Official agent skill

Apify Integration Development

by apify in apify/agent-skills

Guides designing and building an official Apify integration for a company's product: workflow-automation apps, AI agent plugins, AI framework packages or direct API clients.

OfficialNo licenceAuto-check passedBackend & APIs

Install Apify Integration Development

skills CLI
$ npx skills add apify/agent-skills --skill apify-integration-development -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install apify/agent-skills apify-integration-development --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/apify/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/apify-integration-development .claude/skills/apify-integration-development && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
apify-integration-development
GitHub stars
2.4k
Token cost
~3.1k tokens
SKILL.md length
1,548 words
Files
5 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
None found

At a glance

Guides designing and building an official Apify integration for a company's product: workflow-automation apps, AI agent plugins, AI framework packages or direct API clients.

  • Works in 6 steps: Retrying POST /runs on a network error -… → Unbounded while (true) polling - ties up… → Putting maxTotalChargeUsd / maxItems… → …
  • Planning an official Apify integration for your product
  • SKILL.md covers Step 0 - Learn the Apify model…, Use Apify MCP for live context…, Pick your integration shape and Cross-cutting design rules…, plus 4 more sections
  • Reaches apify.com and docs.apify.com; needs APIFY_TOKEN

What it does

The skill helps a partner team ship an official Apify integration end to end, whichever shape fits its product: a workflow-automation app of the Zapier or n8n kind, an AI agent plugin, an AI framework package like those for LangChain or LlamaIndex, or a direct application client built on apify-client. Cross-cutting rules apply to all of them, and one category-specific reference file (workflow automation, AI harness plugin, AI framework package or SDK integration) carries the rest.

Step 0 is required: read apify.com/agents.md, the canonical quickstart, before designing anything, with a mini-glossary as backup. The glossary covers Actors, Actor Runs (each with its own dataset, key-value store and request queue), Datasets, Key-Value Stores, Actor Tasks, the Apify Store, Apify Console and the Compute Unit billing measure. The skill also recommends the Apify MCP server for researching Actors, schemas, pricing and docs while planning.

Once an integration is published, the skill says to contact the Apify integrations team so it can review capability surface, cost controls, error handling and attribution headers before users get it.

When your agent uses it

  • Planning an official Apify integration for your product
  • Building a Zapier- or n8n-style app that exposes Apify Actors
  • Reviewing an integration that runs Actors and reads datasets
  • Creating a LangChain or LlamaIndex package that calls Apify

Example prompts

  • “Plan an Apify integration for our CRM so users can run Actors from a workflow step.”
  • “Review this Apify plugin for a coding agent and check how it handles run costs.”
  • “Design a LlamaIndex reader that loads results from an Apify dataset.”

Requirements

  • Network access to fetch apify.com/agents.md
  • The Apify MCP server, if available, for live Actor and docs lookups

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Retrying POST /runs on a network error - duplicates a billed run.
  2. Unbounded while (true) polling - ties up the host with no ceiling.
  3. Putting maxTotalChargeUsd / maxItems inside Actor input instead of options - silently not a cap.
  4. Dumping a full dataset into an LLM context without size caps or untrusted-content fencing - prompt-injection and context blowout.
  5. One monolithic tool list for an LLM agent - routing accuracy degrades past ~8 tools; curate subsets.
  6. Surfacing a raw HTTP status/message instead of Apify's actual error text - users can't act on "400".

What it can do on your machine

Read from SKILL.md and the folder at commit f5e84aa. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • apify.com
    • docs.apify.com
    • console.apify.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • APIFY_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Apify Integration Development loads about 3.1k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 1,548 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,548 words (~3,080 tokens).

“Design and build an official Apify integration for a company's product, with minimal help from Apify. This skill covers every integration shape Apify supports - workflow-automation apps, AI agent plugins (coding agents and harnesses), AI framework packages, and direct application…”

— opening of SKILL.md by apify
name
apify-integration-development

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (references) in skills/apify-integration-development of apify/agent-skills.

  • SKILL.md
  • references/ai-framework-package.md
  • references/ai-harness-plugin.md
  • references/sdk-integration.md
  • references/workflow-automation.md

Open the folder on GitHubat commit f5e84aa

Compare with similar skills

Apify Integration Development next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Apify Integration Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Apify Integration Development this skillapify/agent-skills2.4k—~3.1kAutomated safety check: PassNone
Makeericrisco/rsc-harness156—~3.1kAutomated safety check: NotesMIT
N8nericrisco/rsc-harness156—~2.6kAutomated safety check: NotesMIT
Zapierericrisco/rsc-harness156—~2.8kAutomated safety check: NotesMIT
Apify Product Data Setupapify/awesome-skills2621 repos~2kAutomated safety check: PassApache-2.0
AI Automation BuilderFerroxLabs/wayland608—~4kAutomated safety check: PassApache-2.0

Similar skills

  • Make

    ericrisco/rsc-harness

    A skill your agent uses when operating Make.com (formerly Integromat) programmatically — driving its REST API v2 or the Make MCP server from code or an agent to create, read, update, activate, run…

    156 GitHub stars~3.1k tokensUpdated today
    Backend & APIsAuto-check: notes
  • N8n

    ericrisco/rsc-harness

    A skill your agent uses when operating a live n8n instance programmatically — its REST API ({host}/api/v1, X-N8N-API-KEY) or the n8n-mcp server — to create, validate, test, activate, update, delete…

    156 GitHub stars~2.6k tokensUpdated today
    Productivity & AutomationAuto-check: notes
  • Zapier

    ericrisco/rsc-harness

    A skill your agent uses when operating Zapier from an agent through the official hosted Zapier MCP server — connecting with a bearer key, discovering an app's actions, enabling one, and invoking a…

    156 GitHub stars~2.8k tokensUpdated today
    Productivity & AutomationAuto-check: notes
  • Apify Product Data Setup

    apify/awesome-skills

    Official

    Wire an AI agent to live e-commerce product data using Apify's E-commerce Scraping Tool over MCP, either as runtime tool calls or as a scheduled refresh into a vector store.

    262 GitHub starsUsed in 1 repo~2k tokens
    Data & AnalyticsAuto-check passed
  • AI Automation Builder

    FerroxLabs/wayland

    Comprehensive guide to building AI-powered automation workflows using n8n, Zapier, Make, and custom agent frameworks covering integration patterns, cost optimization, error handling, and…

    608 GitHub stars~4k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • n8n Custom Code Tool Guide

    czlonkowski/n8n-skills

    Explains the n8n Custom Code Tool's actual runtime contract so an AI-agent-callable tool doesn't get written like a regular workflow Code node.

    6.4k GitHub stars~4k tokensUpdated 21 days ago
    Productivity & AutomationAuto-check passed

More from apify/agent-skills

  • Apify Actor Development

    apify/agent-skills

    Official

    Creates, changes, debugs and deploys Apify Actors, including their input and output schemas, using the Apify CLI.

    2.4k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Official

    Scrapes public data from social, maps, search and review platforms by choosing from about a hundred Apify Actors and running them through the Apify CLI.

    2.4k GitHub starsUsed in 2 repos~1.4k tokens
    Auto-check: notes
  • Official

    Deprecated. An agent skill from apify/agent-skills.

    2.4k GitHub stars~309 tokensUpdated today
    Auto-check passed

Questions about Apify Integration Development

What does Apify Integration Development do?

Guides designing and building an official Apify integration for a company's product: workflow-automation apps, AI agent plugins, AI framework packages or direct API clients. The skill helps a partner team ship an official Apify integration end to end, whichever shape fits its product: a workflow-automation app of the Zapier or n8n kind, an AI agent plugin, an AI framework package like those for LangChain or LlamaIndex, or a direct application client built on apify-client. Cross-cutting rules apply to all of them, and one category-specific reference file (workflow automation, AI harness plugin, AI framework package or SDK integration) carries the rest.

When should I use Apify Integration Development?

Apify Integration Development fits situations like: planning an official Apify integration for your product; building a Zapier- or n8n-style app that exposes Apify Actors; reviewing an integration that runs Actors and reads datasets; creating a LangChain or LlamaIndex package that calls Apify.

How do I install Apify Integration Development in Claude Code?

Run `npx skills add apify/agent-skills --skill apify-integration-development -a claude-code`. Or copy the skill folder (skills/apify-integration-development in apify/agent-skills) into .claude/skills/apify-integration-development in your project. Claude Code loads it when a task matches its description.

How do I install Apify Integration Development in Codex?

Run `npx skills add apify/agent-skills --skill apify-integration-development -a codex`. Or copy the skill folder (skills/apify-integration-development in apify/agent-skills) into .agents/skills/apify-integration-development in your project. Codex loads it when a task matches its description.

Can I use Apify Integration Development in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add apify/agent-skills --skill apify-integration-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/apify-integration-development, .gemini/skills/apify-integration-development, .github/skills/apify-integration-development and .opencode/skills/apify-integration-development in your project.

What does Apify Integration Development need to run?

Going by SKILL.md and its folder, Apify Integration Development needs credentials named APIFY_TOKEN. Our summary lists: Network access to fetch apify.com/agents.md; The Apify MCP server, if available, for live Actor and docs lookups.

Does Apify Integration Development access the network?

SKILL.md names 3 domains. In commands or code: apify.com, docs.apify.com and console.apify.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Apify Integration Development safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Apify Integration Development use?

No licence was found for Apify Integration Development or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Apify Integration Development use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Apify Integration Development?

Skills that share tags, products or a category with Apify Integration Development: Make (ericrisco/rsc-harness, 156 stars), N8n (ericrisco/rsc-harness, 156 stars), Zapier (ericrisco/rsc-harness, 156 stars) and Apify Product Data Setup (apify/awesome-skills, 262 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Apify Integration Development?

apify (a GitHub organization, an official publisher) maintains it in apify/agent-skills, which has 2,408 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 6, 2026.

Source: apify/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.