Fetch the latest content from configured sources and output a concise news summary.This skill does not make HTTP requests directly, all network operations are delegated to search-and-fetch for execution.
Source configuration
All sources are defined in config/sources.yaml. Read that file to learn the currently available topics, direct URL sources, and default topics for the daily briefing.
For fetch strategy details, see references/fetch-strategy.md; for output format templates, see references/output-template.md。
Read depth
This skill supports two read depths, determined during Step 1 intent parsing:
| Depth | Trigger signal | Behavior |
|---|---|---|
| Shallow read (default) | No special modifier | Fetch only the list page, output title + summary + link, and prompt at the end that a deep read is available |
| On-demand deep read | After viewing the list, the user says "read item 2", "deep read this", "expand the first item" | Fetch the detail page for the specified item and output the full content |
| Automatic deep read | "deep read", "full text", "detailed content", "read all", "expand all" | After fetching the list, automatically fetch the details of the first N items (default N=3), executed in parallel |
The user says "help me look at the detailed content of today's agents-radar issues" → automatic deep read The user says "give me a Hacker News briefing" → shallow read, with a prompt at the end
Workflow
Step 1 — Intent parsing
Based on the user input, simultaneously determinesourceandread depth：
Source determination：
| User intent | Basis for determination | Handling method |
|---|---|---|
| Daily briefing | "today's news", "morning report", "evening report", "briefing", no specific topic | Use daily_briefing_topics the configured topics in |
| Specified topic | Mentions a specific field (AI, cryptocurrency, new energy...) | Match the corresponding key in topics corresponding key in |
| Specified source | Mentions a specific website/media name | Match from direct_sources match in |
| Custom query | The user provides specific keywords but they match no configuration | Directly call Search Mode with the user's keywords |
If the user's topic is not in the configuration, do not report an error—just search directly with the user's keywords; this is a natural fallback.
Step 2 — Level 1: Fetch the list
Based on the parsing result, inthe same response turncall all applicable fetch actions in parallel:
Search-type topics(from topics configuration):
- For each
search_queriesentry, call Search Mode - If
websiteslist is not empty, append in the querysite:domain.comrestrict sources - Multiple queries run in parallel, without waiting
Direct URL type(from direct_sources configuration):
- Call Fetch Mode to scrape the list page, receive with integrated mode
- Extract from the results each entry'stitle + URL + one-sentence description, take at most 10 items
Parallelism principle: at most 3-4 parallel fetches each time, execute in rounds when exceeded.
Step 3 — Level 2: Scrape details (depending on depth mode)
Shallow reading mode: skip this step, go directly to Step 4 output.
On-demand deep reading: after the user sees the list they specify items → for the specified URL call Fetch Mode, usestandalone modeoutput complete content (including five-dimension analysis).
Automatic deep reading: after list scraping is complete, immediately scrape in parallel the detail pages of the first N items (default N=3):
- Call Fetch Mode in parallel for N URLs, integrated mode (title + summary + key points, skip five-dimension analysis)
- N can be specified by the user ("deep read the first 5 items"), otherwise default 3
- After detail scraping is complete, merge into the output; each list item expands into a complete content block
For strategy details see references/fetch-strategy.md。
Step 4 — Consolidated output
Output in references/output-template.md format:
- Group by topic/source
- Deduplicate the same URL, keep the entry with the most complete content
- Timeliness first: items from the past 24 hours are placed in front
- Shallow reading ending: fixed append
输入序号或标题可深读全文，或说"深读前N条"自动展开
Delegation protocol
When calling search-and-fetch:
- List scraping / automatic deep reading of details → integrated mode (title + summary + key points, skip five-dimension analysis)
- On-demand deep reading of a single article → standalone mode (complete five-dimension analysis)
Clearly state the mode when delegating, to avoid search-and-fetch outputting extra content.
Extension notes
To add a new information source you only need to edit config/sources.yaml, no need to modify this file:
- New topic → in the
topicsblock add a key - New URL source → in the
direct_sourceslist append an entry - Adjust the daily briefing → modify the
daily_briefing_topicslist