write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

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

More skills from sanity-io

tdd
sanity-io
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants…
performance-optimization
sanity-io
Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times…
content-experimentation-best-practices
sanity-io
Structured guidance for designing, executing, and analyzing content experiments to improve conversion and engagement. Covers hypothesis frameworks, metric selection, sample size calculation, and statistical significance testing across A/B and multivariate experiments Includes detailed resources on p-values, confidence intervals, power analysis, and Bayesian methods for interpreting results Provides CMS integration patterns for managing variants at the field level and connecting external...
content-modeling-best-practices
sanity-io
Structured content modeling guidance for schema design, reusability, and multi-channel delivery. Covers core principles: treating content as data rather than pages, maintaining single sources of truth, designing for future channels, and optimizing for editor workflows Includes decision frameworks for references versus embedded objects, separation of concerns, and content reuse patterns Provides taxonomy and classification guidance for flat, hierarchical, and faceted approaches Applies to...
portable-text-conversion
sanity-io
Convert HTML and Markdown content into Portable Text blocks for Sanity. Use when migrating content from legacy CMSs, importing HTML or Markdown into Sanity,…
portable-text-serialization
sanity-io
Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend…
sanity-best-practices
sanity-io
Comprehensive best practices and integration guides for Sanity CMS development across frameworks and topics. Covers 10+ framework integrations including Next.js, Nuxt, Astro, Remix, SvelteKit, and Angular with framework-specific patterns and setup guidance Includes topic guides for schema design, GROQ query optimization, Visual Editing, Portable Text, images, TypeGen, localization, and content migrations Provides quick-reference structure for loading only relevant guides based on task type,...
sanity-migration
sanity-io
Plans, implements, and reviews migrations from other CMSes and content systems into Sanity. Use when migrating or replatforming to Sanity from AEM, Adobe Experience Manager, Contentful, Strapi, Webflow, WordPress, Payload, Drupal, Markdown/MDX/frontmatter files, WXR/XML exports, CMS APIs, database dumps, static HTML, or when designing extraction, transformation, Portable Text conversion, asset migration, redirects, validation, and cutover workflows.
data-analysisdatabasedevelopment