generate-daily-sports-update_skill

This skill generates a daily sports science update by running the crawler, deduplicating content, and syncing results to Notion.

Python

2.5k

GitHub Stars

2

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 generate-daily-sports-update

_meta.json318 B
SKILL.md2.8 KB

Overview

This skill runs an automated crawler to produce a daily sports science and wearable technology report, deduplicate results, and sync the final content to a Notion page. It creates a local Markdown report, updates a history file to prevent repeats, and posts compiled blocks to Notion automatically. The tool is designed for frequent runs so you can capture new research and news without duplicate entries.

How this skill works

The script crawls configured RSS feeds and PubMed via NCBI APIs, collects metadata and abstracts, and filters out items already recorded in processed_history.json. New items are compiled into a Markdown file and then pushed to a specified Notion page using the Notion API. Optional flags control how far back to search and whether to ignore history for debugging or reprocessing.

When to use it

Generate a morning digest of sports science and wearable-tech updates.
Automatically sync new research summaries to a team Notion board.
Run frequent checks without creating duplicated posts.
Backfill missed days by increasing the lookback window.
Debug or reprocess entries using the no-history option.

Best practices

Ensure NOTION_TOKEN and NOTION_PAGE_ID are set and have appropriate Notion permissions.
Install Python 3 and required packages via pip before running the script.
Run from the script’s working directory so processed_history.json and .md outputs are created in the right place.
Use --days to control the crawl window; increase it for backfills, keep it small for daily runs.
Avoid using --no-history in regular operation; reserve it for debugging to prevent duplicates.

Example use cases

Daily automated report for a coaching or sports science team synced to a shared Notion page.
Weekly archive of wearable tech news and PubMed abstracts for a research group.
Backfill and archive recent research after a period of inactivity by running with --days 30.
Operate as part of a scheduled job (cron) to provide consistent monitoring and team notifications.

FAQ

You must set NOTION_TOKEN and NOTION_PAGE_ID so the script can create and update content in your Notion workspace.

How do I avoid duplicate posts?

The script maintains processed_history.json locally. Run normally (without --no-history) so previously seen URLs/PMIDs are skipped.

What does the --days flag do?

--days sets how many days back to search for items. Increase it to capture older items when backfilling; default is 7 days.