Fetch and filter Hacker News top stories. Use when user asks for tech news, HN updates, daily news digest, or wants to set up automated HN fetching. Supports keyword filtering (AI, programming, startups) and caching.
Scanned 9/7/2026
Install to Claude Code
npx -y skills add modbender/skill-library-mcp --skill hn-daily --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Hn Daily?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/modbender-hn-daily)More formats (shields.io, HTML) on the badges page.
---
name: hn-daily
description: Fetch and filter Hacker News top stories. Use when user asks for tech news, HN updates, daily news digest, or wants to set up automated HN fetching. Supports keyword filtering (AI, programming, startups) and caching.
---
# Hacker News Daily
Fetch top stories from Hacker News with keyword filtering and caching.
## Quick Start
```bash
python3 scripts/fetch_hn.py
```
## Options
```bash
python3 scripts/fetch_hn.py --limit 5 # Return 5 stories
python3 scripts/fetch_hn.py --min-score 100 # Only stories with 100+ points
python3 scripts/fetch_hn.py --no-cache # Force fresh fetch
python3 scripts/fetch_hn.py --format json # JSON output
```
## Proxy
Set `HTTP_PROXY` or `HTTPS_PROXY` environment variable if needed:
```bash
export HTTPS_PROXY=http://127.0.0.1:7890
python3 scripts/fetch_hn.py
```
## Output
Text format (default):
```
📰 Hacker News 精选
1. [AI] OpenAI releases new model
🔗 https://...
👍 892 分 | 💬 234 评论
```
JSON format (`--format json`): Array of story objects with id, title, url, score, etc.
## Caching
Results cached for 4 hours at `~/.cache/hn-daily/hn_cache.json`. Use `--no-cache` to bypass.
## Keywords
Default filter keywords: ai, llm, gpt, claude, openai, programming, python, rust, startup, machine learning, github, etc.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling