Official agent skill

Apify Actor Development

by apify in apify/agent-skills

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

OfficialNo licenceAuto-check passedData & Analytics

Install Apify Actor Development

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

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

GitHub CLI
$ gh skill install apify/agent-skills apify-actor-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-actor-development .claude/skills/apify-actor-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-actor-development
GitHub stars
2.4k
Token cost
~2.9k tokens
SKILL.md length
1,238 words
Files
7 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
None found

At a glance

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

  • Works in 9 steps: Create the project. → Add dependencies the template lacks,… → Implement in src/main.js, src/main.ts,… → …
  • Building a new Apify Actor from scratch
  • SKILL.md covers Setup, Workflow, Rules and Standby mode, plus 4 more sections
  • Calls npm, git and brew; reaches mcp.apify.com; needs APIFY_TOKEN and APIFY_API_TOKEN

What it does

An Actor is a serverless program packaged as a Docker image that takes one JSON input, does one job and writes results to a dataset or key-value store. The skill checks that the `apify` CLI is installed and logged in, recommends installing through npm or Homebrew, and logs in with `apify login` or an `APIFY_TOKEN` environment variable, keeping the token out of shell history, source and logs.

The workflow begins by creating a project from a template chosen by what the Actor does: static HTML crawling, JavaScript-rendered crawling with Playwright, HTTP serving in standby mode, an MCP server, or an empty project, each in TypeScript, JavaScript or Python where available. Every `apify` command carries a `--user-agent` flag that tags the call for telemetry attribution. Reference files cover `actor.json`, the Actor README, input schema, logging, output schemas and standby mode, and wrapping an existing non-Actor project is left to the apify-actorization skill.

When your agent uses it

  • Building a new Apify Actor from scratch
  • Debugging or changing the code of an existing Actor
  • Writing or updating `.actor` input and output schema files
  • Pushing an Actor to the Apify platform

Example prompts

  • “Create an Apify Actor that crawls product pages and saves titles and prices to a dataset.”
  • “Write the input schema for my Actor so it accepts a list of start URLs and a maximum page count.”
  • “My Actor fails on JavaScript-rendered pages, help me debug it and push the fix.”

Requirements

  • The Apify CLI (`apify-cli`), installed with npm or Homebrew
  • An Apify account, logged in with `apify login` or an `APIFY_TOKEN`

Workflow steps

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

  1. Create the project.
  2. Add dependencies the template lacks, such as Crawlee or Playwright: npm install in JS/TS; in Python, a line in requirements.txt followed…
  3. Implement in src/main.js, src/main.ts, or my_actor/main.py (Python templates are a my_actor package run as python -m my_actor), following…
  4. Write the input schema in .actor/input_schema.json (see references/input-schema.md). Done when every input the code reads has a field with…
  5. Write the output schemas: dataset_schema.json, output_schema.json, and key_value_store_schema.json when the code stores files. Follow…
  6. Configure .actor/actor.json (see references/actor-json.md). Set meta.generatedBy to the tool and model in use, for example "Claude Code…
  7. Write README.md following references/actor-readme.md. An Actor without a README is not finished.
  8. Test locally. Put input in storage/key_value_stores/default/INPUT.json, then run apify run --user-agent…
  9. Deploy with apify push --user-agent apify-agent-skills/apify-actor-development once the user confirms, or git push for a Git-sourced…

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

    Shell commands in SKILL.md call:

    • npm
    • git
    • brew
    • pip
    • uv
    • python
    • node
    • npx

    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:

    • mcp.apify.com

    Also links to:

    • docs.apify.com
    • crawlee.dev
    • console.apify.com
    • raw.githubusercontent.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
    • APIFY_API_TOKEN

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

Context cost

Apify Actor Development loads about 2.9k tokens when it runs, and up to ~9.8k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 1,238 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.8k

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 1,238 words (~2,912 tokens).

“An Actor is a serverless program packaged as a Docker image. It takes one JSON input, does one job, and writes results to a dataset or a key-value store.”

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

Read the full SKILL.md on GitHub

Files

SKILL.md and 6 other files (references) in skills/apify-actor-development of apify/agent-skills.

  • SKILL.md
  • references/actor-json.md
  • references/actor-readme.md
  • references/input-schema.md
  • references/logging.md
  • references/output-schemas.md
  • references/standby-mode.md

Open the folder on GitHubat commit f5e84aa

Compare with similar skills

Apify Actor 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 Actor Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Apify Actor Development this skillapify/agent-skills2.4k—~2.9kAutomated safety check: PassNone
Scraper Builderjwynia/agent-skills165—~4kAutomated safety check: PassMIT
Apify Actorizationsickn33/agentic-awesome-skills47k2 repos~1.7kAutomated safety check: PassMIT
CrawleeLeoYeAI/openclaw-master-skills2.2k—~4.7kAutomated safety check: PassMIT
Upgrading Mwaa Environmentsaws/agent-toolkit-for-aws2.8k—~7.3kAutomated safety check: PassApache-2.0
Firecrawl Page Scrape Integrationfirecrawl/firecrawl189k1 repos~944Automated safety check: PassISC

Similar skills

  • Scraper Builder

    jwynia/agent-skills

    Guide AI agents to generate complete PageObject pattern web scraper projects using Playwright and TypeScript with Docker deployment.

    165 GitHub stars~4k tokensUpdated 7 mo ago
    Data & AnalyticsAuto-check passed
  • Apify Actorization

    sickn33/agentic-awesome-skills

    Actorization converts existing software into reusable serverless applications compatible with the Apify platform.

    47k GitHub starsUsed in 2 repos~1.7k tokens
    Data & AnalyticsAuto-check passed
  • Crawlee

    LeoYeAI/openclaw-master-skills

    Expert guide for building web scrapers and crawlers using Crawlee (JavaScript/TypeScript and Python).

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Data & AnalyticsAuto-check passed
  • Upgrading Mwaa Environments

    aws/agent-toolkit-for-aws

    Official

    Upgrades an MWAA environment to a newer Airflow version — within 2.x, within 3.x, or across the 2.x-to-3.x boundary.

    2.8k GitHub stars~7.3k tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Adds Firecrawl's /scrape endpoint to application code to pull markdown, HTML, links, screenshots or structured data from a single known URL.

    189k GitHub starsUsed in 1 repo~944 tokens
    Data & AnalyticsAuto-check passed
  • Guides adding Firecrawl's /interact endpoint to product code for pages that need clicks, forms, pagination or logged-in flows beyond plain scraping.

    189k GitHub starsUsed in 1 repo~731 tokens
    Data & AnalyticsAuto-check passed

More from apify/agent-skills

  • 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

    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.

    2.4k GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Official

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

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

Questions about Apify Actor Development

What does Apify Actor Development do?

Creates, changes, debugs and deploys Apify Actors, including their input and output schemas, using the Apify CLI. An Actor is a serverless program packaged as a Docker image that takes one JSON input, does one job and writes results to a dataset or key-value store. The skill checks that the `apify` CLI is installed and logged in, recommends installing through npm or Homebrew, and logs in with `apify login` or an `APIFY_TOKEN` environment variable, keeping the token out of shell history, source and logs.

When should I use Apify Actor Development?

Apify Actor Development fits situations like: building a new Apify Actor from scratch; debugging or changing the code of an existing Actor; writing or updating `.actor` input and output schema files; pushing an Actor to the Apify platform.

How do I install Apify Actor Development in Claude Code?

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

How do I install Apify Actor Development in Codex?

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

Can I use Apify Actor 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-actor-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-actor-development, .gemini/skills/apify-actor-development, .github/skills/apify-actor-development and .opencode/skills/apify-actor-development in your project.

What does Apify Actor Development need to run?

Going by SKILL.md and its folder, Apify Actor Development needs the command-line tools its instructions call (npm, git, brew, pip, uv and python) and credentials named APIFY_TOKEN and APIFY_API_TOKEN. Our summary lists: The Apify CLI (`apify-cli`), installed with npm or Homebrew; An Apify account, logged in with `apify login` or an `APIFY_TOKEN`.

Does Apify Actor Development access the network?

SKILL.md names 5 domains. In commands or code: mcp.apify.com; the agent is likely to contact it when it follows the instructions. As links in the text: docs.apify.com, crawlee.dev, console.apify.com and raw.githubusercontent.com. This is read from the text; nothing was executed.

Is Apify Actor 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 Actor Development use?

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

How many tokens does Apify Actor Development use?

About 2.9k 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 6.9k tokens, read only when the agent opens those files.

What are the alternatives to Apify Actor Development?

Skills that share tags, products or a category with Apify Actor Development: Scraper Builder (jwynia/agent-skills, 165 stars), Apify Actorization (sickn33/agentic-awesome-skills, 47k stars), Crawlee (LeoYeAI/openclaw-master-skills, 2.2k stars) and Upgrading Mwaa Environments (aws/agent-toolkit-for-aws, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Apify Actor 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.