agentsclimarketplace

Functions do

Skill dot-do/skills/functions-do

.do Agent Skills — reusable, composable skill modules

Install
npx -y skills add dot-do/skills --skill functions-do

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Expert guidance for ai-functions and functions.do — type-safe AI function invocation, schema generation, template literals, and provider routing.

SKILL.md

1.9 KB, 461 tokens by cl100k_base, as published. Nobody here has run it

functions.do

You are an expert in ai-functions and functions.do.

When to Use

Activate this skill when the user is working with ai-functions, functions.do, AI() factory, typed AI schemas, or template literal prompts.

Three Invocation Styles

import { ai, AI, list } from 'ai-functions'

// 1. Ad-hoc template literal
const summary = await ai`Summarize: ${article}`

// 2. Typed factory with schema
const myAI = AI({
  classifyIntent: {
    category: 'string',
    confidence: 'number',
    reasoning: 'string',
  }
})
const result = await myAI.classifyIntent({ text: userMessage })

// 3. List generation
for await (const item of list`List 10 use cases for ${topic}`) {
  console.log(item)
}

Schema Design

const contentAI = AI({
  generateBlogPost: {
    title: 'string',
    slug: 'string',
    sections: ['string'],        // array
    tags: ['string'],
    sentiment: 'positive | neutral | negative',  // union
    readingTimeMinutes: 'number',
  }
})

Built-in Domain Functions

extract · is · say · research · scrape · code · mdx · plan · scope · workflow · ui · image · markdown

Configuration

const result = await myAI.generate({
  topic: 'AI agents',
  model: 'claude-sonnet-4-6',
  temperature: 0.7,
  maxTokens: 2000,
  system: 'You are a technical writer...',
})

Best Practices

  • Group related functions into a single AI() instance per domain
  • Use list() for streaming UX, AI() for structured data, ai\`` for one-offs
  • Narrow types with union strings: 'draft | published | archived'
  • Test with evaluate-do skill before production

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.