Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Rss Reader Pro

ASecurity

Master RSS readers: feed curation, triage workflows, filtering, and turning feeds into signal. Use when you want news and blogs on your terms instead of algorithmic timelines.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgo

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill rss-reader-pro --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rss Reader Pro?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Rss Reader Pro
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-rss-reader-pro/badge)](https://www.skillsdirectory.com/skills/aicodedecode-rss-reader-pro)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: rss-reader-pro
description: Master RSS readers: feed curation, triage workflows, filtering, and turning feeds into signal. Use when you want news and blogs on your terms instead of algorithmic timelines.
category: productivity
---

# RSS Reader Pro

## Overview

RSS puts you in charge of your information diet: you choose the sources, you control the timing, no algorithm decides what you see.

The reader is the inbox for the web: subscribe to blogs, news, journals, releases, even YouTube channels and podcasts.

Pro skill: ruthless feed curation, fast triage habits, and filters that turn firehoses into signal.

## When to use

- Replacing algorithmic news/social feeds with chosen sources
- Following many blogs, journals, or release notes efficiently
- Research requiring monitoring of many sources
- Reducing doomscrolling while staying informed
- Teams sharing curated industry intelligence

## Core concepts

- **Feed curation.**
  Subscribe deliberately: each feed must earn its place with consistent quality. 50 great feeds beat 500 mediocre ones.
- **Folders by purpose.**
  Group feeds: must-read, skim, reference, fun. Different folders get different triage standards and schedules.
- **Triage, don't read.**
  Scan titles, open the 10% worth reading, mark-all-read without guilt. The unread count is not a debt.
- **Filters and rules.**
  Keyword filters: highlight must-read topics, mute noise topics. Tame high-volume feeds (release notes, aggregators) with rules.
- **Read-later integration.**
  Worth-reading items go to a read-later app in one keystroke. The reader is triage; deep reading happens elsewhere.
- **Full-text extraction.**
  Use readability/full-text modes for truncated feeds. Don't click through to ad-infested pages when the reader extracts cleanly.
- **OPML portability.**
  Your subscription list as OPML: portable across readers, backed up, shareable. Never rebuild 200 feeds from memory.
- **Quiet by design.**
  No breaking-news alerts from the reader. Check on your schedule (1-2x daily), not the news cycle's.

## Practical workflow

1. **Choose a reader.**
   Cross-platform with good keyboard shortcuts, filters, and read-later integration. Commit to one.
2. **Subscribe deliberately.**
   Start with 20-30 known-great sources. Add new feeds only after sampling for two weeks.
3. **Organize into folders.**
   Must-read / skim / reference / fun. Assign triage rules per folder (read fully vs. scan titles).
4. **Set check schedule.**
   1-2x daily triage sessions, 15-20 min. Outside sessions, the reader is closed — no news grazing.
5. **Configure filters.**
   Keyword highlights for your topics; mute filters for noise. Especially for high-volume feeds.
6. **Connect read-later.**
   One-keystroke send to your read-later app. Triage fast; read deeply later, deliberately.
7. **Prune monthly.**
   Feeds unread for a month get cut. 'Maybe later' feeds get cut. The feed list is a garden, not an archive.
8. **Export OPML.**
   Backup your subscriptions. Share curated OPMLs with colleagues; import trusted ones to bootstrap new topics.

## Common pitfalls

- **Feed hoarding.**
  500 feeds, 10,000 unread. Unread count becomes anxiety instead of signal. Prune to what you actually read.
- **Unread-count guilt.**
  Treating unreads as obligation. Mark-all-read is a feature, not a failure — the good stuff resurfaces.
- **No triage discipline.**
  Opening every item 'just in case.' Scan titles ruthlessly; open <10%.
- **Algorithm envy.**
  Keeping algorithmic feeds 'for discovery' alongside RSS. Pick your model; the hybrid usually means the algorithm wins.
- **Truncated-feed clicking.**
  Clicking through to cluttered sites when full-text extraction exists. Read in the reader.
- **Never pruning.**
  Feeds die, quality drops, interests change. Monthly pruning keeps the signal high.
- **News grazing.**
  Checking the reader 20x daily like social media. Scheduled sessions; the news waits.
- **No read-later handoff.**
  Trying to read long pieces in the triage flow. Send to read-later; keep triage fast and shallow.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →