News scout
A forkable content system for AI agents that scouts signals, drafts in your voice, and edits out generic AI writing.
npx -y skills add AlexHoudz/content-os-starter-kit --skill news-scoutAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Scout fresh content signals, rank them, and turn them into a few post-worthy angles. Use when building a daily or weekly content brief, reviewing news in a niche, comparing source quality, or deciding what is actually worth posting about. Best for workflows like source scan, angle ranking, and draft handoff.
SKILL.md
2.1 KB, 435 tokens by cl100k_base, as published. Nobody here has run it
News Scout
Overview
Reduce noisy sources into a short list of angles worth writing about.
The job is not to summarize headlines. The job is to find signals, judge them, and explain why they matter now.
Core workflow
1. Read the right inputs
Start with the user's real source list.
Prefer:
- the sources in
templates/SOURCES.md - a narrow niche
- a short freshness window
- low-saturation signals
If the source list is weak, say so.
2. Filter hard
Reject items that are:
- already everywhere
- too generic
- not relevant to the user's audience
- just a headline with no second-order effect
- impossible to turn into a strong point of view
Weak-day detection is part of the skill. Do not force a fake winner.
3. Rank angles, not headlines
For each candidate, define:
- the angle title
- the thesis
- why now
- why it fits the user
- saturation risk
- weakness
- proof or source link
4. Hand off to drafting
Do not write full posts by default. End with 1 to 3 good angles unless the user explicitly asks for draft copy too.
Output pattern
Return the shortlist in a compact format:
- best option first
- clear reason it is worth posting
- saturation note
- one-line weakness
When helpful, use the criteria in references/angle-evaluation.md.
Quality bar
A good scout result should feel like:
- one clear signal
- one clear tension
- one real reason the user should care
- less noise than their feed
A bad scout result feels like:
- generic AI news recap
- obvious funding / launch filler
- points everyone will post by noon
Important rule
Optimize for asymmetry: high relevance, low saturation, strong point of view.
Resources
- Read
references/angle-evaluation.mdwhen ranking weak vs strong angles. - Read
references/source-review.mdwhen the source list or niche still feels fuzzy.