agentleFS
blueskynexusblueskynexus/claude-skills/mt-newswires-analyst/SKILL.md

mt-newswires-analyst

Skill1 starsChanged 3 months agoMITView on GitHub

Fetches and analyzes real-time financial news from MT Newswires for specific stocks, sectors, or market themes. Use this skill whenever the user asks about recent news for a stock ticker, oil companies, energy sector, market updates, analyst rating changes, insider trades, or any query like "what's happening with [company/sector]", "latest news on [ticker]", "oil company news", "energy market update", or "give me a briefing on [topic]". Always use this skill when MT Newswires is connected and the user wants current financial news — even casual asks like "any news on Tesla?" or "what's going on in energy today?" should trigger it.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Always call MT Newswires:current_date first to anchor date-based queries.

    line 51
  2. Distinctive:

    Never fabricate quotes — paraphrase article bodies

    line 104
  3. Distinctive:

    If a story is headline-only (no body), note that and don't speculate on its content

    line 106
  4. Distinctive:

    Keep the briefing scannable — bullets and short paragraphs, not walls of text

    line 107
  5. Distinctive:

    If no relevant news is found, say so clearly and suggest broadening the date range or ticker list

    line 108

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

MT Newswires Analyst

Fetches and synthesizes real-time financial news from MT Newswires, then delivers a clear, structured briefing.


Step 1 — Understand the Request

Identify from the user's message:

  • Tickers (e.g. XOM, CVX, COP, BP, SHEL) — look for explicit symbols or company names you can map to symbols
  • Sector/theme (e.g. oil, energy, tech, macro) — use a representative basket of tickers
  • Date scope — default to today unless user says "this week" or specifies a range

Common oil/energy ticker mappings:

  • ExxonMobil → XOM
  • Chevron → CVX
  • ConocoPhillips → COP
  • BP → BP
  • Shell → SHEL
  • TotalEnergies → TTE
  • Halliburton → HAL
  • Energy sector broad → XOM,CVX,COP,BP,SHEL

Step 2 — Get Today's Date

Always call MT Newswires:current_date first to anchor date-based queries.


Step 3 — Fetch News

Call MT Newswires:fetch with:

  • dataset_name: mt_newswires_north_america (default) or mt_newswires_global for non-US focus
  • endpoint: data
  • product: edge
  • symbols: comma-separated tickers (e.g. "XOM,CVX,COP,BP,SHEL")
  • last: 10 to 20 depending on how much depth is needed
  • from_date / on_date: use today's date from Step 2 if user wants today's news only

Tip: For sector-level queries (e.g. "oil news"), use a basket of 4–6 major tickers rather than a single one.


Step 4 — Deduplicate and Prioritize

Articles often repeat across multiple tickers. Before summarizing:

  • Deduplicate by subkey (unique article ID)
  • Prioritize articles where isPrimary: true (the ticker is the main focus)
  • Sort by releaseTime descending (most recent first)
  • Flag headline_only_story articles — they have no body, just a headline

Step 5 — Synthesize and Present

Structure the output as a briefing:

## [Sector/Company] News Briefing — [Date]

### 🔑 Key Themes
[2-3 sentence summary of the dominant story lines across all articles]

### 📰 Top Stories
1. **[Headline]** — [1-2 sentence summary. Source: MT Newswires, [time]]
2. ...

### 📊 Analyst Activity
[Any price target changes or rating actions, grouped by company]

### 🏦 Insider Trades
[Any SEC filings / insider buy/sell activity]

### ⚡ Market Context
[Oil prices, sector index moves, macro backdrop if mentioned]

Rules:

  • Never fabricate quotes — paraphrase article bodies
  • Flag "Market Chatter" stories as unconfirmed rumors
  • If a story is headline-only (no body), note that and don't speculate on its content
  • Keep the briefing scannable — bullets and short paragraphs, not walls of text
  • If no relevant news is found, say so clearly and suggest broadening the date range or ticker list

Example Triggers

  • "Recent oil company news"
  • "What's happening with XOM today?"
  • "Give me an energy sector briefing"
  • "Any analyst ratings changes on Chevron?"
  • "Latest news on BP and Shell"
  • "Insider trades at ConocoPhillips"
  • "What's driving energy stocks today?"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.