Skip to content
SkillModel-led2,836 tokens in use

Market News Analyst

A six-step method that gathers the last 10 days of market news by web search, scores each event for impact, and writes a ranked Markdown report of how equities and commodities reacted.

7,428 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/market-news-analyst

Skill label

measured from its files

What installing Market News Analyst costs

115tokens idle
2,836tokens in use
18,081tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure23/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

Market News Analyst walks Claude through a review of major market-moving news from the past 10 days: central bank decisions, inflation and jobs data, mega-cap earnings, geopolitical events and commodity moves. It searches the web for each category, scores every event on price impact, breadth and forward-looking significance, and compares the observed reaction with historical patterns.

The output is an English Markdown report ordered from highest to lowest impact. The skill describes and quantifies what happened. It does not recommend trades.

What You Get

  • A ranked list of the past 10 days of market-moving events, highest impact first
  • Impact scores built from price impact, breadth and forward-looking significance
  • A multi-asset reaction review covering equities, Treasury yields, commodities, currencies and VIX
  • A flag on reactions that were amplified, dampened or inverted against historical patterns
  • A Markdown report named market_news_analysis_START_to_END.md that you can ask Claude to save

Common Use Cases

  • Reviewing how the latest FOMC, ECB or BOJ decision moved equities and yields
  • Summarising the week’s most important market news with a stated impact ranking
  • Checking how geopolitical headlines fed through to oil, gold and other commodities
  • Reviewing mega-cap earnings and the reaction across their sector

What Makes It Unique

The method centres on a numeric impact score and on causation discipline. Each event gets a price impact score, a breadth multiplier and a forward-looking modifier, and the report lists events from the highest score down. It also names reaction patterns (consistent, amplified, dampened, inverse) and has a dedicated step for separating cause from timing. It needs no API keys or paid data feeds, only the web tools Claude already has.

Under The Hood

The skill is instructions and reference files, with no scripts of its own. Claude uses its WebSearch tool to run queries across news categories and its WebFetch tool to open pages from official sources such as the Federal Reserve, SEC and BLS and from major news outlets. It loads reference files on event patterns, trusted sources, geopolitical and commodity correlations, corporate news impact and the report template, depending on what it finds. Nothing is written automatically; the Markdown report is saved to a reports folder only when you ask for it.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers