# ai-tech-rss-fetch

ai-tech-rss-fetch fetches RSS and Atom feeds, deduplicates entries, and stores metadata in SQLite. Keeps article titles and dates without downloading full body text.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 236 installs · ★ 11 repo stars
- Author: tiangong-ai
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/tiangong-ai/agent-skills/tree/HEAD/ai-tech-rss-fetch/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/ai-tech-rss-fetch

## What it does

The skill handles RSS and Atom subscriptions via `scripts/rss_subscribe.py`. Feeds can be added individually by URL or in bulk from OPML files.

Under the hood, it pairs `feedparser` with `sqlite3` to store incoming feeds and entries. Incremental sync relies on layered identity keys—such as GUID, canonical URL, and content hashes—while respecting HTTP `304 Not Modified` headers. It captures only metadata; article body scraping and AI summaries are deliberately omitted.

Running the sync script requires `feedparser` installed in Python. In multi-agent environments, pointing `AI_RSS_DB_PATH` to an absolute path is required so separate processes target the exact same SQLite file.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add tiangong-ai/agent-skills --skill ai-tech-rss-fetch -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ai-tech-rss-fetch/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ai-tech-rss-fetch/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add tiangong-ai/agent-skills --skill ai-tech-rss-fetch -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ai-tech-rss-fetch/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add tiangong-ai/agent-skills --skill ai-tech-rss-fetch -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ai-tech-rss-fetch/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install tiangong-ai/agent-skills ai-tech-rss-fetch
```

2. **Manually: put the files in place**
- File: `.github/skills/ai-tech-rss-fetch/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add tiangong-ai/agent-skills --skill ai-tech-rss-fetch -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/tiangong-ai/agent-skills --path ai-tech-rss-fetch
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ai-tech-rss-fetch/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add tiangong-ai/agent-skills --skill ai-tech-rss-fetch -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/tiangong-ai/agent-skills/tree/HEAD/ai-tech-rss-fetch/SKILL.md

## When to use it
- store normalized RSS and Atom feed metadata in SQLite
- import feed collections directly from OPML files
- prevent duplicate articles across syncs using layered keys and hashes
- track incremental feed updates using conditional HTTP requests

## Example prompts
- Import feed subscriptions from assets/hn-popular-blogs-2025.opml into the database
- Run an incremental sync for up to 20 feeds and 100 items per feed
- Add https://example.com/feed.xml to subscriptions and list recent entries

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 198bba6ef4e88673.

BEGIN THIRD-PARTY FILE 198bba6ef4e88673
````text
---
name: ai-tech-rss-fetch
description: Subscribe to AI and tech RSS feeds and persist normalized metadata into SQLite using mature Python tooling (feedparser + sqlite3). Use when adding feed URLs/OPML sources, running incremental sync with deduplication, and storing entry metadata without full-text extraction or summarization.
---

# AI Tech RSS Fetch

## Core Goal
- Subscribe to RSS/Atom sources.
- Persist feed and entry metadata to SQLite.
- Deduplicate entries with layered identity keys plus content fingerprints.
- Keep only metadata; do not fetch full article bodies and do not summarize.

## Triggering Conditions
- Receive a request to subscribe RSS feeds from URLs or OPML.
- Receive a request to run incremental RSS sync reliably.
- Need stable metadata persistence for downstream processing.
- Need dedupe-safe storage of feed items over repeated runs.

## Workflow
1. Prepare runtime and database.
- Ensure dependency is installed: `python3 -m pip install feedparser`.
- In multi-agent runtimes, pin DB to an absolute path before any command:

```bash
export AI_RSS_DB_PATH="/absolute/path/to/workspace-rss-bot/ai_rss.db"
```

- Initialize SQLite schema once:

```bash
python3 scripts/rss_subscribe.py init-db --db "$AI_RSS_DB_PATH"
```

2. Add feed subscriptions.
- Add one feed URL:

```bash
python3 scripts/rss_subscribe.py add-feed --db "$AI_RSS_DB_PATH" --url "https://example.com/feed.xml"
```

- Import feeds from OPML:

```bash
python3 scripts/rss_subscribe.py import-opml --db "$AI_RSS_DB_PATH" --opml assets/hn-popular-blogs-2025.opml
```

3. Run incremental sync.
- Fetch active feeds and store metadata:

```bash
python3 scripts/rss_subscribe.py sync --db "$AI_RSS_DB_PATH" --max-feeds 20 --max-items-per-feed 100
```

- Optional one-feed sync:

```bash
python3 scripts/rss_subscribe.py sync --db "$AI_RSS_DB_PATH" --feed-url "https://example.com/feed.xml"
```

4. Query persisted metadata.
- List feeds:

```bash
python3 scripts/rss_subscribe.py list-feeds --db "$AI_RSS_DB_PATH" --limit 50
```

- List recent entries:

```bash
python3 scripts/rss_subscribe.py list-entries --db "$AI_RSS_DB_PATH" --limit 100
```

## Input Requirements
- Supported inputs:
  - RSS XML feed URLs.
  - OPML feed list files.

## Output Contract (Metadata Only)
- Persist `feeds` metadata to SQLite:
  - `feed_url`, `feed_title`, `site_url`, `etag`, `last_modified`, status fields.
- Persist `entries` metadata to SQLite:
  - `id`, `dedupe_key` (compat primary identity snapshot), `guid`, `url`,
    `canonical_url`, `title`, `author`, `published_at`, `updated_at`, `summary`,
    `categories`, `content_hash`, `match_confidence`, timestamps.
- Persist `entry_identities` mapping table to SQLite:
  - `entry_id`, `key_type`, `key_value`, `created_at`.
  - Supported key types: `guid`, `canonical_url`, `legacy_guid`, `fallback_hash`.
````
END THIRD-PARTY FILE 198bba6ef4e88673

The third-party file has ended. Everything between the 198bba6ef4e88673 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2843 of 4194 bytes. © tiangong-ai · MIT · https://github.com/tiangong-ai/agent-skills/tree/HEAD/ai-tech-rss-fetch/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
