agentleFS
Sign inStart free
IvanCamposIvanCampos/agents/skills/opml-reader/SKILL.md

opml-reader

Skill5 starsChanged 9 months agoMITView on GitHub

Store OPML files and fetch latest posts across RSS/Atom feeds. Use when a user provides an OPML URL or file path, wants it saved under ~/Code/Files, or wants the newest entries aggregated across feeds (with optional JSON/TSV output, dedupe, and concurrency controls).

  • Installs packages

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use scripts/opml_reader.py to (1) store OPML from a URL and (2) list the latest posts across all feeds in the OPML.

    line 9
  2. Distinctive:

    Create a venv and install dependency:

    line 12
  3. Very specific:

    If the user supplies an OPML URL, store it under ~/Code/Files using store.

    line 36
  4. Distinctive:

    If the OPML file already exists, reuse it unless the user explicitly asks to overwrite.

    line 37
  5. Very specific:

    Run latest to aggregate posts and return the newest entries across feeds.

    line 38
  6. Very specific:

    Default output: text lines formatted as index.

    line 42
  7. Very specific:

    Use --format json or --format tsv if the user needs machine-readable output.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

OPML Reader

Overview

Use scripts/opml_reader.py to (1) store OPML from a URL and (2) list the latest posts across all feeds in the OPML. Output timestamps are ISO-8601 in UTC.

Quick Start

  1. Create a venv and install dependency:
python3 -m venv ~/Code/sandbox/.venv-opml-reader
~/Code/sandbox/.venv-opml-reader/bin/pip install feedparser
  1. Store an OPML file:
~/Code/sandbox/.venv-opml-reader/bin/python scripts/opml_reader.py store \
  "https://example.com/feeds.opml" \
  "~/Code/Files/feeds.opml"
  1. Fetch latest posts:
~/Code/sandbox/.venv-opml-reader/bin/python scripts/opml_reader.py latest \
  "~/Code/Files/feeds.opml" \
  --limit 5

Workflow

  • If the user supplies an OPML URL, store it under ~/Code/Files using store.
  • If the OPML file already exists, reuse it unless the user explicitly asks to overwrite.
  • Run latest to aggregate posts and return the newest entries across feeds.
  • Report partial results if some feeds fail (network timeouts are expected on large lists).

Output Options

  • Default output: text lines formatted as index. title | feed | date | link.
  • Use --format json or --format tsv if the user needs machine-readable output.
  • Dedupe is on by default. Use --no-dedupe if the user wants raw results.
  • Adjust --workers and --timeout for large or slow feed lists.

Resources

scripts/

  • scripts/opml_reader.py: Store OPML files and list latest posts across RSS/Atom feeds.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free