ClawHub Skill Scraper avatar

ClawHub Skill Scraper

Pricing

from $2.00 / 1,000 record scrapeds

Go to Apify Store
ClawHub Skill Scraper

ClawHub Skill Scraper

Scrape AI agent skills from the ClawHub marketplace. Extracts SKILL.md definitions, metadata, stats, and changelogs for 80,000+ OpenClaw skills.

Pricing

from $2.00 / 1,000 record scrapeds

Rating

0.0

(0)

Developer

BowTiedRaccoon

BowTiedRaccoon

Maintained by Community

Actor stats

0

Bookmarked

16

Total users

1

Monthly active users

17 days ago

Last modified

Features

Limited permissions

Share

Scrape AI agent skill data from the ClawHub marketplace. Extract skill definitions (SKILL.md), metadata, download stats, install counts, star ratings, comment counts, changelogs, version tags, and author information for 80,000+ skills in the OpenClaw ecosystem.


ClawHub Skill Scraper Features

  • Extracts the full SKILL.md content of each skill, plus the list of files shipped alongside it
  • Collects marketplace stats: downloads, installs, stars, comments, version count
  • Two modes: metadata-only (fast) or full content with SKILL.md, changelog and version tags
  • Handles 80,000+ skills with automatic pagination and rate limiting
  • Outputs structured JSON with 19 fields per skill record

Who Uses ClawHub Skill Data?

  • AI tool directories — Index and categorize AI agent skills for discovery platforms
  • Developer analytics — Track skill adoption trends, download velocity, and popularity across the OpenClaw ecosystem
  • Competitive research — Monitor new skill releases, author activity, and marketplace growth
  • Dataset builders — Collect SKILL.md definitions to train or evaluate AI agents on real-world skill specifications
  • Market research — Analyze the AI agent skill marketplace for investment or product positioning

How the ClawHub Scraper Works

  1. List skills — Walks the ClawHub marketplace to collect every skill's metadata and marketplace stats
  2. Add content — For each skill, adds the full SKILL.md, the latest changelog, version tags, comment count and the list of supporting files

Step 2 only runs when downloadContent is enabled. With it disabled, the scraper returns listing metadata only and runs significantly faster.


Input

{
"maxItems": 50,
"downloadContent": true
}
FieldTypeDefaultDescription
maxItemsinteger50Maximum number of skills to scrape. Set to 0 for unlimited.
downloadContentbooleantrueFetch SKILL.md content, changelog, version tags and supporting-file list for each skill. When disabled, only listing metadata is collected (faster).

ClawHub Scraper Output Fields

{
"slug": "web-search",
"displayName": "Web Search",
"url": "https://clawhub.ai/openclaw/skills/web-search",
"version": "1.2.0",
"summary": "Search the web and return structured results",
"author": "openclaw",
"tags": { "latest": "1.2.0", "stable": "1.1.5" },
"downloads": 12450,
"installsAllTime": 8320,
"installsCurrent": 1540,
"stars": 89,
"comments": 12,
"versions": 8,
"changelog": "Added timeout configuration and retry logic",
"skillMd": "# Web Search\n\nSearch the web using...",
"supportingFiles": [],
"ownerId": "usr_abc123",
"createdAt": "2024-06-15T10:30:00Z",
"updatedAt": "2025-02-20T14:15:00Z",
"publishedAt": "2025-02-20T14:15:00Z"
}
FieldTypeDescription
slugstringUnique skill identifier (URL slug)
displayNamestringHuman-readable skill name
urlstringSkill page on clawhub.ai (null for non-skill packages)
versionstringLatest published version
summarystringShort skill description
authorstringSkill author from skill.yaml metadata
tagsobjectTag-to-version mapping (e.g. latest, stable)
downloadsnumberTotal download count
installsAllTimenumberLifetime install count
installsCurrentnumberCurrent active installs
starsnumberStar/favorite count
commentsnumberComment count
versionsnumberTotal published version count
changelogstringLatest version changelog text
skillMdstringFull SKILL.md file content
supportingFilesarrayPaths of the additional files shipped with the skill's latest version
ownerIdstringInternal owner identifier
createdAtstringSkill creation timestamp (ISO 8601)
updatedAtstringLast update timestamp (ISO 8601)
publishedAtstringLatest version publish timestamp (ISO 8601)

FAQ

How do I scrape all skills from ClawHub?

Set maxItems to 0 and downloadContent to true. The ClawHub Skill Scraper will paginate through the full marketplace and collect SKILL.md content for every skill. The default run timeout is sized for the whole catalog, so a full run completes unattended.

How much does the ClawHub Skill Scraper cost to run?

A full run with content for all 80,000+ skills runs at the default 256 MB of memory; the run charges one event per skill record. Metadata-only mode is significantly faster and cheaper.

What is a SKILL.md file?

SKILL.md is the standard definition file for AI agent skills in the OpenClaw ecosystem. It describes what the skill does, its inputs, outputs, and configuration. The ClawHub Skill Scraper returns the file exactly as the skill's latest version publishes it.

Can I scrape ClawHub without downloading SKILL.md content?

Yes. Set downloadContent to false to collect only marketplace metadata (names, stats, author) without the per-skill content. This mode is much faster and skips the content phase entirely.


Need More Features?

Need custom fields, filters, or a scraper for a different AI marketplace? File an issue or get in touch.

Why Use the ClawHub Skill Scraper?

  • Complete — Combines ClawHub marketplace data with full SKILL.md content, changelog and version tags in a single run
  • Flexible — Metadata-only mode for fast runs, full mode for complete skill definitions
  • Reliable — Rate limiting, retry logic, and graceful error handling for 80,000+ skill records

Further reading: Track Your Competitors Across 7 App Stores From One Toolkit