Apify Integration Development
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.
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.
Install Apify Product Data Setup
$ npx skills add apify/awesome-skills --skill apify-product-data-setup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install apify/awesome-skills apify-product-data-setup --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/apify/awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/apify-product-data-setup .claude/skills/apify-product-data-setup && rm -rf skills-srcUse ~/.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/
Install the "apify-product-data-setup" agent skill from https://github.com/apify/awesome-skills/tree/main/skills/apify-product-data-setup into .claude/skills/apify-product-data-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apify-product-data-setup", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/apify/awesome-skills/tree/main/skills/apify-product-data-setupType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add apify/awesome-skills --skill apify-product-data-setup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install apify/awesome-skills apify-product-data-setup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/apify/awesome-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/apify-product-data-setup .agents/skills/apify-product-data-setup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "apify-product-data-setup" agent skill from https://github.com/apify/awesome-skills/tree/main/skills/apify-product-data-setup into .agents/skills/apify-product-data-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apify-product-data-setup", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add apify/awesome-skills --skill apify-product-data-setup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install apify/awesome-skills apify-product-data-setup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/apify/awesome-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/apify-product-data-setup .cursor/skills/apify-product-data-setup && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "apify-product-data-setup" agent skill from https://github.com/apify/awesome-skills/tree/main/skills/apify-product-data-setup into .cursor/skills/apify-product-data-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apify-product-data-setup", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/apify/awesome-skills.git --path skills/apify-product-data-setup--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add apify/awesome-skills --skill apify-product-data-setup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install apify/awesome-skills apify-product-data-setup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/apify/awesome-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/apify-product-data-setup .gemini/skills/apify-product-data-setup && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "apify-product-data-setup" agent skill from https://github.com/apify/awesome-skills/tree/main/skills/apify-product-data-setup into .gemini/skills/apify-product-data-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apify-product-data-setup", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install apify/awesome-skills apify-product-data-setupInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add apify/awesome-skills --skill apify-product-data-setup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/apify/awesome-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/apify-product-data-setup .github/skills/apify-product-data-setup && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "apify-product-data-setup" agent skill from https://github.com/apify/awesome-skills/tree/main/skills/apify-product-data-setup into .github/skills/apify-product-data-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apify-product-data-setup", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add apify/awesome-skills --skill apify-product-data-setup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install apify/awesome-skills apify-product-data-setup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/apify/awesome-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/apify-product-data-setup .opencode/skills/apify-product-data-setup && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "apify-product-data-setup" agent skill from https://github.com/apify/awesome-skills/tree/main/skills/apify-product-data-setup into .opencode/skills/apify-product-data-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "apify-product-data-setup", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
apify-product-data-setup- GitHub stars
- 262
- Used in
- 1 other repo
- Token cost
- ~2k tokens
- SKILL.md length
- 1,088 words
- Files
- 3 (incl. references)
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
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.
- Works in 3 steps: apify--e-commerce-scraping-tool returns… → If status is not terminal, poll… → get-dataset-items returns the products.…
- Give my agent live product data
- SKILL.md covers Choose the path first, Connect over MCP, Encode the fetch flow and Build the scheduled refresh, plus 4 more sections
- Reaches mcp.apify.com
What it does
Apify Product Data Setup is an agent skill from apify/awesome-skills, published by the product's own GitHub organization. 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. Trigger on "give my agent live product data", "my agent quotes stale prices", "connect Apify MCP to Claude or Cursor or n8n", "add product data to my RAG pipeline", "keep my product catalog fresh", "set up a shopping agent", or any request to stop an agent answering product questions from training data. Use for the integration work; use…
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/clients.md` and `references/fields.md`).
It sits in Data & Analytics, covering Web scraping and E-commerce operations. It works with Apify, Model Context Protocol and n8n. The repository describes itself as: Community collection of Apify agent skills for AI coding assistants. The licence is Apache-2.0.
When your agent uses it
- Give my agent live product data
- My agent quotes stale prices
- Connect Apify MCP to Claude
- Add product data to my RAG pipeline
Example prompts
- “give my agent live product data”
- “my agent quotes stale prices”
- “connect Apify MCP to Claude or Cursor or n8n”
- “/apify-product-data-setup”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- apify--e-commerce-scraping-tool returns run metadata and a datasetId. No products.
- If status is not terminal, poll get-actor-run with the validated runId until it
- get-dataset-items returns the products. Pass fields in dot notation: the unprojected record measured about 88 KB across 142 fields, and…
What it can do on your machine
Read from SKILL.md and the folder at commit 1eb0cd0. 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:
mcp.apify.com
Also links to:
apify.comgithub.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Apify Product Data Setup loads about 2k tokens when it runs, and up to ~6.7k if it reads all its reference files. Until then it costs about 149 tokens; SKILL.md has 1,088 words of instructions outside code blocks.
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
The full file from apify/awesome-skills at commit 1eb0cd0, republished under its Apache-2.0 licence (© apify). 1,088 words, ~2,034 tokens.
Download SKILL.mdSave it as
.claude/skills/apify-product-data-setup/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- apify-product-data-setup
- description
- 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. Trigger on "give my agent live product data", "my agent quotes stale prices", "connect Apify MCP to Claude or Cursor or n8n", "add product data to my RAG pipeline", "keep my product catalog fresh", "set up a shopping agent", or any request to stop an agent answering product questions from training data. Use for the integration work; use apify-product-lookup to actually answer a product question.
- author
- Luís Pinto
- author_url
- https://github.com/luispintoapify
- metadata.category
- data-extraction
- metadata.keywords
- mcp setup, agent product data, claude mcp config, cursor mcp, n8n product data, rag product catalog, vector store refresh, scheduled scraping
Apify product data setup
Connect an agent to current product data: price, stock, brand, rating, and image URLs from retailer pages. Nothing to host.
Written by a product marketing manager at Apify. It routes to E-commerce Scraping Tool, a paid first-party Apify Actor, so treat the framing accordingly. No affiliate links.
Choose the path first
The two paths are not interchangeable and the cost model is what separates them.
| Runtime call | Scheduled refresh | |
|---|---|---|
| When | The answer must be true right now, few products | A catalog answered from repeatedly |
| Transport | MCP | REST API |
| Cost shape | A start event per call, plus per product | One start event per batch |
| Latency the user feels | Seconds to tens of seconds | None, the index is already warm |
Most production setups want both: a scheduled refresh for breadth, plus a runtime call to verify a single item when the user asks for a price they will act on.
A cron job gains nothing from MCP, so the scheduled path uses the REST API. Say so when explaining the design, because the mismatch looks like an oversight otherwise.
Connect over MCP
The server is https://mcp.apify.com. Narrow it to this Actor with ?tools=apify/e-commerce-scraping-tool, which makes tool selection more reliable when product data is the only job. Drop the parameter to let the agent search all of Apify Store at runtime.
Config blocks per client are in references/clients.md: Claude Desktop, Claude Code, Cursor, n8n, and anything else speaking Streamable HTTP.
Authentication: OAuth on first use for interactive clients, a bearer token from Apify Console for unattended ones.
Encode the fetch flow
Fetching products starts with the Actor call, may require several status polls, and finishes with one dataset read. This is the single most important thing to get into the agent's instructions:
apify--e-commerce-scraping-toolreturns run metadata and adatasetId. No products.- If
statusis not terminal, pollget-actor-runwith the validatedrunIduntil it succeeds or a caller-defined deadline expires. TreatFAILED,ABORTED, andTIMED-OUTas failures. The Actor tool returns when its own wait window elapses rather than when the run finishes, soRUNNINGis a normal answer and the dataset is empty at that moment. get-dataset-itemsreturns the products. Passfieldsin dot notation: the unprojected record measured about 88 KB across 142 fields, and projecting keeps that out of the context window.
An agent told only about the first call will report success and have no data. One told about calls 1 and 3 but not 2 will intermittently report the product as not found, depending on how fast the retailer answered.
Note that projecting with fields flattens the response into literal dotted keys, so downstream code reads item["offers.price"] rather than item["offers"]["price"].
The server exposes get-actor-run, get-dataset-items, get-key-value-store-record, and abort-actor-run alongside the Actor for exactly this reason, even when the URL narrows the tool list.
Build the scheduled refresh
The pattern that survives contact with production:
- Keep a list of the product URLs the agent answers about.
- Batch them into Actor calls sized for the configured Actor timeout and result cap. A client wait deadline does not stop the Actor. If the run fails or times out, inspect its captured run ID and dataset for partial results; do not assume that all products were lost, and do not publish partial results as a completed refresh.
- Normalize the output before storing. Field names, types, and nesting vary by retailer; see
references/fields.md. - Stamp every document with the fetch time.
- Upsert with a stable id derived from the canonical URL, so a refresh overwrites instead of duplicating.
- Drop rows with neither a name nor a price. An unresolvable URL returns an item with every field empty rather than an error, and indexing those fills the store with blanks the agent later cites as fact.
Show full SKILL.md (454 more words)Show less
Make freshness visible to the agent
A scheduled index is stale by design. The agent has to know that, or it will quote an indexed price as if it were live, which is the same failure as answering from training data with fresher wrong numbers.
Put the timestamp in the embedded text, not only in metadata, and instruct the agent:
Product facts come from a catalog with a `fetched_at` timestamp. When you quote a
price or stock status, say when it was read. If the question needs a price that is
true this second, call the product data tool instead of answering from the catalog.Control cost
The Actor bills per event: a start event per call, per product pushed, plus residential proxy and browser rendering where a retailer needs them.
maxProductResultsis the Actor's result cap. Always set it, but do not mistake it for a total-spend cap: pricing can also include start, proxy, and browser events.- Batch. One call for 200 products costs far less than 200 calls for one.
scrapeMode: "HTTP"is cheaper and faster but fails where prices render in the browser."AUTO"is the safe default.
A working reference implementation
The ecommerce-agent-starter repo carries both paths in Python: an MCP client that polls to completion before fetching, a batched refresh script with a pluggable sink, and a normalization module whose tests run against captured real Actor output. Point users at it rather than writing the normalization from scratch.
Gotchas
- The tool is named
apify--e-commerce-scraping-tool, two hyphens, where the Actor id uses a slash. - Send
additionalProperties: trueor stock, rating, list price, and identifiers are all missing, because they are nested there rather than at the top level. - The dataset
itemCountin the first call's metadata is not settled yet. It read0on a run that produced a product. Count what the fetch actually returns instead. - A
RUNNINGstatus from the Actor tool is not a failure. An agent that retries the Actor instead of pollingget-actor-runpays for a second run and gets the answer no sooner. - Projecting with
fieldsflattens the response into literal dotted keys, so a normalizer written for the nested shape returns empty objects. Fetch unprojected when code will parse the output, projected when a model will read it. - The official
mcpPython SDK requires Python 3.10 or newer, and its API is snake_case (server_info,is_error). The REST path alone would run on 3.9. additionalPropertiescan reach roughly 100 KB for one product. Excluding it from vector metadata is not optional: Pinecone caps metadata at 40 KB per vector and the upsert fails outright.- Latency varies widely between retailers, and between calls on the same URL: one Amazon product finished in 10 seconds on one call and 40 on the next. Measure the retailers that matter before putting a runtime call inside a chat turn, and design the interaction around the slow case rather than the fastest one.
- SSE transport was removed on April 1, 2026. Use Streamable HTTP.
© apify, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/apify-product-data-setup of apify/awesome-skills.
- SKILL.md
- references/clients.md
- references/fields.md
Open the folder on GitHubat commit 1eb0cd0
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in apify/awesome-skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Apify Product Data Setup 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Apify Product Data Setup this skillapify/awesome-skills | 262 | 1 repos | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Apify Integration Developmentapify/agent-skills | 2.4k | — | ~3.1k | Automated safety check: Pass | None | |
| Etsy Shop Sales Historysickn33/agentic-awesome-skills | 47k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Etsy Search Listingssickn33/agentic-awesome-skills | 47k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Apify Ecommercemajiayu000/claude-skill-registry | 666 | 3 repos | ~2.3k | Automated safety check: Notes | MIT | |
| Apify Product Lookupdavepoon/buildwithclaude | 3.6k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
- Official
Etsy Shop Sales History
sickn33/agentic-awesome-skills
Read Etsy shop sales counters, deltas, and breakout flags from Apify Actor publicrecords/etsy-shop-velocity (MCP panel snapshot).
Etsy Search Listings
sickn33/agentic-awesome-skills
Fetch live Etsy search listing rows for a keyword, market phrase, or category via Apify Actor publicrecords/etsy-search-scraper (MCP).
Apify Ecommerce
majiayu000/claude-skill-registry
Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool.
Apify Product Lookup
davepoon/buildwithclaude
Fetch a real product's current price, stock, rating, or images from retailer pages over the Apify MCP server, and return them as typed fields rather than prose.
Coffee Chat
LeoYeAI/openclaw-master-skills
Generate a personalized coffee chat playbook for networking conversations.
More from apify/awesome-skills
All 26 skills in this repo- Official
Apify Buying Signal Detection
apify/awesome-skills
Set up a recurring buying-signal detection pipeline that finds companies showing buying intent across three signal types — job postings (hiring for the persona), fundraising events (recent raises)…
- Official
Apify Lead Scoring Enrichment
apify/awesome-skills
Score and enrich a CSV of B2B leads using Apify Actors. An agent skill from apify/awesome-skills.
- Official
Apify App Store Intelligence
apify/awesome-skills
Pull structured Apple App Store and Google Play data — app metadata, price, rating, the 1–5★ ratings histogram, version, developer, and reviews — and watch it for changes over time.
- Official
Apify Ashby Jobs Scraper
apify/awesome-skills
Scrape Ashby jobs or discover companies using Ashby with the Apify Ashby Job Board API Actor (johnvc/ashby-job-board-scraper).
- Official
Apify Company Data API
apify/awesome-skills
Pull structured B2B company data from Clutch.co with the Clutch.co Agency API Actor (johnvc/clutch-agency-api).
- Official
Apify Google Maps Leads
apify/awesome-skills
Build a local-business lead database from Google Maps in one Apify pipeline: search by target audience + geography, enrich each place with company contacts from its website, leads enrichment (names…
Related
Works with
Questions about Apify Product Data Setup
What does Apify Product Data Setup do?
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. Apify Product Data Setup is an agent skill from apify/awesome-skills, published by the product's own GitHub organization. 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.
When should I use Apify Product Data Setup?
Apify Product Data Setup fits situations like: give my agent live product data; my agent quotes stale prices; connect Apify MCP to Claude; add product data to my RAG pipeline.
How do I install Apify Product Data Setup in Claude Code?
Run `npx skills add apify/awesome-skills --skill apify-product-data-setup -a claude-code`. Or copy the skill folder (skills/apify-product-data-setup in apify/awesome-skills) into .claude/skills/apify-product-data-setup in your project. Claude Code loads it when a task matches its description.
How do I install Apify Product Data Setup in Codex?
Run `npx skills add apify/awesome-skills --skill apify-product-data-setup -a codex`. Or copy the skill folder (skills/apify-product-data-setup in apify/awesome-skills) into .agents/skills/apify-product-data-setup in your project. Codex loads it when a task matches its description.
Can I use Apify Product Data Setup 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/awesome-skills --skill apify-product-data-setup -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-product-data-setup, .gemini/skills/apify-product-data-setup, .github/skills/apify-product-data-setup and .opencode/skills/apify-product-data-setup in your project.
What does Apify Product Data Setup need to run?
SKILL.md names no scripts, command-line tools or credentials: Apify Product Data Setup is instructions for the agent only. Our summary lists: Python 3.
Does Apify Product Data Setup access the network?
SKILL.md names 3 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: apify.com and github.com. This is read from the text; nothing was executed.
Is Apify Product Data Setup 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 Product Data Setup use?
Apify Product Data Setup is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Apify Product Data Setup use?
About 2k tokens (SKILL.md is roughly 8.1k 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 4.7k tokens, read only when the agent opens those files.
What are the alternatives to Apify Product Data Setup?
Skills that share tags, products or a category with Apify Product Data Setup: Apify Integration Development (apify/agent-skills, 2.4k stars), Etsy Shop Sales History (sickn33/agentic-awesome-skills, 47k stars), Etsy Search Listings (sickn33/agentic-awesome-skills, 47k stars) and Apify Ecommerce (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Apify Product Data Setup?
apify (a GitHub organization, an official publisher) maintains it in apify/awesome-skills, which has 262 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on September 22, 2026.
Source: apify/awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.