Guide · Agent skill
How to use the Apify Output Schema Generator agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
The apify-generate-output-schema skill teaches an AI agent to write the JSON files that tell the Apify Console how to display an Actor's results. It is written for developers who build or maintain Apify Actors and want correct result views without writing the schema files by hand. After this guide you will know what the skill does, how to install it, how to ask for it in plain language, and what to check before you trust the output.
Apify Output Schema Generatorsickn33/agentic-awesome-skills · MIT Download the skill Quick start
- 1Get the skill files. Download the ZIP of the apify-generate-output-schema skill from this page and unzip it.
- 2Place the skill folder. Move it into ~/.claude/skills/ for personal use, or into your project's .claude/skills/ folder for a shared install.
- 3Open your Actor project. Make sure the project has a .actor/ directory with actor.json and the Actor's source code.
- 4Ask for the schemas. Describe the goal in plain language, for example asking the agent to create output schemas for this Actor.
- 5Review the output. Check the generated dataset_schema.json, output_schema.json, key_value_store_schema.json and actor.json against your code and types.
- 6Test in Apify Console. Run the Actor and confirm the results display as you expect in the Console views.
What is an agent skill?
An agent skill is a folder containing a SKILL.md file with instructions that an AI agent can load when a task matches them. This skill's SKILL.md tells the agent how to generate Apify output schemas step by step.
The skill is packaged as a single file, SKILL.md, in the apify-generate-output-schema folder.
What the skill makes the agent do
The output schema tells Apify Console how to display run results. The agent reads the Actor's source code to find what data it pushes to the dataset or key-value store, then creates dataset_schema.json, output_schema.json and key_value_store_schema.json (if the Actor uses a key-value store), and updates actor.json.
The skill also tells the agent to match conventions already used in the repository, to reuse existing type definitions, and to avoid real personal data in examples.
- Finds calls such as Actor.pushData, Actor.push_data, Actor.setValue and Actor.set_value in JavaScript, TypeScript or Python code
- Looks for existing schemas in the repository and copies their naming, description style and formatting
- Uses existing TypeScript interfaces or Python type classes as the source of truth where they exist
- Puts every possible output field in the properties section, then selects a subset for the overview view
How to install the skill
Download the ZIP of this skill from this page and unzip it. Put the skill folder in ~/.claude/skills/ for a personal install, or in a project's .claude/skills/ folder to share it with one repository.
If you use the Claude apps instead, upload the skill under Settings, then Capabilities, then Skills.
- Personal: ~/.claude/skills/
- Project only: .claude/skills/ inside your project
Requirements before you start
The skill assumes you already have an Apify Actor project. It needs a .actor/ directory containing actor.json, and the Actor's source code in JavaScript, TypeScript or Python. Without these, the agent has no code to analyze.
The skill does not run scripts and does not use the network, according to its listing.
- An Apify Actor project with a .actor/actor.json file
- Actor source code in JavaScript, TypeScript or Python
How to trigger the skill with natural requests
Ask the agent in plain language from inside your Actor project. Name the goal, such as creating or updating output schemas, and the agent should pick up the skill because its description covers creating and updating Actor output schemas.
Requests that work well name the Actor and the files you want, for example asking for dataset_schema.json and output_schema.json for the scraper in the current project.
- Create the output schemas for this Actor based on its source code
- Update dataset_schema.json and key_value_store_schema.json after I changed what the Actor pushes
- Generate output schema files for the Actor and match the other Actors in this repo
Review the generated schema before you use it
The skill tells the agent to derive nullability from evidence and to check the schema against any TypeScript types and the code that produces the values. Code can be stale or branch-dependent, so the agent may infer types that do not match what your current code outputs.
Check that every output field is listed in fields.properties, that required lists only fields that are truly always present, and that examples contain no real user IDs, usernames or personal data.
- Confirm every field the Actor can output appears in fields.properties
- Check required and nullable against all runtime branches
- Confirm example values are anonymized
- Remember that nullable is an Apify extension to JSON Schema draft-07
{"type": "string", "description": "Title of the scraped item", "nullable": true, "example": "Example Item Title"}What people use it for
- Creating dataset_schema.json and an overview view for a new scraper Actor
- Updating output schemas after new fields were added to the data the Actor pushes
- Bringing one Actor's schema formatting in line with the others in a multi-Actor repository
- Adding a key-value store schema for an Actor that saves files or records under keys
Frequently asked questions
How do I install the apify-generate-output-schema skill?
Download the ZIP from this page and unzip it. Place the folder in ~/.claude/skills/ for personal use or in a project's .claude/skills/ folder. In the Claude apps, you can instead upload it under Settings, then Capabilities, then Skills.
What do I need to use this skill?
You need an Apify Actor project with a .actor/actor.json file and source code in JavaScript, TypeScript or Python. The skill assumes these exist and will not work from nothing.
Is the skill free and what is its licence?
The skill is listed under the MIT licence. This guide does not cover pricing beyond what the listing states.
Does the skill run scripts or use the internet?
According to its listing, it runs no scripts and uses no network. It works by reading your code and writing JSON files.
Why does the generated schema look wrong?
The agent infers types from code, which may be stale or branch-dependent. Compare the schema with your current code and runtime branches, then correct it before relying on it.
Can I use it for non-developers or without an Apify Actor?
No. The skill is not meant for people without an Apify Actor project, because it expects an existing .actor/ directory and source code to analyze.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
This skill suits Apify Actor developers who want correct Console result views and consistent schemas across several Actors in one repository. Skip it if you have no Actor project or want output you can use without reviewing it against your code.
Download the skill