Historic News Skill
Research and annotate price-moving news events on the chart. Uses the
shared AgentSwarm service to spawn a research team.
The team
| Role |
Mandatory |
Tools |
Added when |
| Researcher |
✅ |
search_web, fetch_news, fetch_url |
Always — does the actual web queries for historic news |
| Analyzer |
✅ |
— |
Always — parses raw findings into structured NewsEvent objects with timestamps, categories, impact ratings, and direction |
| QA |
✅ |
— |
Always — filters out unsubstantiated events, checks timestamps are plausible, drops duplicates |
| Macro Researcher |
⏳ optional |
search_web, fetch_policy |
Added when the asset is a commodity, currency, or index (where macro news dominates price action) |
| Regulatory Researcher |
⏳ optional |
fetch_policy, fetch_url |
Added when the asset has active policy considerations (crypto, pharma, defense) |
Flow
- Team Planner picks which researchers to include based on asset class
- Researchers run in parallel — each does 2-4 targeted web searches for news in different periods (pre-rally, drawdown, range-bound, etc.)
- Analyzer merges findings into a structured event list with:
timestamp (unix seconds)headline, summary, source, urlcategory — earnings | regulatory | macro | product | sentiment | geopolitical | technicalimpact — high | medium | lowdirection — bullish | bearish | neutralprice_impact_pct — rough estimate of the event's price effect (optional)
- QA reviews: drops duplicates, flags timestamps outside the chart's data range, ensures each event has a credible source
- Final event list is pushed to the store → chart renders vertical markers → Historic News tab lists them
Output
- On chart: colored vertical line + dot at each event's timestamp. Red for bearish, green for bullish, orange for neutral. Hover for tooltip.
- Bottom-panel tab: timeline list of events sorted newest-first. Click an event → chart zooms to that time range + selected article detail appears on the right.
Input — interactive directives
The skill parses your message for steering directives so you can drive the swarm:
| You say |
What happens |
historic news for this chart |
Researches the chart's own asset over its date range (default) |
fetch oil news on this chart |
Researches oil, plots markers on the loaded chart (different asset!) |
plot AAPL news on the BTC chart |
Researches AAPL, tags markers for the BTC chart specifically |
show macro news on all charts |
Broadcasts — same news set renders on every open chart |
earnings news for TSLA |
Topic-filtered — only earnings queries run |
regulatory + macro news for AAPL |
Multiple categories combined |
Recognised category keywords: earnings, regulatory/SEC/policy, macro/fed/fomc/inflation/cpi, product/launch, geopolitical/war/sanctions. Recognised broadcast keywords: all charts, every chart, multiple charts, broadcast.
Requires a dataset loaded on the chart (the skill queries around the chart's visible date range and uses the chart's symbol as the default plot target).
How real news is fetched
The researcher does NOT hallucinate from training data. The processor:
- Generates 6-9 search queries from the topic + date range + categories
- Calls
web_search() (DuckDuckGo, rate-limited) for each
- Aggregates real results — real titles, real URLs, real snippets
- Feeds those real findings to the analyzer agent
The analyzer is then explicitly told: "use the EXACT URL from the search result. NEVER invent URLs." So every Reuters/Bloomberg link in the output is a link the search engine actually returned.
Example
User: "Find historic news events that moved AAPL"
→ Team: Researcher + Analyzer + QA. Researcher queries for AAPL
earnings, product launches, and macro shocks in the chart's date
range. Analyzer extracts ~15-25 events with timestamps + summaries.
QA drops 3 unsubstantiated ones. Final: 20 events plotted on
chart with category-coloured markers. Bottom panel shows timeline.
User clicks the "Q1 earnings surprise" event → chart zooms to
that date; right panel shows the full article summary + link.
1---2name: historic-news3description: Research historical news events that moved (or are moving) an asset's price and plot them as data points directly on the chart. Click a marker in the Historic News tab to zoom the chart to that event and read the article. Useful for identifying the fundamental drivers behind price action — earnings, regulation, product launches, macro shocks, geopolitical events.4---56# Historic News Skill78> Research and annotate price-moving news events on the chart. Uses the9> shared AgentSwarm service to spawn a research team.1011## The team1213| Role | Mandatory | Tools | Added when |14|---|---|---|---|15| **Researcher** | ✅ | `search_web`, `fetch_news`, `fetch_url` | Always — does the actual web queries for historic news |16| **Analyzer** | ✅ | — | Always — parses raw findings into structured NewsEvent objects with timestamps, categories, impact ratings, and direction |17| **QA** | ✅ | — | Always — filters out unsubstantiated events, checks timestamps are plausible, drops duplicates |18| **Macro Researcher** | ⏳ optional | `search_web`, `fetch_policy` | Added when the asset is a commodity, currency, or index (where macro news dominates price action) |19| **Regulatory Researcher** | ⏳ optional | `fetch_policy`, `fetch_url` | Added when the asset has active policy considerations (crypto, pharma, defense) |2021## Flow22231. Team Planner picks which researchers to include based on asset class242. Researchers run in parallel — each does 2-4 targeted web searches for news in different periods (pre-rally, drawdown, range-bound, etc.)253. Analyzer merges findings into a structured event list with:26 - `timestamp` (unix seconds)27 - `headline`, `summary`, `source`, `url`28 - `category` — earnings | regulatory | macro | product | sentiment | geopolitical | technical29 - `impact` — high | medium | low30 - `direction` — bullish | bearish | neutral31 - `price_impact_pct` — rough estimate of the event's price effect (optional)324. QA reviews: drops duplicates, flags timestamps outside the chart's data range, ensures each event has a credible source335. Final event list is pushed to the store → chart renders vertical markers → Historic News tab lists them3435## Output3637- **On chart**: colored vertical line + dot at each event's timestamp. Red for bearish, green for bullish, orange for neutral. Hover for tooltip.38- **Bottom-panel tab**: timeline list of events sorted newest-first. Click an event → chart zooms to that time range + selected article detail appears on the right.3940## Input — interactive directives4142The skill parses your message for steering directives so you can drive the swarm:4344| You say | What happens |45|---|---|46| `historic news for this chart` | Researches the chart's own asset over its date range (default) |47| `fetch oil news on this chart` | Researches oil, plots markers on the loaded chart (different asset!) |48| `plot AAPL news on the BTC chart` | Researches AAPL, tags markers for the BTC chart specifically |49| `show macro news on all charts` | Broadcasts — same news set renders on every open chart |50| `earnings news for TSLA` | Topic-filtered — only earnings queries run |51| `regulatory + macro news for AAPL` | Multiple categories combined |5253Recognised category keywords: `earnings`, `regulatory`/`SEC`/`policy`, `macro`/`fed`/`fomc`/`inflation`/`cpi`, `product`/`launch`, `geopolitical`/`war`/`sanctions`. Recognised broadcast keywords: `all charts`, `every chart`, `multiple charts`, `broadcast`.5455Requires a dataset loaded on the chart (the skill queries around the chart's visible date range and uses the chart's symbol as the default plot target).5657## How real news is fetched5859The researcher does NOT hallucinate from training data. The processor:60611. Generates 6-9 search queries from the topic + date range + categories622. Calls `web_search()` (DuckDuckGo, rate-limited) for each633. Aggregates real results — real titles, real URLs, real snippets644. Feeds those real findings to the analyzer agent6566The analyzer is then explicitly told: "use the EXACT URL from the search result. NEVER invent URLs." So every Reuters/Bloomberg link in the output is a link the search engine actually returned.6768## Example6970> User: *"Find historic news events that moved AAPL"*71>72> → Team: Researcher + Analyzer + QA. Researcher queries for AAPL73> earnings, product launches, and macro shocks in the chart's date74> range. Analyzer extracts ~15-25 events with timestamps + summaries.75> QA drops 3 unsubstantiated ones. Final: 20 events plotted on76> chart with category-coloured markers. Bottom panel shows timeline.77>78> User clicks the "Q1 earnings surprise" event → chart zooms to79> that date; right panel shows the full article summary + link.
spyderweb47