| name | research |
| description | Gather source material for the radio show from any content source — web, HN, GitHub, papers, or general topics. |
Research
Gather source material for the radio show based on the user's prompt. The research strategy is agent-driven — you decide how to gather content based on what the user asks for.
Scripts
All research scripts live in skills/research/scripts/ and output to {workspace}/data/research/. They use only Python stdlib — no dependencies.
| Script | Command | Source |
|---|
fetch_hn.py | python3 skills/research/scripts/fetch_hn.py --workspace ./workspace --top 6 | Hacker News |
fetch_github.py | python3 skills/research/scripts/fetch_github.py --repo owner/repo --workspace ./workspace | GitHub repos |
fetch_url.py | python3 skills/research/scripts/fetch_url.py --url https://... --workspace ./workspace | Any URL |
Script Details
fetch_hn.py — Hacker News (two-phase)
Phase 1: Scan — grab top 10 story titles, scores, and comment counts (fast, no deep-diving):
python3 skills/research/scripts/fetch_hn.py --workspace ./workspace --mode scan --top 10
Output: {workspace}/data/research/hn-scan.md — a list of stories with IDs.
You read this file, pick the 2-3 most interesting stories for radio, then run phase 2.
When picking stories, SKIP anything related to politics, race, religion, international conflicts, historical controversies, gender/culture wars, or immigration. Stick to tech, programming, AI/ML, open source, science, startups, and developer culture.
