Daily News Report
Run a daily orchestrated scrape of preset tech sources, dedupe with cache, and publish a filtered Markdown digest for staying current without manual tab hopping.
Overview
Daily News Report is an agent skill most often used in Idea (also Grow and Operate) that orchestrates browser scraping and caching to produce a daily technical Markdown digest.
Install
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill daily-news-reportWhat is this skill?
- v3.0 main-agent orchestration with sub-agent execution for fetches
- Browser scraping plus URL and content-hash caches to skip duplicates
- Preset source list (e.g. HN, HF papers, blogs) with per-source stats
- Daily Markdown report output with last-run metadata (items collected/published)
- Schema version 1.0 cache file for runs and deduplication
- Architecture labeled Daily News Report v3.0 with main agent + sub-agent + browser scraping
- Example last_run: 20 items collected and 20 published
Adoption & trust: 809 installs on skills.sh; 40.1k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You lose hours to fragmented news tabs and still miss papers or HN threads that matter for your stack.
Who is it for?
Indie builders who want a scheduled, cache-aware tech news pipeline inside their agent environment.
Skip if: Builders who need licensed newswire APIs only, zero network automation policy, or fully hands-off publishing without reviewing scraped content.
When should I use this skill?
You want a scheduled daily technical news Markdown report from a preset URL list with caching and quality filtering.
What do I get? / Deliverables
You receive a deduplicated daily Markdown report from your source list with run stats logged for the next tuning cycle.
- Daily Markdown news report
- Updated cache JSON with url_cache, content_hashes, and source_stats
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf on Idea because the primary job is continuous research intake before you commit build decisions. Research subphase matches curated external signal gathering rather than shipping code.
Where it fits
Scan HN and HF papers each morning before choosing what to prototype.
Pipe the Markdown digest into a newsletter draft or changelog inspiration file.
Raise priority on sources with better avg_quality_score in source_stats after a week of runs.
How it compares
Orchestrated scraping workflow—not a passive RSS reader skill with no agent delegation.
Common Questions / FAQ
Who is daily-news-report for?
Solo developers and agent users who want automated daily technical digests from HN, papers, and blogs with smart deduplication.
When should I use daily-news-report?
Use it during Idea research to scan markets and papers, in Grow content to fuel newsletters, and in Operate iterate when adjusting which sources earn priority from cache stats.
Is daily-news-report safe to install?
It uses browser scraping and network fetches against third-party sites; review the Security Audits panel on this page and treat outbound scraping as higher risk than read-only local skills.
SKILL.md
READMESKILL.md - Daily News Report
{ "schema_version": "1.0", "description": "Daily News Report 缓存文件，用于避免重复抓取和跟踪历史表现", "last_run": { "date": "2026-01-21", "duration_seconds": 180, "items_collected": 20, "items_published": 20, "sources_used": ["hn", "hf_papers", "james_clear", "fs_blog", "scotthyoung"] }, "source_stats": { "_comment": "记录每个源的历史表现，用于动态调整优先级", "hn": { "total_fetches": 0, "success_count": 0, "avg_items_per_fetch": 0, "avg_quality_score": 0, "last_fetch": null, "last_success": null } }, "url_cache": { "_comment": "已处理的 URL 缓存，避免重复收录", "_ttl_hours": 168, "entries": {} }, "content_hashes": { "_comment": "内容指纹，用于去重", "_ttl_hours": 168, "entries": {} }, "article_history": { "_comment": "已收录文章的简要记录", "2026-01-21": [] } } --- name: daily-news-report description: "Scrapes content based on a preset URL list, filters high-quality technical information, and generates daily Markdown reports." risk: unknown source: community date_added: "2026-02-27" --- # Daily News Report v3.0 > **Architecture Upgrade**: Main Agent Orchestration + SubAgent Execution + Browser Scraping + Smart Caching ## Core Architecture ``` ┌─────────────────────────────────────────────────────────────────────┐ │ Main Agent (Orchestrator) │ │ Role: Scheduling, Monitoring, Evaluation, Decision, Aggregation │ ├─────────────────────────────────────────────────────────────────────┤ │ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ 1. Init │ → │ 2. Dispatch │ → │ 3. Monitor │ → │ 4. Evaluate │ │ │ │ Read Config │ │ Assign Tasks│ │ Collect Res │ │ Filter/Sort │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘ │ │ │ │ │ │ │ │ ▼ ▼ ▼ ▼ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ 5. Decision │ ← │ Enough 20? │ │ 6. Generate │ → │ 7. Update │ │ │ │ Cont/Stop │ │ Y/N │ │ Report File │ │ Cache Stats │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘ │ │ │ └──────────────────────────────────────────────────────────────────────┘ ↓ Dispatch ↑ Return Results ┌─────────────────────────────────────────────────────────────────────┐ │ SubAgent Execution Layer │ ├─────────────────────────────────────────────────────────────────────┤ │ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ Worker A │ │ Worker B │ │ Browser │ │ │ │ (WebFetch) │ │ (WebFetch) │ │ (Headless) │ │ │ │ Tier1 Batch │ │ Tier2 Batch │ │ JS Render │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ │ │ ↓ ↓ ↓ │ │ ┌─────────────────────────────────────────────────────────────┐ │ │ │ Structured Result Return │ │ │ │ { status, data: [...], errors: [...], metadata: {...} } │ │ │ └─────────────────────────────────────────────────────────────┘ │ │ │ └─────────────────────────────────────────────────────────────────────┘ ``` ## Configuration Files This skill uses the following configuration files: | File | Purpose | |------|---------| | `sources.json` | Source configuration, priorities, scrape methods | | `cache.json` | Cached data, historical st