write-a-skill

Crear nuevas habilidades de agente con estructura adecuada, divulgación progresiva y recursos empaquetados. Úsalo cuando el usuario quiera crear, escribir o construir una nueva habilidad.

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

Más skills de sanity-io

performance-optimization
sanity-io
Optimiza el rendimiento de la aplicación. Úsalo cuando existan requisitos de rendimiento, cuando sospeches regresiones de rendimiento, o cuando Core Web Vitals o los tiempos de carga…
official
rxjs-like-a-pro
sanity-io
Esta habilidad te ayuda a escribir código RxJS que sea idiomático, componible y libre de errores comunes. La filosofía central: mantén la lógica dentro de la cadena de observables. Cada vez que recurras a .subscribe(), pregúntate si el trabajo podría expresarse como una transformación dentro de .pipe().
official
find-skills
sanity-io
Ayuda a los usuarios a descubrir e instalar habilidades de agente cuando hacen preguntas como "¿cómo hago X?", "encuentra una habilidad para X", "¿hay una habilidad que pueda...", o expresan…
official
next-cache-components
sanity-io
Componentes de caché de Next.js 16 - PPR, directiva use cache, cacheLife, cacheTag, updateTag
official
vercel-react-best-practices
sanity-io
Directrices de optimización de rendimiento de React y Next.js de Vercel Engineering. Esta habilidad debe usarse al escribir, revisar o refactorizar React/Next.js…
official
frontend-design
sanity-io
Crear interfaces frontend distintivas y de calidad de producción con un alto nivel de diseño. Usa esta habilidad cuando el usuario solicite construir componentes web, páginas o…
official
plugin-transfer
sanity-io
Guía a los agentes en la migración de un plugin existente a este monorepo mediante el flujo de trabajo del generador copy-plugin.
official
test-studio-script-runner
sanity-io
Explica la herramienta Script Runner de dev/test-studio. Úsala al agregar, editar, ejecutar o documentar scripts en dev/test-studio/src/script-runner, o cuando el…
official