ai-tech-rss-fetch

Q: How do I install ai-tech-rss-fetch?

Run npx skills add https://github.com/tiangong-ai/agent-skills --skill ai-tech-rss-fetch in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ai-tech-rss-fetch/ (personal) or .claude/skills/ai-tech-rss-fetch/ (project).

by tiangong-aiAI & Agents

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.

Installs: 235
Last 24h: —
Trending rank: —
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/tiangong-ai/agent-skills --skill ai-tech-rss-fetch

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads ai-tech-rss-fetch automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

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

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:

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

Initialize SQLite schema once:

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

Add feed subscriptions.

Add one feed URL:

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

Import feeds from OPML:

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

Run incremental sync.

Fetch active feeds and store metadata:

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

Optional one-feed sync:

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

Query persisted metadata.

List feeds:

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

List recent entries:

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.
Do not store generated summaries and do not create archive markdown files.

Configurable Parameters

db_path
AI_RSS_DB_PATH (recommended absolute path in multi-agent runtime)
opml_path
feed_urls
max_feeds_per_run
max_items_per_feed
user_agent
seen_ttl_days
enable_conditional_get
Example config: assets/config.example.json

Error and Boundary Handling

Feed HTTP/network failure: keep syncing other feeds and record last_error.
Feed 304 Not Modified: skip entry parsing and keep state.
Missing guid and link: use hashed fallback identity and set match_confidence=low.
Dependency missing (feedparser): return install guidance.

Final Output Checklist (Required)

core goal
trigger conditions
input requirements
metadata schema
dedupe and sync rules
command workflow
configurable parameters
error handling

Use the following simplified checklist verbatim when the user requests it:

核心目标
输入需求
触发条件
元数据模型
去重与同步规则
命令流程
可配置参数
错误处理

References

references/input-model.md
references/output-rules.md
references/time-range-rules.md

Assets

assets/hn-popular-blogs-2025.opml (candidate feed pool)
assets/config.example.json

Scripts

scripts/rss_subscribe.py

FAQ

What does the ai-tech-rss-fetch skill do?

How do I install ai-tech-rss-fetch?

Run npx skills add https://github.com/tiangong-ai/agent-skills --skill ai-tech-rss-fetch in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ai-tech-rss-fetch/ (personal) or .claude/skills/ai-tech-rss-fetch/ (project).

Which AI agents can use ai-tech-rss-fetch?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is ai-tech-rss-fetch safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains ai-tech-rss-fetch?

It is published by tiangong-ai in tiangong-ai/agent-skills. It has 235 recorded installs.

More from tiangong-ai/agent-skills

View all →

email-smtp-send

tiangong-ai/agent-skills

Send emails through SMTP with optional local attachments and optional IMAP APPEND sync to Sent mailbox. Use when tasks need reliable outbound email delivery, attachment sending, SMTP connectivity checks, or cross-client sent-mail visibility (for example appending to "Sent Items" after SMTP send).

Productivity & Automation6.8K installs