auto-building_skill

This skill helps you auto-build tailored information collection systems by defining sections, categories, and data sources and automating collection, review,

Python

2.6k

GitHub Stars

5

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill auto-building

_meta.json288 B
CHANGELOG.md325 B
package.json612 B
README.md1.6 KB
SKILL.md6.1 KB

Overview

This skill builds a customizable automated information-collection and publishing system based on the AUTO-BUILDING source. It lets you define sections, categories, and data sources so the system automatically scrapes, reviews, and publishes collected content. The skill is aimed at quickly producing tailored content aggregation platforms with minimal coding changes.

How this skill works

You specify desired primary and secondary categories and add data sources in the configuration files. The system uses scheduled or manual scraping scripts to collect content from GitHub, RSS, directory sites, or custom URLs, then routes items into a review queue. Approved items move to the published store and appear on the site; administrators control scraping rules, filters, and content types via the admin UI.

When to use it

Create a daily tech news briefing aggregating multiple RSS feeds
Monitor competitor product pages and track price or listing changes
Aggregate industry-specific news (finance, healthcare, AI) into a single portal
Build a curated resource or tool directory (AI tools, open-source projects)
Prototype a custom information hub without rewriting scraping pipelines

Best practices

Only change configuration files (config/sources.json and src/data/resources.ts) for customization
Define clear categories and granular data-source entries to simplify filtering
Use the admin UI to add or refine scraping rules and keyword filters rather than editing scripts
Run scraping and review workflows regularly (npm run daily or scheduled tasks) and audit pending items
Start with RSS and GitHub sources for stable, structured inputs before adding custom pages

Example use cases

News morning brief: collect from 36kr and Huxiu, filter today's articles, publish a daily digest
E-commerce price monitor: track Amazon and Taobao product pages for price or stock changes
AI tools index: ingest GitHub repos and classify tools into subcategories like autocomplete and testing
Sector aggregator: compile healthcare research updates from selective journals and feeds

FAQ

Edit config/sources.json to add primary/secondary categories and data sources, and update src/data/resources.ts for category labels.

Can I add custom scraping rules?

Yes — add rules via the admin UI under the 'scraping rules' tab. You can use regex or AI-generated rules and set filters or content types.