e livre de armadilhas comuns. A filosofia central: mantenha a lógica na cadeia observável. Toda vez que você recorrer a .subscribe(), pergunte se o trabalho poderia ser expresso como uma transformação dentro de .pipe().
official
find-skills
sanity-io
Ajuda os usuários a descobrir e instalar skills de agente quando fazem perguntas como "como faço X", "encontre uma skill para X", "existe uma skill que possa...", ou expressam...
official
next-cache-components
sanity-io
Componentes de Cache do Next.js 16 - PPR, diretiva use cache, cacheLife, cacheTag, updateTag
official
vercel-react-best-practices
sanity-io
Diretrizes de otimização de desempenho para React e Next.js da Vercel Engineering. Esta skill deve ser usada ao escrever, revisar ou refatorar React/Next.js…
official
frontend-design
sanity-io
Crie interfaces frontend distintas e de qualidade profissional, com alto padrão de design. Use esta habilidade quando o usuário pedir para construir componentes web, páginas ou…
official
plugin-transfer
sanity-io
Orienta agentes na migração de um plugin existente para este monorepo usando o fluxo de trabalho do gerador copy-plugin.
official
test-studio-script-runner
sanity-io
Explica a ferramenta Script Runner do dev/test-studio. Use ao adicionar, editar, executar ou documentar scripts em dev/test-studio/src/script-runner, ou quando o…
official